Modifier and Type | Field and Description |
---|---|
FImage |
Patch._W
Gain
|
protected FImage |
Patch.im_ |
Modifier and Type | Method and Description |
---|---|
boolean |
MFCheck.check(int idx,
FImage im,
Jama.Matrix s)
Check the whether its actually a face
|
List<Rectangle> |
FDet.detect(FImage im)
Detect faces in an image
|
void |
CLM.fit(FImage im,
int[] wSize,
int nIter,
double clamp,
double fTol)
Fit the model to the image
|
int |
Tracker.track(FImage im,
int[] wSize,
int fpd,
int nIter,
double clamp,
double fTol,
boolean fcheck) |
Constructor and Description |
---|
Patch(int t,
double a,
double b,
FImage W) |
Constructor and Description |
---|
FImageOptionHandler(org.kohsuke.args4j.CmdLineParser parser,
org.kohsuke.args4j.OptionDef option,
org.kohsuke.args4j.spi.Setter<? super FImage> setter)
Default constructor.
|
Modifier and Type | Method and Description |
---|---|
String |
CityLandscapeTree.classifyImage(FImage image,
int k)
Classifies the given image.
|
Modifier and Type | Method and Description |
---|---|
int[][] |
BasicDuplicateImageDatabase.extractFeatures(FImage image)
Extract hashed features from an image
|
Modifier and Type | Method and Description |
---|---|
LocalFeatureList<? extends LocalFeature<?,? extends FeatureVector>> |
DoGSiftFeatureExtractor.apply(FImage img) |
LocalFeatureList<? extends LocalFeature<?,? extends FeatureVector>> |
DSiftFeatureExtractor.apply(FImage img) |
Modifier and Type | Method and Description |
---|---|
static Jama.Matrix |
KeypointCorrespondenceTestHelper.generateMildTransform(FImage image)
Generate an affine transform between some reasonable limits:
- Rotate it between 0 and 360
- transform it between 0 and 10 pixels
- slant it (sheer in x and y) between 0 and 10 degrees
- scale it between 0 and 2.0 times
|
static Jama.Matrix |
KeypointCorrespondenceTestHelper.generateMildTransform(FImage image,
Random seed)
Generate an affine transform between some reasonable limits:
- Rotate it between 0 and 360
- transform it between 0 and 10 pixels
- slant it (sheer in x and y) between 0 and 10 degrees
- scale it between 0 and 2.0 times
|
Modifier and Type | Method and Description |
---|---|
float[][] |
KinectController.cameraToWorld(FImage regDepth,
int startx,
int stopx,
int stepx,
int starty,
int stopy,
int stepy)
Compute the world coordinates from the pixel locations in the given
registered depth image.
|
Modifier and Type | Field and Description |
---|---|
static InputStreamObjectReader<FImage> |
ImageUtilities.FIMAGE_READER
An
InputStreamObjectReader for reading FImage s. |
Modifier and Type | Method and Description |
---|---|
FImage |
FImage.abs()
Set all pixels to their absolute values, so that all pixel values in the
image will be greater than zero.
|
FImage |
FImage.add(FImage im)
Adds the pixel values of the given
FImage to the pixels of this
image. |
FImage |
FImage.add(Float num)
Returns a new
FImage that contains the pixels of this image
increased by the given value. |
FImage |
FImage.add(Image<?,?> im)
Adds the given image to this image and return new image.
|
FImage |
FImage.addInplace(FImage im)
Adds the given image pixel values to the pixel values of this image.
|
FImage |
FImage.addInplace(Float num)
Add a scalar to each pixel in this image (side-affects this image).
|
FImage |
FImage.addInplace(Image<?,?> im)
Add the given image to this image (side-affects this image).
|
FImage |
FImage.clip(Float min,
Float max)
Sets any pixels that are below
min to zero or above
max to the highest normal value that the image allows
(usually 1 for floating-point images). |
FImage |
FImage.clipMax(Float thresh)
Set all values greater than the given value to the highest normal value
that the image allows (usually 1 for floating-point images).
|
FImage |
FImage.clipMin(Float thresh)
Set all values less than the given value to zero.
|
FImage |
FImage.clone()
Deep copy of an image (internal image buffers copied).
|
static FImage |
CLImageConversion.convert(com.nativelibs4java.opencl.CLQueue queue,
com.nativelibs4java.opencl.CLEvent evt,
com.nativelibs4java.opencl.CLImage2D clImage,
FImage oiImage)
Convert a
CLImage2D to an FImage . |
static FImage |
CLImageConversion.convertFromFB(FloatBuffer fb,
int width,
int height,
FImage image)
Convert packed intensity pixels in a
FloatBuffer back into an
FImage . |
static FImage[] |
FImage.createArray(int num,
int width,
int height)
Convenience method to initialise an array of FImages
|
static FImage |
ImageUtilities.createFImage(BufferedImage image)
Create an FImage from a buffered image.
|
FImage |
FImage.divide(FImage im)
Divides the pixels values of this image with the values from the given
image.
|
FImage |
FImage.divideInplace(FImage im)
Divides the pixel values of this image with the values from the given
image.
|
FImage |
FImage.divideInplace(float fval)
Divide all pixels by a given value
|
FImage |
FImage.divideInplace(Float val)
Divide each pixel of the image by the given scalar value.
|
FImage |
FImage.divideInplace(Image<?,?> im)
Divide each pixel in this image by the corresponding pixel value in the
given image.
|
FImage |
FImage.extractCentreSubPix(float cx,
float cy,
FImage out) |
FImage |
FImage.extractROI(int x,
int y,
FImage out)
Extract a rectangular region of interest from this image and put it in
the given image.
|
FImage |
FImage.extractROI(int x,
int y,
int w,
int h)
Extract a rectangular region of interest of the given width and height.
|
FImage |
FImage.fill(float colour)
Fill an image with the given colour
|
FImage |
FImage.fill(Float colour)
Fill this image with the given colour.
|
FImage |
MBFImage.flatten() |
FImage |
MBFImage.flattenMax() |
FImage |
FImage.flipX() |
FImage |
FImage.flipY() |
FImage |
FImage.getField(Image.Field f)
Get the given field of this image.
|
FImage |
FImage.getFieldCopy(Image.Field f)
Get the given field of this image, maintaining the image's aspect ratio
by doubling the fields.
|
FImage |
FImage.getFieldInterpolate(Image.Field f)
Get the given field of this image, maintaining the image's aspect ratio
by interpolating between the fields.
|
static FImage[] |
ImageUtilities.getNormalisedColourPlanes(BufferedImage bimg)
Calculate normalised RGB planes.
|
FImage |
FImage.internalAssign(FImage im)
Assign the internal state from another image of the same type.
|
FImage |
FImage.internalAssign(int[] data,
int width,
int height)
Copy pixels from given ARGB buffer image into this image.
|
FImage |
FImage.internalCopy(FImage im)
Copy the internal state from another image of the same type.
|
FImage |
FImage.inverse()
Invert the image pixels by finding the maximum value and subtracting each
pixel value from that maximum.
|
FImage |
FImage.multiply(Float num)
Multiply each pixel of this by the given scalar and return new image.
|
FImage |
FImage.multiplyInplace(FImage im)
Multiplies this image's pixel values by the corresponding pixel values in
the given image side-affecting this image.
|
FImage |
FImage.multiplyInplace(float fnum)
Multiply all pixel values by the given value
|
FImage |
FImage.multiplyInplace(Float num)
Multiply each pixel of this by the given scalar.
|
FImage |
FImage.multiplyInplace(Image<?,?> im)
Multiply each pixel in this image by the corresponding pixel in the given
image.
|
FImage |
MBFImage.newBandInstance(int width,
int height) |
FImage |
FImage.newInstance(int width,
int height)
Create a new instance of this image subclass with given dimensions.
|
FImage |
FImage.normalise()
Normalise all pixel values to fall within the range 0.0 - 1.0.
|
FImage |
FImage.overlayInplace(FImage img,
FImage alpha,
int x,
int y)
Overlay the given image on this image with the given alpha channel at the
given location.
|
FImage |
FImage.overlayInplace(FImage image,
int x,
int y)
Overlays the given image on this image directly.
|
FImage |
FImage.process(KernelProcessor<Float,FImage> p)
Process this image with the given
KernelProcessor and return new
image containing the result. |
FImage |
FImage.process(KernelProcessor<Float,FImage> p,
boolean pad)
Process this image with the given
KernelProcessor and return new
image containing the result. |
FImage |
FImage.processInplace(PixelProcessor<Float> p)
Process this image with the given
PixelProcessor side-affecting
this image. |
static FImage |
FImage.randomImage(int width,
int height)
Create a random image of the given size.
|
static FImage |
ImageUtilities.readF(DataInput in)
Read an
FImage from a DataInput |
static FImage |
ImageUtilities.readF(File input)
Reads an
FImage from the given file. |
static FImage |
ImageUtilities.readF(InputStream input)
Reads an
FImage from the given input stream. |
static FImage |
ImageUtilities.readF(URL input)
Reads an
FImage from the given URL. |
FImage |
FImage.replace(float target,
float replacement)
Replace pixels of a certain colour with another colour.
|
FImage |
FImage.replace(Float target,
Float replacement) |
FImage |
FImage.subtract(FImage im)
Subtracts the given
FImage from this image returning a new image
containing the result. |
FImage |
FImage.subtract(Float num)
Subtract a scalar from every pixel value in this image and return new
image.
|
FImage |
FImage.subtract(Image<?,?> input)
Subtract the corresponding pixel value from the given image from the
pixel values in this image.
|
FImage |
FImage.subtractInplace(FImage im)
Subtracts (pixel-by-pixel) the given
FImage from this image. |
FImage |
FImage.subtractInplace(Float num)
Subtract a scalar from every pixel value in this image.
|
FImage |
FImage.subtractInplace(Image<?,?> im)
Subtract the corresponding pixel value from the given image from the
pixel values in this image.
|
FImage |
FImage.threshold(Float thresh)
Set all values less than the given threshold to 0 and all others to 1.
|
FImage |
FImage.transform(Jama.Matrix transform)
Apply a transform matrix to the image and returns the result as a new
image.
|
FImage |
FImage.zero()
Set all pixels in the image to zero.
|
Modifier and Type | Method and Description |
---|---|
FImage |
FImage.add(FImage im)
Adds the pixel values of the given
FImage to the pixels of this
image. |
FImage |
FImage.addInplace(FImage im)
Adds the given image pixel values to the pixel values of this image.
|
void |
Image.analyseWithMasked(FImage mask,
PixelAnalyser<Q> analyser)
Analyse this image with the given
PixelAnalyser , only analysing
those pixels where the mask is non-zero. |
static com.nativelibs4java.opencl.CLImage2D |
CLImageConversion.convert(com.nativelibs4java.opencl.CLContext context,
FImage image)
Convert an
FImage to CLImage2D . |
static FImage |
CLImageConversion.convert(com.nativelibs4java.opencl.CLQueue queue,
com.nativelibs4java.opencl.CLEvent evt,
com.nativelibs4java.opencl.CLImage2D clImage,
FImage oiImage)
Convert a
CLImage2D to an FImage . |
static FImage |
CLImageConversion.convertFromFB(FloatBuffer fb,
int width,
int height,
FImage image)
Convert packed intensity pixels in a
FloatBuffer back into an
FImage . |
static FloatBuffer |
CLImageConversion.convertToFB(FImage image,
ByteOrder byteOrder)
Converts an FImage to a
FloatBuffer containing packed
intensity pixels. |
static BufferedImage |
ImageUtilities.createBufferedImage(FImage img)
Efficiently create a TYPE_BYTE_GRAY for display.
|
static BufferedImage |
ImageUtilities.createBufferedImage(FImage img,
BufferedImage ret)
Efficiently create a TYPE_BYTE_GRAY for display.
|
static MBFImage |
MBFImage.createRGB(FImage image)
|
FImage |
FImage.divide(FImage im)
Divides the pixels values of this image with the values from the given
image.
|
FImage |
FImage.divideInplace(FImage im)
Divides the pixel values of this image with the values from the given
image.
|
boolean |
FImage.equalsThresh(FImage o,
float thresh)
Compare this image against another using a threshold on the absolute
difference between pixel values in order to determine equality.
|
FImage |
FImage.extractCentreSubPix(float cx,
float cy,
FImage out) |
FImage |
FImage.extractROI(int x,
int y,
FImage out)
Extract a rectangular region of interest from this image and put it in
the given image.
|
FImage |
FImage.internalAssign(FImage im)
Assign the internal state from another image of the same type.
|
FImage |
FImage.internalCopy(FImage im)
Copy the internal state from another image of the same type.
|
FImage |
FImage.multiplyInplace(FImage im)
Multiplies this image's pixel values by the corresponding pixel values in
the given image side-affecting this image.
|
FImage |
FImage.overlayInplace(FImage img,
FImage alpha,
int x,
int y)
Overlay the given image on this image with the given alpha channel at the
given location.
|
FImage |
FImage.overlayInplace(FImage image,
int x,
int y)
Overlays the given image on this image directly.
|
I |
Image.processMasked(FImage mask,
PixelProcessor<Q> p)
Process this image with the given
PixelProcessor only affecting
those pixels where the mask is non-zero. |
I |
Image.processMaskedInplace(FImage mask,
PixelProcessor<Q> p)
Process this image with the given
PixelProcessor , only affecting
those pixels where the mask is non-zero. |
FImage |
FImage.subtract(FImage im)
Subtracts the given
FImage from this image returning a new image
containing the result. |
FImage |
FImage.subtractInplace(FImage im)
Subtracts (pixel-by-pixel) the given
FImage from this image. |
Modifier and Type | Method and Description |
---|---|
FImage |
FImage.process(KernelProcessor<Float,FImage> p)
Process this image with the given
KernelProcessor and return new
image containing the result. |
FImage |
FImage.process(KernelProcessor<Float,FImage> p,
boolean pad)
Process this image with the given
KernelProcessor and return new
image containing the result. |
Constructor and Description |
---|
MBFImage(ColourSpace colourSpace,
FImage... images)
Construct an MBFImage from single band images.
|
MBFImage(FImage... images)
Construct an MBFImage from single band images with the default RGB
colourspace if there are three images, RGBA if there are 4 images, or
CUSTOM otherwise.
|
Modifier and Type | Class and Description |
---|---|
class |
FloodFill<I extends Image<?,I> & SinglebandImageProcessor.Processable<Float,FImage,I>>
Flood-fill of @link{FImage}s or @link{MBFImage}s.
|
Modifier and Type | Field and Description |
---|---|
FImage |
SummedAreaTable.data
The SAT data
|
protected FImage |
ImageInterpolation.image |
FImage |
SummedSqAreaTable.sqSum
The squared sum data
|
FImage |
SummedSqAreaTable.sum
The sum data
|
FImage |
SummedSqTiltAreaTable.tiltSum
The tilted sum data
|
Modifier and Type | Method and Description |
---|---|
FImage |
HoughLines.calculateHorizontalProjection()
Calculates a projection across the accumulator space.
|
FImage |
HoughLines.calculateHorizontalProjection(FImage accum)
Calculates a projection across the given accumulator space.
|
static <T> FImage |
FloodFill.floodFill(Image<T,?> image,
int startx,
int starty,
float threshold)
Flood-fill an image from the given starting pixel position with the given
threshold.
|
static <T> FImage |
FloodFill.floodFill(Image<T,?> image,
Pixel start,
float threshold)
Flood-fill an image from the given starting pixel position with the given
threshold.
|
FImage |
HoughLines.getAccumulator()
Returns the accumulator space.
|
FImage |
EuclideanDistanceTransform.getDistances() |
FImage |
FloodFill.getFlooded()
Get the binary flooded image map
|
FImage |
TemplateMatcher.getResponseMap() |
FImage |
FourierTemplateMatcher.getResponseMap() |
FImage |
TemplateMatcher.getTemplate() |
protected FImage |
TemplateMatcher.Mode.prepareTemplate(FImage template)
Prepare the template if necessary.
|
Modifier and Type | Method and Description |
---|---|
void |
HoughCircles.analyseImage(FImage image) |
void |
EuclideanDistanceTransform.analyseImage(FImage image) |
void |
ImageInterpolation.analyseImage(FImage image) |
void |
TemplateMatcher.analyseImage(FImage image)
Perform template matching.
|
void |
SummedSqAreaTable.analyseImage(FImage image) |
void |
VerticalProjection.analyseImage(FImage image) |
void |
FourierTemplateMatcher.analyseImage(FImage image)
Perform template matching.
|
void |
HoughLines.analyseImage(FImage image)
Analyse an image.
|
void |
EdgeDirectionCoherenceVector.analyseImage(FImage image) |
void |
SummedAreaTable.analyseImage(FImage image) |
void |
HorizontalProjection.analyseImage(FImage image) |
void |
SummedSqTiltAreaTable.analyseImage(FImage image) |
FImage |
HoughLines.calculateHorizontalProjection(FImage accum)
Calculates a projection across the given accumulator space.
|
double |
HoughLines.calculatePrevailingAngle(FImage accum,
int offset,
double nDegrees)
Returns the most frequent angle that occurs within the given accumulator
space by calculating a horizontal projection over the accumulator
space and returning the angle with the most votes.
|
protected abstract float |
TemplateMatcher.Mode.computeMatchScore(FImage image,
FImage template,
int x,
int y,
Object workingSpace)
Compute the matching score between the image and template, with the top-left of the
template at (x, y) in the image.
|
protected void |
SummedSqTiltAreaTable.computeRotSqSumIntegralImages(FImage image) |
protected void |
SummedSqTiltAreaTable.computeSqSumIntegralImages(FImage img) |
protected void |
SummedSqAreaTable.computeTable(FImage image) |
protected void |
SummedAreaTable.computeTable(FImage image) |
Line2d |
HoughLines.getBestLine(FImage accumulatorSpace,
int offset)
Returns the top line in the given accumulator space.
|
List<Line2d> |
HoughLines.getBestLines(int n,
FImage accumulatorSpace,
int offset)
Returns the top n lines from the given accumulator space.
|
static FValuePixel[] |
TemplateMatcher.getBestResponses(int numResponses,
FImage responseMap,
int offsetX,
int offsetY,
Comparator<FValuePixel> comparator)
Get the top-N "best" responses found by the template matcher.
|
float |
ImageInterpolation.Interpolator.interpolate(float x,
float y,
FImage image,
Object workingSpace)
Interpolate a pixel value
|
protected FImage |
TemplateMatcher.Mode.prepareTemplate(FImage template)
Prepare the template if necessary.
|
protected Object |
TemplateMatcher.Mode.prepareWorkingSpace(FImage template)
Prepare an object to hold the working space required by the
mode during score computation.
|
abstract void |
FourierTemplateMatcher.Mode.processCorrelationMap(FImage img,
FImage template,
FImage corr)
Process the cross-correlation image to the contain the relevant output values for the
chosen mode.
|
static float[] |
VerticalProjection.project(FImage image)
Project an image onto the y-axis.
|
static float[] |
HorizontalProjection.project(FImage image)
Project an image onto the x-axis.
|
static void |
EuclideanDistanceTransform.squaredEuclideanDistance(FImage image,
FImage distances,
int[][] indices)
The static function which underlies EuclideanDistanceTransform.
|
static void |
EuclideanDistanceTransform.squaredEuclideanDistanceBinary(FImage image,
FImage distances,
int[][] indices)
Calculate the squared euclidean distance transform of a binary image with
foreground pixels set to 1 and background set to 0.
|
Constructor and Description |
---|
FourierTemplateMatcher(FImage template,
FourierTemplateMatcher.Mode mode)
Default constructor with the template to match.
|
FourierTemplateMatcher(FImage template,
Rectangle bounds,
FourierTemplateMatcher.Mode mode)
Construct with the template to match and the bounds rectangle in which
to search.
|
SummedAreaTable(FImage image)
Construct a SAT from the provided image
|
SummedSqAreaTable(FImage image)
Construct a SAT from the provided image
|
SummedSqTiltAreaTable(FImage image)
Construct a SAT for normal sum, squared sum and tilted sum from the
provided image.
|
SummedSqTiltAreaTable(FImage image,
boolean computeTilted)
Construct a SAT for normal sum, squared sum and (optionally) tilted sum
from the provided image.
|
TemplateMatcher(FImage template,
TemplateMatcher.Mode mode)
Default constructor with the template to match and the mode
with which to estimate template responses.
|
TemplateMatcher(FImage template,
TemplateMatcher.Mode mode,
Rectangle bounds)
Construct with the template to match, the mode with which to
estimate template responses and the bounds rectangle in which
to search.
|
Modifier and Type | Method and Description |
---|---|
void |
GradientOrientationHistogramExtractor.analyseImage(FImage image) |
void |
HistogramAnalyser.analyseImage(FImage image)
Computes the Histogram for this image.
|
void |
InterpolatedBinnedWindowedExtractor.analyseImage(FImage image)
Computes the bin-map for this image.
|
void |
BinnedWindowedExtractor.analyseImage(FImage image)
Computes the bin-map for this image.
|
void |
GradientOrientationHistogramExtractor.analyseImage(FImage image,
FImage edges)
Analyse the given image, but construct the internal data such that the
gradient magnitudes are multiplied by the given edge map before being
accumulated.
|
Histogram |
InterpolatedBinnedWindowedExtractor.computeHistogram(int x,
int y,
FImage extWeights,
FImage windowWeights) |
Histogram |
BinnedWindowedExtractor.computeHistogram(int x,
int y,
FImage weights,
FImage windowWeights)
Compute the histogram for the given window.
|
Histogram |
InterpolatedBinnedWindowedExtractor.computeHistogram(int x,
int y,
int w,
int h,
FImage extWeights) |
Histogram |
BinnedWindowedExtractor.computeHistogram(int x,
int y,
int w,
int h,
FImage weights)
Compute the histogram for the given window.
|
Histogram |
BinnedWindowedExtractor.computeHistogram(Rectangle roi,
FImage weights)
Compute the histogram for the given window.
|
protected void |
SATWindowedExtractor.computeSATs(FImage[] magnitudeMaps) |
static Histogram |
HistogramAnalyser.getHistogram(FImage image,
int nbins)
Quickly create a histogram from an image.
|
Constructor and Description |
---|
SATWindowedExtractor(FImage[] magnitudeMaps)
Construct with the given spatial histogram magnitude maps.
|
Modifier and Type | Method and Description |
---|---|
FImage |
CIEDE2000.combine(MBFImage image1,
MBFImage image2) |
static FImage |
CIEDE2000.makeDisparityMap(MBFImage im1,
MBFImage im2)
Compute the disparity map between two images.
|
Modifier and Type | Class and Description |
---|---|
class |
Octave<OPTIONS extends PyramidOptions<?,IMAGE>,PYRAMID extends Pyramid<OPTIONS,?,IMAGE>,IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>
An octave is an interval in scale space, typically corresponding to a
doubling of sigma.
|
interface |
OctaveProcessor<OCTAVE extends Octave<?,?,IMAGE>,IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>
The OctaveProcessor interface defines an object that
is capable performing work on an octave.
|
class |
Pyramid<OPTIONS extends PyramidOptions<OCTAVE,IMAGE>,OCTAVE extends Octave<OPTIONS,?,IMAGE>,IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>
An image pyramid consisting of a stack of octaves.
|
class |
PyramidOptions<OCTAVE extends Octave<?,?,IMAGE>,IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>
Basic options for constructing a pyramid
|
interface |
PyramidProcessor<IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>
The PyramidProcessor interface defines an object that
is capable performing work on a pyramid.
|
class |
SimplePyramid<IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>
A simple image pyramid built as a stack of images.
|
Modifier and Type | Method and Description |
---|---|
static <T extends Image<?,T> & SinglebandImageProcessor.Processable<Float,FImage,T>> |
SimplePyramid.createGaussianPyramid(T image,
float sigma,
int nLevels)
Convenience method to create a gaussian pyramid from an image.
|
Modifier and Type | Class and Description |
---|---|
class |
GaussianOctave<IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>
This class represents a Gaussian octave in the style of Lowe's SIFT paper.
|
class |
GaussianPyramid<I extends Image<?,I> & SinglebandImageProcessor.Processable<Float,FImage,I>>
A Gaussian image pyramid consisting of a stack of octaves where the image
halves its size.
|
class |
GaussianPyramidOptions<IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>
Options for constructing a Gaussian pyramid in the style of Lowe's SIFT
paper.
|
Modifier and Type | Method and Description |
---|---|
SinglebandImageProcessor<Float,FImage> |
GaussianPyramidOptions.createGaussianBlur(float sigma)
Create a
SinglebandImageProcessor that performs a Gaussian
blurring with a standard deviation given by sigma. |
Modifier and Type | Method and Description |
---|---|
void |
WatershedProcessor.processImage(FImage greyscaleImage)
Process the given image.
|
Constructor and Description |
---|
WatershedProcessorAlgorithm(FImage bGreyscaleImage,
IntValuePixel startPixel,
Class<? extends ComponentFeature>... featureClasses)
Default constructor
|
Modifier and Type | Method and Description |
---|---|
FImage |
MomentFeature.extractEllipsePatch(FImage image,
double sf)
Extract a rectangular image patch centered on the feature
with the same primary orientation and a given scale factor.
|
Modifier and Type | Method and Description |
---|---|
FImage |
MomentFeature.extractEllipsePatch(FImage image,
double sf)
Extract a rectangular image patch centered on the feature
with the same primary orientation and a given scale factor.
|
Modifier and Type | Field and Description |
---|---|
static BinaryReader<FImage> |
CIFARDataset.FIMAGE_READER
Reader for getting the data as
FImage s |
Modifier and Type | Method and Description |
---|---|
FImage |
FImageReader.read(byte[] record) |
Modifier and Type | Method and Description |
---|---|
<I extends Image<?,I> & SinglebandImageProcessor.Processable<Float,FImage,I>> |
CameraIntrinsics.undistort(I image)
Undistort the given image by removing the radial and tangential
distortions of this camera.
|
Modifier and Type | Method and Description |
---|---|
FImage[] |
CameraIntrinsics.buildRectifiedUndistortionMap(int width,
int height,
CameraIntrinsics target,
Jama.Matrix R)
Build the rectified distortion map, which for every un-distorted point in
the given size image contains the x and y ordinates of the corresponding
rectifed distorted point.
|
FImage[] |
CameraIntrinsics.buildUndistortionMap(int width,
int height)
Build the distortion map, which for every un-distorted point in the given
size image contains the x and y ordinates of the corresponding distorted
point.
|
FImage[] |
CameraIntrinsics.buildUndistortionMap(int width,
int height,
CameraIntrinsics target)
Build the distortion map, which for every un-distorted point in the given
size image contains the x and y ordinates of the corresponding distorted
point.
|
Modifier and Type | Method and Description |
---|---|
void |
FastChessboardDetector.analyseImage(FImage src) |
void |
ChessboardCornerFinder.analyseImage(FImage image) |
Modifier and Type | Method and Description |
---|---|
static FImage |
Transforms.calculateHue(MBFImage in)
Calculate Hue in 0..1 range from a 3-band RGB MBFImage
|
static FImage |
Transforms.calculateIntensity(MBFImage in)
Calculate intensity by averaging R, G, B planes.
|
static FImage |
Transforms.calculateIntensity(MBFImage in,
float wR,
float wG,
float wB)
Calculate Intensity image from an RGB or RGBA MBFImage with given
weightings for R, G and B
|
static FImage |
Transforms.calculateIntensityNTSC_LUT(MBFImage in)
Calculate intensity by a weighted average of the R, G, B planes.
|
static FImage |
Transforms.calculateIntensityNTSC(MBFImage in)
Calculate intensity by a weighted average of the R, G, B planes.
|
static FImage |
Transforms.calculateSaturation(MBFImage in)
Calculate Saturation image from a 3-band RGB MBFImage
|
Modifier and Type | Method and Description |
---|---|
MBFImage |
ColourMap.apply(FImage img)
Apply a colourmap to an image
|
static MBFImage |
Transforms.H_TO_H1H2_2(FImage in)
Convert to Hue to H2 VARIANT 2 using the formulation from:
http://ilab.usc.edu/wiki/index.php/HSV_And_H2SV_Color_Space
|
static MBFImage |
Transforms.H_TO_H1H2(FImage in)
Convert to Hue to H2 using the formulation from:
http://ilab.usc.edu/wiki/index.php/HSV_And_H2SV_Color_Space
|
Modifier and Type | Method and Description |
---|---|
void |
GreyscaleConnectedComponentLabeler.analyseImage(FImage image) |
void |
ConnectedComponentLabeler.analyseImage(FImage image) |
List<ConnectedComponent> |
GreyscaleConnectedComponentLabeler.findComponents(FImage image)
Syntactic sugar for calling
GreyscaleConnectedComponentLabeler.analyseImage(FImage) followed by
GreyscaleConnectedComponentLabeler.getComponents() ; |
List<ConnectedComponent> |
ConnectedComponentLabeler.findComponents(FImage image)
Syntactic sugar for calling
ConnectedComponentLabeler.analyseImage(FImage) followed by
ConnectedComponentLabeler.getComponents() ; |
abstract List<ConnectedComponent> |
ConnectedComponentLabeler.Algorithm.findComponents(FImage image,
float bgThreshold,
ConnectedComponent.ConnectMode mode)
Find the connected components in an image.
|
protected ConnectedComponent |
GreyscaleConnectedComponentLabeler.floodFill(FImage image,
Pixel start,
int[][] output,
int color) |
Modifier and Type | Method and Description |
---|---|
void |
SuzukiContourProcessor.analyseImage(FImage image) |
List<Pixel> |
ContourFollowingStrategy.contour(FImage image,
Pixel start,
Pixel from)
Follow the contour, adding each pixel to a list.
|
abstract void |
ContourFollowingStrategy.contour(FImage image,
Pixel start,
Pixel from,
Operation<Pixel> operation)
Given some starting pixel in an image on a contour and the direction of a
non starting image, return each pixel on a contour from the start pixel
in the image.
|
void |
MooreNeighborStrategy.contour(FImage image,
Pixel start,
Pixel from,
Operation<Pixel> operation) |
void |
SuzukiNeighborStrategy.contour(FImage image,
Pixel start,
Pixel from,
Operation<Pixel> operation) |
void |
SuzukiNeighborStrategy.directedContour(FImage image,
Pixel ij,
Pixel i2j2,
Operation<IndependentPair<Pixel,boolean[]>> operation)
Directed contour following.
|
void |
MooreNeighborStrategy.directedContour(FImage image,
Pixel start,
Pixel from,
Operation<IndependentPair<Pixel,org.openimaj.image.contour.Direction>> operation)
Directed contour following.
|
static Contour |
SuzukiContourProcessor.findContours(FImage image)
Find contours in the given image and return the border
|
static Contour |
SuzukiContourProcessor.findContours(FImage image,
SuzukiContourProcessor proc)
Detect borders hierarchically in this binary image.
|
Modifier and Type | Method and Description |
---|---|
FImage |
DoubleFV2FImage.extractFeature(DoubleFV object) |
static FImage |
DoubleFV2FImage.extractFeature(DoubleFV fv,
int width,
int height)
|
FImage |
FloatFV2FImage.extractFeature(FloatFV object) |
static FImage |
FloatFV2FImage.extractFeature(FloatFV fv,
int width,
int height)
|
Modifier and Type | Method and Description |
---|---|
DoubleFV |
FImage2DoubleFV.extractFeature(FImage object) |
FloatFV |
FImage2FloatFV.extractFeature(FImage object) |
Modifier and Type | Method and Description |
---|---|
static FImage |
UniformBinaryPattern.extractPatternImage(int[][] patternImage,
int code)
Compute a binary map showing the locations of the specified pattern code.
|
static FImage[] |
UniformBinaryPattern.extractPatternImages(int[][] patternImage,
int nbits)
Compute all binary maps for each possible pattern code given the number
of bits used to encode patterns.
|
Modifier and Type | Method and Description |
---|---|
void |
LocalTernaryPattern.analyseImage(FImage image) |
void |
ExtendedLocalBinaryPattern.analyseImage(FImage image) |
void |
BasicLocalBinaryPattern.analyseImage(FImage image) |
static int[][] |
BasicLocalBinaryPattern.calculateLBP(FImage image)
Calculate the LBP for every pixel in the image.
|
static int[][] |
ExtendedLocalBinaryPattern.calculateLBP(FImage image,
float radius,
int samples)
Calculate the LBP for every pixel in the image.
|
static int |
ExtendedLocalBinaryPattern.calculateLBP(FImage image,
float radius,
int samples,
int x,
int y)
Calculate the extended LBP for a single point.
|
static int |
ExtendedLocalBinaryPattern.calculateLBP(FImage image,
float radius,
int samples,
Pixel point)
Calculate the extended LBP for a single point.
|
static int |
BasicLocalBinaryPattern.calculateLBP(FImage image,
int x,
int y)
Calculate the basic LBP for a single point.
|
static int |
BasicLocalBinaryPattern.calculateLBP(FImage image,
Pixel point)
Calculate the basic LBP for a single point.
|
static int[][][] |
LocalTernaryPattern.calculateLTP(FImage image,
float radius,
int samples,
float threshold)
Calculate the LBP for every pixel in the image.
|
static int[] |
LocalTernaryPattern.calculateLTP(FImage image,
float radius,
int samples,
float threshold,
int x,
int y)
Calculate the LTP for a single point.
|
static int[] |
LocalTernaryPattern.calculateLTP(FImage image,
float radius,
int samples,
float threshold,
Pixel point)
Calculate the LTP for a single point.
|
Modifier and Type | Method and Description |
---|---|
void |
HOG.analyseImage(FImage image) |
void |
PHOG.analyseImage(FImage image) |
void |
HOG.analyseImage(FImage image,
FImage edges)
Analyse the given image, but construct the internal data such that the
gradient magnitudes are multiplied by the given edge map before being
accumulated.
|
Constructor and Description |
---|
PHOG(int nlevels,
int nbins,
boolean histogramInterpolation,
FImageGradients.Mode orientationMode,
ImageProcessor<FImage> edgeDetector)
Construct with the given parameters.
|
Modifier and Type | Class and Description |
---|---|
class |
PyramidDenseSIFT<IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>
A scale-space pyramid of dense SIFT for
FImage s. |
Modifier and Type | Method and Description |
---|---|
void |
DenseSIFT.analyseImage(FImage image,
Rectangle bounds) |
Modifier and Type | Class and Description |
---|---|
class |
Gist<IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>
Implementation of the "Gist" spatial envelope feature.
|
Modifier and Type | Field and Description |
---|---|
protected FImage[] |
Gist.gaborFilters |
Modifier and Type | Method and Description |
---|---|
void |
SharpPixelProportion.analyseImage(FImage image) |
void |
Sharpness.analyseImage(FImage image) |
void |
RMSContrast.analyseImage(FImage image) |
void |
SharpnessVariation.analyseImage(FImage image) |
void |
WeberContrast.analyseImage(FImage image) |
void |
LRIntensityBalance.analyseImage(FImage image) |
void |
HorizontalIntensityDistribution.analyseImage(FImage image) |
void |
YehBokehEstimator.analyseImage(FImage image) |
abstract double |
AvgBrightness.Mode.computeBrightness(MBFImage img,
FImage mask)
Compute the average brightness of the given image (applying the mask
if it's not
null ). |
protected void |
Gist.sampleResponses(FImage image,
float[] v,
int offset)
Sample the average response from each of the blocks in the image and
insert into the vector.
|
Constructor and Description |
---|
AvgBrightness(AvgBrightness.Mode mode,
FImage mask)
Construct with the given mode and a mask.
|
HueStats(FImage mask)
Construct with a mask.
|
Naturalness(FImage mask)
Construct with a mask.
|
Sharpness(FImage mask)
Construct with a mask.
|
SharpnessVariation(FImage mask)
Construct with a mask.
|
Modifier and Type | Class and Description |
---|---|
class |
AffineSimulationExtractor<Q extends List<T>,T extends ScaleSpacePoint,I extends Image<P,I> & SinglebandImageProcessor.Processable<Float,FImage,I>,P>
Base class for local feature detectors/extractors that use affine simulations
in order to increase detections and improve performance with respect to
affine change.
|
class |
ASIFT<I extends Image<P,I> & SinglebandImageProcessor.Processable<Float,FImage,I>,P>
Abstract base implementation of Affine-simulated SIFT (ASIFT).
|
Modifier and Type | Method and Description |
---|---|
Engine<Keypoint,FImage> |
BasicASIFT.constructEngine(DoGSIFTEngineOptions<FImage> opts) |
Modifier and Type | Method and Description |
---|---|
Engine<Keypoint,FImage> |
BasicASIFT.constructEngine(DoGSIFTEngineOptions<FImage> opts) |
Constructor and Description |
---|
BasicASIFT(DoGSIFTEngineOptions<FImage> opts)
Construct with the given options for the internal
DoGSIFTEngine . |
Modifier and Type | Method and Description |
---|---|
static FImage |
VLAD.drawDescriptor(float[] descr,
int nterms,
int nSpatialBins,
int nOriBins)
Generate a visualisation of the feature.
|
Modifier and Type | Class and Description |
---|---|
class |
AbstractOctaveLocalFeatureCollector<OCTAVE extends Octave<?,?,IMAGE>,EXTRACTOR extends FeatureVectorExtractor<?,ScaleSpaceImageExtractorProperties<IMAGE>>,FEATURE extends LocalFeature<?,?>,IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>
Abstract base class for objects that collate
LocalFeature s as they
are extracted from Octave s. |
interface |
Collector<OCTAVE extends Octave<?,?,IMAGE>,FEATURE extends LocalFeature<?,?>,IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>
|
class |
ConcreteOctaveLocalFeatureCollector<OCTAVE extends Octave<?,?,IMAGE>,FE extends FeatureVectorExtractor<?,ScaleSpaceImageExtractorProperties<IMAGE>>,IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>
Concrete implementation of an
AbstractOctaveLocalFeatureCollector
that collects LocalFeature s in the form of LocalFeatureImpl
with the feature vector provided by the given feature extractor, and the
Location provided by a ScaleSpaceLocation with an x, y and
scale coordinates. |
class |
OctaveKeypointCollector<IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>
Concrete implementation of an
AbstractOctaveLocalFeatureCollector
that collects Keypoint s with the feature vector provided by the
given feature extractor. |
Modifier and Type | Field and Description |
---|---|
protected ScaleSpaceImageExtractorProperties<FImage> |
OctaveMinMaxKeypointCollector.extractionProperties |
Modifier and Type | Method and Description |
---|---|
void |
OctaveMinMaxKeypointCollector.foundInterestPoint(OctaveInterestPointFinder<GaussianOctave<FImage>,FImage> finder,
float x,
float y,
float octaveScale) |
void |
OctaveMinMaxKeypointCollector.foundInterestPoint(OctaveInterestPointFinder<GaussianOctave<FImage>,FImage> finder,
float x,
float y,
float octaveScale) |
Modifier and Type | Interface and Description |
---|---|
interface |
ScaleSpaceFeatureExtractor<F extends FeatureVector,IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>
The ScaleSpaceImageExtractor interface describes a class capable of extracting
FeatureVector(s) from the information provided in a
ScaleSpaceImageExtractorProperties . |
Modifier and Type | Field and Description |
---|---|
protected FImage[] |
ColourGradientFeatureExtractor.magnitudes |
protected FImage[] |
ColourGradientFeatureExtractor.orientations |
Modifier and Type | Method and Description |
---|---|
GradientScaleSpaceImageExtractorProperties<FImage> |
GradientFeatureExtractor.getCurrentGradientProps(ScaleSpaceImageExtractorProperties<FImage> properties)
Get the GradientScaleSpaceImageExtractorProperties for the given
properties.
|
GradientScaleSpaceImageExtractorProperties<FImage> |
ColourGradientFeatureExtractor.getCurrentGradientProps(ScaleSpaceImageExtractorProperties<MBFImage> properties)
Get the GradientScaleSpaceImageExtractorProperties for the given
properties.
|
Modifier and Type | Method and Description |
---|---|
FloatFV[] |
AbstractDominantOrientationExtractor.extractFeature(GradientScaleSpaceImageExtractorProperties<FImage> props)
Find the dominant orientations
|
FloatFV[] |
OrientationHistogramExtractor.extractFeature(GradientScaleSpaceImageExtractorProperties<FImage> props)
Extract the orientation histogram given the properties.
|
OrientedFeatureVector[] |
GradientFeatureExtractor.extractFeature(ScaleSpaceImageExtractorProperties<FImage> properties) |
abstract float[] |
AbstractDominantOrientationExtractor.extractFeatureRaw(GradientScaleSpaceImageExtractorProperties<FImage> props)
Find the dominant orientations.
|
float[] |
DominantOrientationExtractor.extractFeatureRaw(GradientScaleSpaceImageExtractorProperties<FImage> properties)
Extract an orientation histogram and find the dominant orientations
by looking for peaks.
|
float[] |
OrientationHistogramExtractor.extractFeatureRaw(GradientScaleSpaceImageExtractorProperties<FImage> properties)
Extract the orientation histogram given the properties.
|
float[] |
NullOrientationExtractor.extractFeatureRaw(GradientScaleSpaceImageExtractorProperties<FImage> props) |
GradientScaleSpaceImageExtractorProperties<FImage> |
GradientFeatureExtractor.getCurrentGradientProps(ScaleSpaceImageExtractorProperties<FImage> properties)
Get the GradientScaleSpaceImageExtractorProperties for the given
properties.
|
Modifier and Type | Class and Description |
---|---|
class |
DoGOctave<I extends Image<?,I> & SinglebandImageProcessor.Processable<Float,FImage,I>>
A DoGOctave is capable of processing an octave of Gaussian blurred
images to produce an octave of difference-of-Gaussian images.
|
Modifier and Type | Method and Description |
---|---|
GaussianOctave<FImage> |
FirstBandDoGOctaveExtremaFinder.getDoGOctave()
Get the difference-of-Gaussian octave corresponding to
the current Gaussian octave.
|
GaussianOctave<FImage> |
DoGOctaveExtremaFinder.getDoGOctave()
Get the difference-of-Gaussian octave corresponding to
the current Gaussian octave.
|
GaussianOctave<FImage> |
DoGOctaveExtremaFinder.getOctave() |
OctaveInterestPointListener<GaussianOctave<FImage>,FImage> |
DoGOctaveExtremaFinder.getOctaveInterestPointListener() |
OctaveInterestPointListener<GaussianOctave<FImage>,FImage> |
DoGOctaveExtremaFinder.getOctaveInterestPointListener() |
Modifier and Type | Method and Description |
---|---|
void |
FirstBandDoGOctaveExtremaFinder.foundInterestPoint(OctaveInterestPointFinder<GaussianOctave<FImage>,FImage> finder,
float x,
float y,
float octaveScale) |
void |
FirstBandDoGOctaveExtremaFinder.foundInterestPoint(OctaveInterestPointFinder<GaussianOctave<FImage>,FImage> finder,
float x,
float y,
float octaveScale) |
void |
DoGOctaveExtremaFinder.foundInterestPoint(OctaveInterestPointFinder<GaussianOctave<FImage>,FImage> finder,
float x,
float y,
float octaveScale) |
void |
DoGOctaveExtremaFinder.foundInterestPoint(OctaveInterestPointFinder<GaussianOctave<FImage>,FImage> finder,
float x,
float y,
float octaveScale) |
void |
DoGOctaveExtremaFinder.process(GaussianOctave<FImage> octave) |
void |
DoGOctaveExtremaFinder.setOctaveInterestPointListener(OctaveInterestPointListener<GaussianOctave<FImage>,FImage> listener) |
void |
DoGOctaveExtremaFinder.setOctaveInterestPointListener(OctaveInterestPointListener<GaussianOctave<FImage>,FImage> listener) |
Modifier and Type | Method and Description |
---|---|
void |
AffineInterestPointFeatureCollector.foundInterestPoint(FImage image,
EllipticInterestPointData point) |
void |
AffineInterestPointFeatureCollector.foundInterestPoint(FImage image,
EllipticInterestPointData point,
double octaveSize) |
void |
CircularInterestPointFeatureCollector.foundInterestPoint(FImage image,
InterestPointData point) |
void |
CircularInterestPointFeatureCollector.foundInterestPoint(FImage image,
InterestPointData point,
double octaveSize) |
abstract void |
InterestPointFeatureCollector.foundInterestPoint(FImage image,
T point)
Collect interest points from a single image
|
abstract void |
InterestPointFeatureCollector.foundInterestPoint(FImage image,
T point,
double octaveSize)
Collect interest points from an image known to be in a pyramid with a given octave size
|
Modifier and Type | Method and Description |
---|---|
GradientScaleSpaceImageExtractorProperties<FImage> |
InterestPointGradientFeatureExtractor.getCurrentGradientProps(ScaleSpaceImageExtractorProperties<FImage> properties)
Get the GradientScaleSpaceImageExtractorProperties for the given
properties.
|
Modifier and Type | Method and Description |
---|---|
protected OrientedFeatureVector |
InterestPointGradientFeatureExtractor.createFeature(InterestPointImageExtractorProperties<Float,FImage> properties,
float orientation) |
OrientedFeatureVector[] |
InterestPointGradientFeatureExtractor.extractFeature(InterestPointImageExtractorProperties<Float,FImage> properties) |
GradientScaleSpaceImageExtractorProperties<FImage> |
InterestPointGradientFeatureExtractor.getCurrentGradientProps(ScaleSpaceImageExtractorProperties<FImage> properties)
Get the GradientScaleSpaceImageExtractorProperties for the given
properties.
|
Modifier and Type | Method and Description |
---|---|
protected void |
OctaveInterestPointFinder.processOctaveLevelPoints(FImage fImage,
List<T> points,
float currentScale,
float octaveSize) |
protected void |
LoggingOctaveInterestPointFinder.processOctaveLevelPoints(FImage fImage,
List<T> points,
float currentScale,
float octaveSize) |
Modifier and Type | Method and Description |
---|---|
void |
OctaveInterestPointFinder.process(GaussianOctave<FImage> octave) |
Modifier and Type | Method and Description |
---|---|
List<Component> |
MSERFeatureGenerator.generateMSERs(FImage img)
Performs a watershed then an MSER detection on the given image and
returns the MSERs.
|
List<Component> |
MSERFeatureGenerator.generateMSERs(FImage img,
MSERFeatureGenerator.MSERDirection dir)
Performs a watershed then an MSER detection on the given image and
returns the MSERs.
|
List<MergeTreeBuilder> |
MSERFeatureGenerator.performWatershed(FImage img)
Perform the watershed algorithm on the given image.
|
Modifier and Type | Class and Description |
---|---|
class |
AbstractOctaveExtremaFinder<OCTAVE extends GaussianOctave<FImage>>
Class for finding extrema within
Octave s using the approach in
Section 4 of Lowe's IJCV paper (minus the bit on using Brown's interpolation
approach to improve localisation). |
class |
AbstractOctaveInterestPointFinder<OCTAVE extends Octave<?,?,IMAGE>,IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>
Abstract base class for objects capable of detecting interest points
within an octave.
|
class |
BasicOctaveGridFinder<OCTAVE extends Octave<?,?,IMAGE>,IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>
An
AbstractOctaveInterestPointFinder that detects points on a regular
grid. |
interface |
OctaveInterestPointFinder<OCTAVE extends Octave<?,?,IMAGE>,IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>
Interface for objects that can detect interest points within an
octave.
|
interface |
OctaveInterestPointListener<OCTAVE extends Octave<?,?,IMAGE>,IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>
Interface for objects that listen for interest point detections
in an octave.
|
Modifier and Type | Method and Description |
---|---|
protected boolean |
AbstractOctaveExtremaFinder.firstCheck(float val,
int x,
int y,
int scaleIndex,
FImage[] images)
Perform the first of the checks that determine whether a point is a valid
interest point.
|
protected boolean |
BasicOctaveExtremaFinder.firstCheck(float val,
int x,
int y,
int s,
FImage[] dogs) |
protected boolean |
AbstractOctaveExtremaFinder.isLocalExtremum(float val,
FImage image,
int x,
int y)
Test to see if a point is a local extremum by searching the +/- 1 pixel
neighbourhood in x and y.
|
protected boolean |
AbstractOctaveExtremaFinder.isNotEdge(FImage image,
int x,
int y)
Test if the pixel at x,y in the image is NOT on an edge.
|
protected abstract void |
AbstractOctaveExtremaFinder.processExtrema(FImage[] images,
int s,
int x,
int y,
float octSize)
Perform any additional checks on the point, and then inform the listener
that a point has been found.
|
protected void |
BasicOctaveExtremaFinder.processExtrema(FImage[] dogs,
int s,
int x,
int y,
float octSize) |
protected void |
InterpolatingOctaveExtremaFinder.processExtrema(FImage[] dogs,
int s,
int x,
int y,
float octSize) |
protected void |
InterpolatingOctaveExtremaFinder.processExtremaInternal(FImage[] dogs,
int s,
int x,
int y,
float octSize) |
Modifier and Type | Method and Description |
---|---|
protected void |
BasicOctaveExtremaFinder.beforeProcess(GaussianOctave<FImage> octave) |
void |
InterpolatingOctaveExtremaFinder.process(GaussianOctave<FImage> octave) |
Modifier and Type | Class and Description |
---|---|
class |
DoGSIFTEngineOptions<IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>
Options for controlling SIFT feature localisation and extraction.
|
Modifier and Type | Method and Description |
---|---|
DoGSIFTEngineOptions<FImage> |
DoGSIFTEngine.getOptions() |
DoGSIFTEngineOptions<FImage> |
MinMaxDoGSIFTEngine.getOptions()
Get the options for this engine.
|
Modifier and Type | Method and Description |
---|---|
LocalFeatureList<Keypoint> |
ALTDoGSIFTEngine.findFeatures(FImage image) |
LocalFeatureList<Keypoint> |
DoGSIFTEngine.findFeatures(FImage image) |
LocalFeatureList<Keypoint> |
BasicGridSIFTEngine.findFeatures(FImage image) |
LocalFeatureList<MinMaxKeypoint> |
MinMaxDoGSIFTEngine.findFeatures(FImage image) |
LocalFeatureList<Keypoint> |
DoGColourSIFTEngine.findFeatures(MBFImage image,
FImage luminance)
Find DoG interest points in the given luminance image, but extract the
SIFT features from the colour image.
|
Constructor and Description |
---|
BasicGridSIFTEngine(boolean orientate,
DoGSIFTEngineOptions<FImage> options)
Construct with the given parameters.
|
DoGSIFTEngine(DoGSIFTEngineOptions<FImage> options)
Construct a DoGSIFTEngine with the given options.
|
MinMaxDoGSIFTEngine(DoGSIFTEngineOptions<FImage> options)
Construct a
MinMaxDoGSIFTEngine with the given options. |
Modifier and Type | Field and Description |
---|---|
protected AffineSimulationExtractor<LocalFeatureList<Keypoint>,Keypoint,FImage,Float> |
ASIFTEngine.asift |
Modifier and Type | Method and Description |
---|---|
LocalFeatureList<AffineSimulationKeypoint> |
ASIFTEngine.findFeatures(FImage image) |
LocalFeatureList<Keypoint> |
ASIFTEngine.findKeypoints(FImage image)
Find the features as a list of
Keypoint objects |
LocalFeatureList<Keypoint> |
ASIFTEngine.findKeypoints(FImage image,
AffineParams params)
Find the features of a single simulation as a list of
Keypoint
objects |
Map<AffineParams,LocalFeatureList<Keypoint>> |
ASIFTEngine.findKeypointsMapped(FImage image)
Find the features and return the resultant features in a per-simulation
format.
|
Constructor and Description |
---|
ASIFTEngine(DoGSIFTEngineOptions<FImage> opts)
Construct using 5 tilt levels and the given parameters for the internal
DoGSIFTEngine . |
ASIFTEngine(DoGSIFTEngineOptions<FImage> opts,
int nTilts)
Construct using the given numbe of tilt levels and parameters for the
internal
DoGSIFTEngine . |
Modifier and Type | Class and Description |
---|---|
class |
InterestPointImageExtractorProperties<P,I extends Image<P,I> & SinglebandImageProcessor.Processable<Float,FImage,I>> |
Modifier and Type | Method and Description |
---|---|
LocalFeatureList<InterestPointKeypoint<T>> |
AbstractIPDSIFTEngine.findFeatures(FImage image)
Find the interest points using the provided detector and extract a SIFT
descriptor per point.
|
Modifier and Type | Class and Description |
---|---|
class |
GradientScaleSpaceImageExtractorProperties<I extends Image<?,I> & SinglebandImageProcessor.Processable<Float,FImage,I>>
An extended
ScaleSpaceImageExtractorProperties that holds edge
responses in the form of gradient orientations and magnitudes. |
class |
LocalImageExtractorProperties<I extends Image<?,I> & SinglebandImageProcessor.Processable<Float,FImage,I>>
An extended
ExtractorProperties that holds the image being processed
and interest point location |
class |
ScaleSpaceImageExtractorProperties<I extends Image<?,I> & SinglebandImageProcessor.Processable<Float,FImage,I>>
An extended
LocalImageExtractorProperties that additionally holds the
interest point location scale. |
Modifier and Type | Field and Description |
---|---|
FImage |
GradientScaleSpaceImageExtractorProperties.magnitude
The gradient magnitude map
|
FImage |
GradientScaleSpaceImageExtractorProperties.orientation
The gradient orientation map
|
Modifier and Type | Class and Description |
---|---|
class |
InterestPointVisualiser<T,Q extends Image<T,Q> & SinglebandImageProcessor.Processable<Float,FImage,Q>>
Visualise the interest points extracted using an
InterestPointDetector . |
Modifier and Type | Field and Description |
---|---|
FImage |
AbstractStructureTensorIPD.lxmxblur |
FImage |
AbstractStructureTensorIPD.lxmyblur |
FImage |
AbstractStructureTensorIPD.lymyblur |
Modifier and Type | Method and Description |
---|---|
static <T,Q extends Image<T,Q> & SinglebandImageProcessor.Processable<Float,FImage,Q>> |
InterestPointVisualiser.visualiseInterestPoints(Q image,
List<? extends InterestPointData> keys)
Extract ellipses from second moment matricies of interest point keypoints
|
static <T,Q extends Image<T,Q> & SinglebandImageProcessor.Processable<Float,FImage,Q>> |
InterestPointVisualiser.visualiseInterestPoints(Q image,
List<? extends InterestPointData> keys,
double scale)
Extract ellipses from second moment matricies of interest point keypoints
|
static <T,Q extends Image<T,Q> & SinglebandImageProcessor.Processable<Float,FImage,Q>> |
InterestPointVisualiser.visualiseKeypoints(Q image,
List<? extends InterestPointKeypoint<? extends InterestPointData>> keys)
Extract ellipses from second moment matricies of interest point keypoints
|
Modifier and Type | Method and Description |
---|---|
FImage |
LaplaceIPD.createInterestPointMap() |
FImage |
HessianIPD.createInterestPointMap() |
FImage |
RidgeIPD.createInterestPointMap() |
abstract FImage |
AbstractStructureTensorIPD.createInterestPointMap() |
FImage |
HarrisIPD.createInterestPointMap() |
FImage |
QuadratureIPD.createInterestPointMap() |
Modifier and Type | Method and Description |
---|---|
protected void |
AbstractStructureTensorIPD.detectMaxima(FImage image,
Rectangle window) |
void |
AffineAdaption.findInterestPoints(FImage image) |
void |
InterestPointDetector.findInterestPoints(FImage image)
Find the interest points in an image
|
void |
AbstractStructureTensorIPD.findInterestPoints(FImage image) |
void |
AffineAdaption.findInterestPoints(FImage image,
Rectangle window) |
void |
InterestPointDetector.findInterestPoints(FImage image,
Rectangle window)
Find the interest points in an image
|
void |
AbstractStructureTensorIPD.findInterestPoints(FImage image,
Rectangle window) |
Point2dImpl |
SubPixelCorners.findSubPixCorner(FImage src,
Point2d corner)
Find the sub-pixel estimated position of a corner
|
List<Point2dImpl> |
SubPixelCorners.findSubPixCorners(FImage src,
List<? extends Point2d> corners)
Find the sub-pixel estimated position of each corner
|
void |
AbstractStructureTensorIPD.prepareInterestPoints(FImage image) |
Modifier and Type | Class and Description |
---|---|
class |
KeypointVisualizer<T,Q extends Image<T,Q> & SinglebandImageProcessor.Processable<Float,FImage,Q>>
Helpers for visualising (SIFT) interest points.
|
Modifier and Type | Method and Description |
---|---|
static <T,Q extends Image<T,Q> & SinglebandImageProcessor.Processable<Float,FImage,Q>> |
KeypointVisualizer.drawPatchesInplace(Q image,
List<? extends Keypoint> keypoints,
T boxColour,
T circleColour)
Draw the SIFT features onto an image.
|
Modifier and Type | Method and Description |
---|---|
FImage |
ImageClassificationModel.classifyImage(T im)
Classify the given image and return the corresponding probability map
|
FImage |
EigenImages.reconstruct(double[] weights)
Reconstruct an image from a weight vector
|
FImage |
EigenImages.reconstruct(DoubleFV weights)
Reconstruct an image from a weight vector
|
FImage |
FisherImages.visualise(int num)
Draw an eigenvector as an image
|
FImage |
EigenImages.visualisePC(int pc)
Draw a principal component as an image.
|
Modifier and Type | Method and Description |
---|---|
DoubleFV |
EigenImages.extractFeature(FImage img) |
DoubleFV |
FisherImages.extractFeature(FImage object) |
Modifier and Type | Method and Description |
---|---|
<KEY> void |
FisherImages.train(GroupedDataset<KEY,? extends ListDataset<FImage>,FImage> data)
Train on a grouped dataset.
|
<KEY> void |
FisherImages.train(GroupedDataset<KEY,? extends ListDataset<FImage>,FImage> data)
Train on a grouped dataset.
|
void |
EigenImages.train(List<? extends FImage> data) |
void |
FisherImages.train(List<? extends IndependentPair<?,FImage>> data) |
void |
FisherImages.train(Map<?,? extends List<FImage>> data)
Train on a map of data.
|
Modifier and Type | Class and Description |
---|---|
class |
MultiResolutionActiveShapeModel<I extends Image<?,I> & SinglebandImageProcessor.Processable<Float,FImage,I>>
Implementation of a basic Multi-resolution Active Shape Model.
|
Modifier and Type | Method and Description |
---|---|
static <I extends Image<?,I> & SinglebandImageProcessor.Processable<Float,FImage,I>> |
MultiResolutionActiveShapeModel.trainModel(int numLevels,
PrincipalComponentAnalysis.ComponentSelector selector,
List<IndependentPair<PointList,I>> data,
PointDistributionModel.Constraint constraint,
LandmarkModelFactory<I> factory)
Train a new
MultiResolutionActiveShapeModel from the given
data. |
Modifier and Type | Method and Description |
---|---|
protected FImage |
FPatchLandmarkModel.extractBlock(FImage image,
Point2d pt,
int sz) |
Modifier and Type | Method and Description |
---|---|
LandmarkModel<FImage> |
FPatchLandmarkModel.Factory.createLandmarkModel() |
LandmarkModel<FImage> |
FPatchLandmarkModel.Factory.createLandmarkModel(float scaleFactor) |
Modifier and Type | Method and Description |
---|---|
float |
FNormalLandmarkModel.computeCost(FImage image,
Point2d point,
PointList pointList) |
float |
FPatchLandmarkModel.computeCost(FImage image,
Point2d point,
PointList pointList) |
protected FImage |
FPatchLandmarkModel.extractBlock(FImage image,
Point2d pt,
int sz) |
void |
FNormalLandmarkModel.updateModel(FImage image,
Point2d point,
PointList pointList) |
void |
FPatchLandmarkModel.updateModel(FImage image,
Point2d point,
PointList pointList) |
ObjectFloatPair<Point2d> |
FNormalLandmarkModel.updatePosition(FImage image,
Point2d initial,
PointList pointList) |
ObjectFloatPair<Point2d> |
FPatchLandmarkModel.updatePosition(FImage image,
Point2d initial,
PointList pointList) |
Modifier and Type | Method and Description |
---|---|
FImage |
PatchClassificationModel.classifyImage(T im) |
FImage |
PatchClassificationModel.predict(T data) |
Modifier and Type | Method and Description |
---|---|
boolean |
PatchClassificationModel.estimate(List<? extends IndependentPair<T,FImage>> data) |
Modifier and Type | Method and Description |
---|---|
FImage |
PixelClassificationModel.classifyImage(T im) |
FImage |
PixelClassificationModel.predict(T data) |
Modifier and Type | Method and Description |
---|---|
boolean |
PixelClassificationModel.estimate(List<? extends IndependentPair<T,FImage>> data) |
Modifier and Type | Class and Description |
---|---|
class |
RotationSimulationObjectDetector<IMAGE extends Image<PIXEL,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>,PIXEL,DETECTED_OBJECT>
An
ObjectDetector that wraps another ObjectDetector and
performs rotation simulations on the images it passes to the internal
detector. |
Modifier and Type | Method and Description |
---|---|
static GroupedDataset<Boolean,ListDataset<FImage>,FImage> |
INRIAPersonDataset.getTrainingData() |
static GroupedDataset<Boolean,ListDataset<FImage>,FImage> |
INRIAPersonDataset.getTrainingData() |
Modifier and Type | Method and Description |
---|---|
List<Rectangle> |
Detector.detect(FImage image) |
Modifier and Type | Method and Description |
---|---|
static FImage |
DrawingTest.drawRects(WeightedRectangle[] rects) |
static FImage |
DrawingTest.drawRects(WeightedRectangle[] rects,
FImage image) |
Modifier and Type | Method and Description |
---|---|
static FImage |
DrawingTest.drawRects(WeightedRectangle[] rects,
FImage image) |
Modifier and Type | Method and Description |
---|---|
List<Rectangle> |
HOGDetector.detect(FImage image) |
void |
HOGClassifier.prepare(FImage image) |
Modifier and Type | Method and Description |
---|---|
String |
SimpleOCR.process(FImage image)
Extract the date-time from the given image
|
Modifier and Type | Method and Description |
---|---|
FImage |
PixelSet.calculateBinaryMask(Image<?,?> input)
Returns an image where the connected component is masked in the image.
|
FImage |
PixelSet.extractPixels1d(FImage input)
Extract a 1 x area image with all the pixels from the region in it.
|
FImage |
PixelSet.toFImage()
Returns a mask image for this connected component that will be the size
of this component's bounding box.
|
FImage |
PixelSet.toFImage(int padding)
Returns a mask image for this connected component that will be the size
of this component's bounding box plus a border of the given amount of
padding.
|
Modifier and Type | Method and Description |
---|---|
FImage |
PixelSet.extractPixels1d(FImage input)
Extract a 1 x area image with all the pixels from the region in it.
|
static ConnectedComponent |
ConnectedComponent.floodFill(FImage image,
Pixel start)
Performs a flood fill on the given image starting at the given pixel.
|
List<Pixel> |
ConnectedComponent.ConnectMode.getNeighbours(FImage image,
int x,
int y,
float bgThreshold)
Get the neighbouring pixels
|
Constructor and Description |
---|
ConnectedComponent(FImage mask,
float thresh)
Constructs a connected component from a mask image.
|
PixelSet(FImage mask,
float thresh)
Constructs a PixelSet from a mask image.
|
Modifier and Type | Method and Description |
---|---|
abstract float[] |
FLineSampler.extractSamples(Line2d line,
FImage image,
int numSamples) |
Line2d |
FLineSampler.getSampleLine(Line2d line,
FImage image,
int numSamples) |
Modifier and Type | Method and Description |
---|---|
float |
FStatisticalPixelProfileModel.computeCost(FImage image,
Line2d line) |
float |
FStatisticalPixelProfileModel.computeMahalanobis(FImage image,
Line2d line)
Compute the Mahalanobis distance of a vector of samples extracted along a
line in the given image to the internal model.
|
float[] |
FStatisticalPixelProfileModel.computeMahalanobisWindowed(FImage image,
Line2d line,
int numSamples)
Extract numSamples samples from the line in the image and then compare
this model at each overlapping position starting from the first sample at
the beginning of the line.
|
float |
FStatisticalPixelProfileModel.computeMovementDistance(FImage image,
Line2d line,
int numSamples,
Point2d pt) |
Point2d |
FStatisticalPixelProfileModel.computeNewBest(FImage image,
Line2d line,
int numSamples) |
void |
AbstractPixelStatisticsModel.estimateModel(FImage... images)
Estimate the model parameters from the given image(s).
|
void |
FStatisticalPixelProfileModel.updateModel(FImage image,
Line2d line) |
Constructor and Description |
---|
MaskingBlockHistogramModel(FImage mask,
int blocks_x,
int blocks_y,
int... nbins)
Construct with the given parameters
|
MaskingHistogramModel(FImage mask,
int... nbins)
Construct with the given parameters
|
Modifier and Type | Field and Description |
---|---|
FImage |
MinMaxAnalyser.max
The max filtered image computed from the last call to
MinMaxAnalyser.analyseImage(FImage) |
FImage |
MinMaxAnalyser.min
The min filtered image computed from the last call to
MinMaxAnalyser.analyseImage(FImage) |
FImage |
FourierCorrelation.template
The template image
|
Modifier and Type | Method and Description |
---|---|
static FImage |
FourierCorrelation.correlate(FImage image,
FImage template,
boolean inplace)
Correlate an image with a kernel using an FFT.
|
FImage |
FourierTransformComplex.getImaginary() |
FImage |
FourierTransform.getLogNormalisedMagnitude()
Get a log-normalised copy of the magnitude image suitable for displaying.
|
FImage |
FourierTransform.getMagnitude() |
FImage |
FourierTransform.getPhase() |
FImage |
FourierTransformComplex.getReal() |
FImage |
FourierTransform.inverse()
Perform the inverse FFT using the underlying magnitude and phase images.
|
FImage |
FourierTransformComplex.inverse()
Perform the inverse FFT using the underlying magnitude and phase images.
|
Modifier and Type | Method and Description |
---|---|
void |
MinMaxAnalyser.analyseImage(FImage image) |
static FImage |
FourierCorrelation.correlate(FImage image,
FImage template,
boolean inplace)
Correlate an image with a kernel using an FFT.
|
static void |
MaxFilter.filter(FImage img,
int times)
Apply the filter some number of times to an image with the default 3x3
block support
|
static float[][] |
FourierTransform.prepareData(FImage input,
int rs,
int cs,
boolean centre)
Prepare data for a input to the FFT, padding if necessary.
|
static float[] |
FourierTransform.prepareData1d(FImage input,
int rs,
int cs,
boolean centre)
Prepare data for a input to the FFT, padding if necessary.
|
void |
MeanCenter.processImage(FImage image) |
void |
LocalContrastFilter.processImage(FImage image) |
void |
MaxFilter.processImage(FImage image) |
void |
AnisotropicDiffusion.processImage(FImage image) |
void |
EqualisationProcessor.processImage(FImage image)
Equalise the colours in the image.
|
void |
MedianFilter.processImage(FImage image) |
void |
DifferenceOfGaussian.processImage(FImage image) |
void |
FourierCorrelation.processImage(FImage image) |
void |
MinFilter.processImage(FImage image) |
void |
MaskedRobustContrastEqualisation.processImage(FImage image) |
void |
AnisotropicDiffusion.processImageOneIteration(FImage image)
Perform a single iteration of anisotropic diffusion
|
static void |
FourierTransform.unprepareData(float[][] prepared,
FImage output,
boolean centre)
Extract the actual data from prepared data.
|
static void |
FourierTransform.unprepareData(float[] prepared,
FImage output,
boolean centre)
Extract the actual data from prepared data.
|
Constructor and Description |
---|
FourierCorrelation(FImage template)
Construct the correlation operator with the given template
|
FourierTransform(FImage image,
boolean centre)
Construct Fourier Transform by performing a forward transform on the
given image.
|
FourierTransform(FImage magnitude,
FImage phase,
boolean centre)
Construct Fourier Transform object from the given magnitude and phase
images in the frequency domain.
|
FourierTransformComplex(FImage image,
boolean centre)
Construct Fourier Transform by performing a forward transform on the
given image.
|
FourierTransformComplex(FImage real,
FImage imaginary,
boolean centre)
Construct Fourier Transform object from the given magnitude and phase
images in the frequency domain.
|
MaskedRobustContrastEqualisation(FImage mask)
Construct with a mask.
|
Modifier and Type | Field and Description |
---|---|
FImage |
FSobel.dx
The X gradients
|
FImage |
FSobel.dy
The Y gradients
|
FImage |
CLSobel.gradientX
The computed Sobel gradient in the X direction
|
FImage |
CLSobel.gradientY
The computed Sobel gradient in the Y direction
|
FImage |
FConvolution.kernel
The kernel
|
static FImage |
FSobelMagnitude.KERNEL_X
The 3x3 derivative of a gaussian of sigma 1 in the x direction
|
static FImage |
FSobelMagnitude.KERNEL_Y
The 3x3 derivative of a gaussian of sigma 1 in the x direction
|
FImage |
CLSobel.magnitude
The computed Sobel magnitude
|
FImage |
FImageGradients.magnitudes
The gradient magnitudes
|
FImage |
CLSobel.orientation
The computed Sobel orientations
|
FImage |
FImageGradients.orientations
The gradient orientations
|
Modifier and Type | Method and Description |
---|---|
static FImage |
FourierConvolve.convolve(FImage image,
float[][] kernel,
boolean inplace)
Convolve an image with a kernel using an FFT.
|
static FImage |
FourierConvolve.convolvePrepared(FImage image,
FImage filter,
boolean centered)
Convolve an image with a pre-prepared frequency domain filter.
|
static FImage[] |
GaborFilters.createGaborJets(int width,
int height,
int... orientationsPerScale)
Create a jet of (multiscale) Gabor filters in the frequency domain.
|
static FImage |
Disk.createKernelImage(int radius)
Makes a disk averaging filter with the given radius.
|
static FImage |
LaplacianOfGaussian2D.createKernelImage(int size,
float sigma)
Create a kernel image with given kernel size and variance.
|
static FImage |
Gaussian2D.createKernelImage(int size,
float sigma)
Create a kernel image with given kernel size and standard deviation.
|
static FImage |
LaplacianOfGaussian2D.createKernelImage(int width,
int height,
float sigma)
Create a kernel image with given kernel size and variance.
|
static FImage |
Gaussian2D.createKernelImage(int width,
int height,
float sigma)
Create a kernel image with given kernel size and standard deviation.
|
FImage |
CLSobel.getGradientX() |
FImage |
CLSobel.getGradientY() |
FImage |
CLSobel.getMagnitude() |
FImage |
CLSobel.getOrientation() |
Modifier and Type | Method and Description |
---|---|
void |
CLSobel.analyseImage(FImage image) |
void |
FSobel.analyseImage(FImage image) |
void |
FImageGradients.analyseImage(FImage image) |
static FImage |
FourierConvolve.convolve(FImage image,
float[][] kernel,
boolean inplace)
Convolve an image with a kernel using an FFT.
|
static void |
FImageConvolveSeparable.convolveHorizontal(FImage image,
float[] kernel)
Convolve the image in the horizontal direction with the kernel.
|
static FImage |
FourierConvolve.convolvePrepared(FImage image,
FImage filter,
boolean centered)
Convolve an image with a pre-prepared frequency domain filter.
|
static void |
FImageConvolveSeparable.convolveVertical(FImage image,
float[] kernel)
Convolve the image in the vertical direction with the kernel.
|
static void |
FImageConvolveSeparable.fastConvolve3(FImage source,
FImage dest,
float[] kx,
float[] ky,
float[] buffer)
Fast convolution for separated 3x3 kernels.
|
static FImageGradients |
FImageGradients.getGradientMagnitudesAndOrientations(FImage image)
Static helper to create a new
FImageGradients and call
FImageGradients.analyseImage(FImage) with the image. |
static FImageGradients |
FImageGradients.getGradientMagnitudesAndOrientations(FImage image,
FImageGradients.Mode mode)
Static helper to create a new
FImageGradients and call
FImageGradients.analyseImage(FImage) with the image. |
static void |
FImageGradients.gradientMagnitudesAndOrientations(FImage image,
FImage magnitudes,
FImage orientations)
Estimate gradients magnitudes and orientations by calculating pixel
differences.
|
static void |
FImageGradients.gradientMagnitudesAndQuantisedOrientations(FImage image,
FImage[] magnitudes)
Estimate gradients magnitudes and orientations by calculating pixel
differences.
|
static void |
FImageGradients.gradientMagnitudesAndQuantisedOrientations(FImage image,
FImage[] magnitudes)
Estimate gradients magnitudes and orientations by calculating pixel
differences.
|
static void |
FImageGradients.gradientMagnitudesAndQuantisedOrientations(FImage image,
FImage[] magnitudes,
boolean interp,
FImageGradients.Mode mode)
Estimate gradients magnitudes and orientations by calculating pixel
differences.
|
static void |
FImageGradients.gradientMagnitudesAndQuantisedOrientations(FImage image,
FImage[] magnitudes,
boolean interp,
FImageGradients.Mode mode)
Estimate gradients magnitudes and orientations by calculating pixel
differences.
|
static void |
FImageGradients.gradientMagnitudesAndUnsignedOrientations(FImage image,
FImage magnitudes,
FImage orientations)
Estimate gradients magnitudes and orientations by calculating pixel
differences.
|
void |
FDiscGausConvolve.processImage(FImage image) |
void |
FGaussianConvolve.processImage(FImage image) |
void |
SumBoxFilter.processImage(FImage image) |
void |
FConvolution.processImage(FImage image) |
void |
AverageBoxFilter.processImage(FImage image) |
void |
FFastGaussianConvolve.processImage(FImage image) |
void |
FTriangleFilter.processImage(FImage image) |
void |
FImageConvolveSeparable.processImage(FImage image) |
void |
FourierConvolve.processImage(FImage image) |
Float |
FSobelMagnitude.processKernel(FImage patch) |
float |
FConvolution.responseAt(int x,
int y,
FImage image)
Return the kernel response at the x,y in the given image.
|
Constructor and Description |
---|
FConvolution(FImage kernel)
Construct the convolution operator with the given kernel
|
FourierConvolve(FImage kernel)
Construct the convolution operator with the given kernel
|
Modifier and Type | Field and Description |
---|---|
protected FImage[] |
FilterBank.responses |
Modifier and Type | Method and Description |
---|---|
FImage[] |
FilterBank.getResponseImages()
Get the response images for the image analysed with
FilterBank.analyseImage(FImage) . |
protected static FImage |
LeungMalikFilterBank.makeFilter(float scale,
int phasex,
int phasey,
float angle,
int size) |
protected static FImage |
LeungMalikFilterBank.normalise(FImage f) |
FImage |
FilterBank.renderFilters(int numFiltersX)
Create an image to visualise the filters in the bank.
|
Modifier and Type | Method and Description |
---|---|
void |
LawsTexture.analyseImage(FImage in) |
void |
FilterBank.analyseImage(FImage in) |
void |
MR8FilterBank.analyseImage(FImage image) |
protected static FImage |
LeungMalikFilterBank.normalise(FImage f) |
Modifier and Type | Field and Description |
---|---|
FImage |
EdgeFinder.angle
The direction of each edge as worked out by the angle between the triangle formed by the dx and dy of a pixel
|
FImage |
EdgeFinder.magnitude
The magnitudes of each edge as worked out by the hypotenuse of the triangle formed by the dx and dy of a pixel
|
Modifier and Type | Method and Description |
---|---|
FImage |
NonMaximumSuppression.combine(FImage mag,
FImage ori)
Perform non-maximum suppression.
|
FImage |
NonMaximumSuppressionTangent.combine(FImage dxImage,
FImage dyImage)
Perform non-maximum suppression.
|
static FImage |
NonMaximumSuppression.computeSuppressed(FImage mag,
FImage ori)
Perform non-maximum suppression.
|
static FImage |
NonMaximumSuppressionTangent.computeSuppressed(FImage dxImage,
FImage dyImage)
Perform non-maximum suppression.
|
static FImage |
NonMaximumSuppressionTangent.computeSuppressed(FImage dxImage,
FImage dyImage,
FImage magsOut)
Perform non-maximum suppression.
|
FImage |
CannyEdgeDetector2.getEdgeImage()
Deprecated.
|
static FImage |
StrokeWidthTransform.normaliseImage(FImage input)
Normalise the output image of the
StrokeWidthTransform for
display. |
static FImage |
SUSANEdgeDetector.simpleSusan(FImage img,
double thresh,
double nmax)
Performs the simple SUSAN edge detection.
|
static FImage |
SUSANEdgeDetector.smoothCircularSusan(FImage img,
double thresh,
double nmax,
double radius)
Performs the simple SUSAN edge detection.
|
static FImage |
SUSANEdgeDetector.smoothSusan(FImage img,
double thresh,
double nmax)
Performs the simple SUSAN edge detection.
|
Modifier and Type | Method and Description |
---|---|
void |
EdgeFinder.analyseImage(FImage image) |
FImage |
NonMaximumSuppression.combine(FImage mag,
FImage ori)
Perform non-maximum suppression.
|
FImage |
NonMaximumSuppressionTangent.combine(FImage dxImage,
FImage dyImage)
Perform non-maximum suppression.
|
static FImage |
NonMaximumSuppression.computeSuppressed(FImage mag,
FImage ori)
Perform non-maximum suppression.
|
static FImage |
NonMaximumSuppressionTangent.computeSuppressed(FImage dxImage,
FImage dyImage)
Perform non-maximum suppression.
|
static FImage |
NonMaximumSuppressionTangent.computeSuppressed(FImage dxImage,
FImage dyImage,
FImage magsOut)
Perform non-maximum suppression.
|
static FImage |
StrokeWidthTransform.normaliseImage(FImage input)
Normalise the output image of the
StrokeWidthTransform for
display. |
void |
CannyEdgeDetector2.processImage(FImage image)
Deprecated.
Process an image.
|
void |
SUSANEdgeDetector.processImage(FImage image)
Process an image.
|
void |
StrokeWidthTransform.processImage(FImage image) |
void |
CannyEdgeDetector.processImage(FImage image) |
void |
CannyEdgeDetector.processImage(FImage output,
FImage dx,
FImage dy)
Apply non-max suppression and hysteresis thresholding based on the given
(Sobel) gradient maps and write the result to the given output image.
|
void |
CannyEdgeDetector.processImage(FImage image,
FSobel sobel)
Apply non-max suppression and hysteresis thresholding based using the
given
FSobel analyser to generate the gradients. |
void |
CannyEdgeDetector2.setSourceImage(FImage image)
Deprecated.
|
static FImage |
SUSANEdgeDetector.simpleSusan(FImage img,
double thresh,
double nmax)
Performs the simple SUSAN edge detection.
|
static FImage |
SUSANEdgeDetector.smoothCircularSusan(FImage img,
double thresh,
double nmax,
double radius)
Performs the simple SUSAN edge detection.
|
static FImage |
SUSANEdgeDetector.smoothSusan(FImage img,
double thresh,
double nmax)
Performs the simple SUSAN edge detection.
|
Modifier and Type | Method and Description |
---|---|
void |
DioramaEffect.processImage(FImage image) |
Modifier and Type | Method and Description |
---|---|
void |
OrientedPolygonExtractionProcessor.processImage(FImage image) |
Modifier and Type | Field and Description |
---|---|
protected FImage |
CLMAligner.mask |
Modifier and Type | Method and Description |
---|---|
FImage |
CLMAligner.align(CLMDetectedFace face) |
FImage |
ScalingAligner.align(DetectedFace face) |
FImage |
RotateScaleAligner.align(KEDetectedFace descriptor) |
FImage |
MeshWarpAligner.align(KEDetectedFace descriptor) |
FImage |
AffineAligner.align(KEDetectedFace descriptor) |
FImage |
FaceAligner.align(T face)
For the provided face detection, return an aligned version of the face.
|
FImage |
IdentityAligner.align(T face) |
FImage |
FaceAligner.getMask()
Return a mask image for aligned faces.
|
FImage |
CLMAligner.getMask() |
FImage |
RotateScaleAligner.getMask() |
FImage |
ScalingAligner.getMask() |
FImage |
MeshWarpAligner.getMask() |
FImage |
AffineAligner.getMask() |
FImage |
IdentityAligner.getMask() |
protected FImage |
MeshWarpAligner.getWarpedImage(FacialKeypoint[] kpts,
FImage patch,
Jama.Matrix tf0) |
Modifier and Type | Method and Description |
---|---|
protected FImage |
MeshWarpAligner.getWarpedImage(FacialKeypoint[] kpts,
FImage patch,
Jama.Matrix tf0) |
Constructor and Description |
---|
AffineAligner(FImage mask)
Construct with a mask (in the canonical frame) to apply after aligning
and default border percentage (0.225).
|
AffineAligner(FImage mask,
float facePatchBorderPercentage)
Construct with a mask (in the canonical frame) to apply after aligning
and default border percentage (0.225).
|
RotateScaleAligner(FImage mask)
Construct with a mask (in the canonical frame) to apply after alignment.
|
Modifier and Type | Field and Description |
---|---|
protected FImage |
DetectedFace.facePatch
The extracted sub-image representing the face.
|
Modifier and Type | Method and Description |
---|---|
protected FImage |
SandeepFaceDetector.generateFaceMap(FImage skin,
FImage edge) |
protected FImage |
SandeepFaceDetector.generateSkinColorMap(MBFImage inputHS) |
protected FImage |
SandeepFaceDetector.generateSobelMagnitudes(MBFImage inputRGB) |
FImage |
DetectedFace.getFacePatch()
Returns the sub-image representing the face.
|
Modifier and Type | Method and Description |
---|---|
static List<CLMDetectedFace> |
CLMDetectedFace.convert(List<MultiTracker.TrackedFace> faces,
FImage image)
Helper method to convert a list of
MultiTracker.TrackedFace s to
CLMDetectedFace s. |
List<DetectedFace> |
HaarCascadeDetector.detectFaces(FImage image) |
List<CLMDetectedFace> |
CLMFaceDetector.detectFaces(FImage image) |
List<CLMDetectedFace> |
CLMFaceDetector.detectFaces(FImage image,
List<Rectangle> detRects)
Detect faces in the image using the given rectangles as the seeds from
which to start fitting the model.
|
protected List<CCDetectedFace> |
SandeepFaceDetector.extractFaces(FImage faceMap,
FImage skinMap,
FImage image) |
protected FImage |
SandeepFaceDetector.generateFaceMap(FImage skin,
FImage edge) |
void |
DetectedFace.setFacePatch(FImage img)
Reset the face patch image
|
Constructor and Description |
---|
CCDetectedFace(Rectangle bounds,
FImage patch,
ConnectedComponent cc,
float confidence)
Construct with a bounds rectangle (the bounding box of the face in the
detection image),an image patch that describes the contents of the bounds
rectangle from the original image, and a
ConnectedComponent
describing the shape of the detected face. |
CLMDetectedFace(MultiTracker.TrackedFace face,
FImage image)
Construct a
CLMDetectedFace by copying the state from a
MultiTracker.TrackedFace |
CLMDetectedFace(Rectangle bounds,
Jama.Matrix shape,
Jama.Matrix poseParameters,
Jama.Matrix shapeParameters,
Jama.Matrix visibility,
FImage fullImage)
Construct with the given bounds, shape and pose parameters and detection
image.
|
DetectedFace(Rectangle bounds,
FImage patch,
float confidence)
Construct with a bounds rectangle (the bounding box of the face in the
detection image) and an image patch that describes the contents of the
bounds rectangle from the original image.
|
EllipticalDetectedFace(Ellipse ellipse,
FImage image,
float confidence)
Construct the
EllipticalDetectedFace from the given parameters. |
Modifier and Type | Method and Description |
---|---|
FImage |
FDDBRecord.getFImage() |
Modifier and Type | Field and Description |
---|---|
protected FaceDetector<? extends DetectedFace,FImage> |
FKEFaceDetector.faceDetector |
Modifier and Type | Method and Description |
---|---|
static FImage |
FKEFaceDetector.extractPatch(FImage image,
Jama.Matrix transform,
int size,
int border)
Extract a patch from the image based on the parameters.
|
static FImage |
FKEFaceDetector.pyramidResize(FImage image,
Jama.Matrix transform)
Resize the image using a pyramid.
|
Modifier and Type | Method and Description |
---|---|
List<KEDetectedFace> |
FKEFaceDetector.detectFaces(FImage image) |
FacialKeypoint[] |
FacialKeypointExtractor.extractFacialKeypoints(FImage canonicalImage)
Extract the facial keypoints from a canonical image.
|
static FImage |
FKEFaceDetector.extractPatch(FImage image,
Jama.Matrix transform,
int size,
int border)
Extract a patch from the image based on the parameters.
|
protected FacialKeypoint[] |
FacialKeypointExtractor.findParts(FImage[] AC) |
static FImage |
FKEFaceDetector.pyramidResize(FImage image,
Jama.Matrix transform)
Resize the image using a pyramid.
|
Constructor and Description |
---|
KEDetectedFace(Rectangle bounds,
FImage patch,
FacialKeypoint[] keypoints,
float confidence)
Construct with parameters.
|
Constructor and Description |
---|
FKEFaceDetector(FaceDetector<? extends DetectedFace,FImage> detector)
Construct with the given underlying (frontal) face detector.
|
FKEFaceDetector(FaceDetector<? extends DetectedFace,FImage> detector,
float patchScale)
Construct with the given underlying (frontal) face detector, and the
given scale-factor for extracting the face patch.
|
Modifier and Type | Method and Description |
---|---|
FImage |
FacePatchFeature.DetectedFacePart.getImage() |
Modifier and Type | Method and Description |
---|---|
protected void |
LocalLBPHistogram.initialise(FImage face,
FImage mask,
int blocksX,
int blocksY,
int samples,
int radius) |
Modifier and Type | Method and Description |
---|---|
protected FImage[] |
AbstractLtpDtFeature.constructSlices(List<List<Pixel>> ltpPixels,
int width,
int height) |
protected FImage[] |
AbstractLtpDtFeature.extractDistanceTransforms(FImage[] slices,
LTPWeighting weighting) |
FImage[] |
AbstractLtpDtFeature.getDistanceMaps()
Get the Euclidean distance maps for each slice.
|
protected static FImage |
AbstractLtpDtFeature.normaliseImage(FImage image,
FImage mask) |
Modifier and Type | Method and Description |
---|---|
protected FImage[] |
AbstractLtpDtFeature.extractDistanceTransforms(FImage[] slices,
LTPWeighting weighting) |
protected static List<List<Pixel>> |
AbstractLtpDtFeature.extractLTPSlicePixels(FImage image) |
protected static FImage |
AbstractLtpDtFeature.normaliseImage(FImage image,
FImage mask) |
Constructor and Description |
---|
LtpDtFeature(FImage face,
FImage mask,
LTPWeighting weighting)
Construct a
LtpDtFeature feature. |
Modifier and Type | Field and Description |
---|---|
protected FaceDetector<FACE,FImage> |
FaceRecognitionEngine.detector |
Modifier and Type | Method and Description |
---|---|
FaceDetector<FACE,FImage> |
FaceRecognitionEngine.getDetector() |
Modifier and Type | Method and Description |
---|---|
List<IndependentPair<FACE,List<ScoredAnnotation<PERSON>>>> |
FaceRecognitionEngine.recognise(FImage image)
Detect and recognise the faces in the given image, returning a list of
potential people for each face.
|
List<IndependentPair<FACE,List<ScoredAnnotation<PERSON>>>> |
FaceRecognitionEngine.recognise(FImage image,
Set<PERSON> restrict)
Detect and recognise the faces in the given image, returning a list of
potential people for each face.
|
List<IndependentPair<FACE,ScoredAnnotation<PERSON>>> |
FaceRecognitionEngine.recogniseBest(FImage image)
Detect and recognise the faces in the given image, returning the most
likely person for each face.
|
List<IndependentPair<FACE,ScoredAnnotation<PERSON>>> |
FaceRecognitionEngine.recogniseBest(FImage image,
Set<PERSON> restrict)
Detect and recognise the faces in the given image, returning the most
likely person for each face.
|
FACE |
FaceRecognitionEngine.train(PERSON person,
FImage image)
Train the recogniser with a single example, returning the detected face.
|
Modifier and Type | Method and Description |
---|---|
static <FACE extends DetectedFace,EXTRACTOR extends FeatureExtractor<?,FACE>,PERSON> |
FaceRecognitionEngine.create(FaceDetector<FACE,FImage> detector,
FaceRecogniser<FACE,PERSON> recogniser)
Create a
FaceRecognitionEngine with the given face detector and
recogniser. |
void |
FaceRecognitionEngine.train(GroupedDataset<PERSON,ListDataset<FImage>,FImage> dataset)
Train with a dataset
|
void |
FaceRecognitionEngine.train(GroupedDataset<PERSON,ListDataset<FImage>,FImage> dataset)
Train with a dataset
|
Constructor and Description |
---|
FaceRecognitionEngine(FaceDetector<FACE,FImage> detector,
FaceRecogniser<FACE,PERSON> recogniser)
Construct a
FaceRecognitionEngine with the given face detector
and recogniser. |
Modifier and Type | Method and Description |
---|---|
List<DetectedFace> |
KLTHaarFaceTracker.trackFace(FImage img)
Given the image, can a face be tracked on the image.
|
Modifier and Type | Field and Description |
---|---|
FImage |
MultiTracker.TrackedFace.templateImage
The template image
|
Modifier and Type | Method and Description |
---|---|
void |
CLMFaceTracker.track(FImage im)
Track the face in the given frame.
|
int |
MultiTracker.track(FImage im,
int[] wSize,
int fpd,
int nIter,
double clamp,
double fTol,
boolean fcheck,
float searchAreaSize)
Track faces from a previous frame to the given frame.
|
protected Rectangle |
MultiTracker.updateTemplate(MultiTracker.TrackedFace f,
FImage im,
Jama.Matrix s,
boolean resize) |
Modifier and Type | Method and Description |
---|---|
static FImage |
MatteGenerator.generateMatte(FImage image,
MatteGenerator.MatteType type,
Object... args)
Generate a matte into the given
FImage . |
static FImage |
MatteGenerator.generateMatte(MBFImage image,
int band,
MatteGenerator.MatteType type,
Object... args)
Generate a matte into the given image on the given band.
|
Modifier and Type | Method and Description |
---|---|
static FImage |
MatteGenerator.generateMatte(FImage image,
MatteGenerator.MatteType type,
Object... args)
Generate a matte into the given
FImage . |
abstract void |
MatteGenerator.MatteType.generateMatte(FImage img,
Object... args)
Generate the matte into the given image.
|
Modifier and Type | Method and Description |
---|---|
static void |
Dilate.dilate(FImage img,
int times)
Apply dilation some number of times to an image with the default
StructuringElement.BOX element |
static void |
Erode.erode(FImage img,
int times)
Apply erosion some number of times to an image with the default
StructuringElement.BOX element |
void |
Open.processImage(FImage image) |
void |
SequentialThin.processImage(FImage image) |
void |
Thicken.processImage(FImage image) |
void |
Thin.processImage(FImage image) |
void |
Close.processImage(FImage image) |
Float |
Dilate.processKernel(FImage patch) |
Float |
HitAndMiss.processKernel(FImage patch) |
Float |
Erode.processKernel(FImage patch) |
Modifier and Type | Method and Description |
---|---|
static <I extends Image<?,I> & SinglebandImageProcessor.Processable<Float,FImage,I>> |
ResizeProcessor.doubleSize(I image)
Double the size of the image.
|
static <I extends Image<?,I> & SinglebandImageProcessor.Processable<Float,FImage,I>> |
ResizeProcessor.halfSize(I image)
Halve the size of the image.
|
Modifier and Type | Method and Description |
---|---|
static FImage |
ResizeProcessor.doubleSize(FImage image)
Double the size of the image.
|
static FImage |
ResizeProcessor.halfSize(FImage image)
Halve the size of the image.
|
static FImage |
ResizeProcessor.resample(FImage in,
int newX,
int newY)
Returns a new image that is a resampled version of the given image.
|
static FImage |
ResizeProcessor.resample(FImage in,
int newX,
int newY,
boolean aspect)
Resamples the given image returning it as a reference.
|
static FImage |
ResizeProcessor.resample(FImage in,
int newX,
int newY,
boolean aspect,
ResizeFilterFunction filterf)
Resamples the given image returning it as a reference.
|
static FImage |
ResizeProcessor.resizeMax(FImage image,
int maxDim)
Resize an image such that its biggest size is at most as big as the given
size.
|
static FImage |
ResizeProcessor.resizeMax(FImage image,
int maxDim,
ResizeFilterFunction filterf)
Resize an image such that its biggest size is at most as big as the given
size.
|
static FImage |
ResizeProcessor.resizeMaxArea(FImage image,
int maxArea)
Resize an image such that its area size is at most as big as the given
area.
|
static FImage |
ResizeProcessor.resizeMaxArea(FImage image,
int maxArea,
ResizeFilterFunction filterf)
Resize an image such that its area size is at most as big as the given
area.
|
static FImage |
ResizeProcessor.zoom(FImage in,
FImage dst,
ResizeFilterFunction filterf)
Resizes bitmaps while resampling them.
|
static FImage |
ResizeProcessor.zoom(FImage in,
Rectangle inRect,
FImage dst,
Rectangle dstRect)
Draws one portion of an image into another, resampling as necessary using
the default filter function.
|
static FImage |
ResizeProcessor.zoom(FImage in,
Rectangle inRect,
FImage dst,
Rectangle dstRect,
ResizeFilterFunction filterf)
Draws one portion of an image into another, resampling as necessary.
|
static FImage |
ResizeProcessor.zoomInplace(FImage in,
int newX,
int newY)
Resizes an image.
|
static FImage |
ResizeProcessor.zoomInplace(FImage in,
int newX,
int newY,
ResizeFilterFunction filterf)
Resizes an image.
|
Modifier and Type | Method and Description |
---|---|
static FImage |
ResizeProcessor.doubleSize(FImage image)
Double the size of the image.
|
static FImage |
ResizeProcessor.halfSize(FImage image)
Halve the size of the image.
|
protected static void |
ResizeProcessor.internalDoubleSize(FImage image) |
protected static void |
ResizeProcessor.internalHalfSize(FImage image) |
void |
BilinearInterpolation.processImage(FImage image) |
void |
BicubicInterpolation.processImage(FImage image) |
void |
FixedResizeProcessor.processImage(FImage in)
Process an image.
|
void |
ResizeProcessor.processImage(FImage image)
Process an image.
|
static FImage |
ResizeProcessor.resample(FImage in,
int newX,
int newY)
Returns a new image that is a resampled version of the given image.
|
static FImage |
ResizeProcessor.resample(FImage in,
int newX,
int newY,
boolean aspect)
Resamples the given image returning it as a reference.
|
static FImage |
ResizeProcessor.resample(FImage in,
int newX,
int newY,
boolean aspect,
ResizeFilterFunction filterf)
Resamples the given image returning it as a reference.
|
static FImage |
ResizeProcessor.resizeMax(FImage image,
int maxDim)
Resize an image such that its biggest size is at most as big as the given
size.
|
static FImage |
ResizeProcessor.resizeMax(FImage image,
int maxDim,
ResizeFilterFunction filterf)
Resize an image such that its biggest size is at most as big as the given
size.
|
static FImage |
ResizeProcessor.resizeMaxArea(FImage image,
int maxArea)
Resize an image such that its area size is at most as big as the given
area.
|
static FImage |
ResizeProcessor.resizeMaxArea(FImage image,
int maxArea,
ResizeFilterFunction filterf)
Resize an image such that its area size is at most as big as the given
area.
|
static FImage |
ResizeProcessor.zoom(FImage in,
FImage dst,
ResizeFilterFunction filterf)
Resizes bitmaps while resampling them.
|
static FImage |
ResizeProcessor.zoom(FImage in,
Rectangle inRect,
FImage dst,
Rectangle dstRect)
Draws one portion of an image into another, resampling as necessary using
the default filter function.
|
static FImage |
ResizeProcessor.zoom(FImage in,
Rectangle inRect,
FImage dst,
Rectangle dstRect,
ResizeFilterFunction filterf)
Draws one portion of an image into another, resampling as necessary.
|
static FImage |
ResizeProcessor.zoomInplace(FImage in,
int newX,
int newY)
Resizes an image.
|
static FImage |
ResizeProcessor.zoomInplace(FImage in,
int newX,
int newY,
ResizeFilterFunction filterf)
Resizes an image.
|
Constructor and Description |
---|
FixedResizeProcessor(FImage image,
int newX,
int newY) |
Modifier and Type | Class and Description |
---|---|
class |
AbstractFMMInpainter<IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>
Abstract base class for inpainting algorithms based on the Fast Marching
Method (FMM) for selecting the order of pixels to paint.
|
class |
TeleaInpainting<IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>
Implementation of Alexandru Telea's FMM-based inpainting algorithm.
|
Modifier and Type | Field and Description |
---|---|
protected FImage |
AbstractImageMaskInpainter.mask
The mask image
|
protected FImage |
AbstractFMMInpainter.timeMap
The space-time map (T)
|
Modifier and Type | Method and Description |
---|---|
protected void |
TeleaInpainting.inpaint(int x,
int y,
FImage input) |
void |
Inpainter.setMask(FImage mask)
Set the mask.
|
void |
AbstractImageMaskInpainter.setMask(FImage mask) |
Modifier and Type | Method and Description |
---|---|
static float |
OtsuThreshold.calculateThreshold(FImage img,
int numBins)
Estimate the threshold for the given image.
|
protected static int[] |
OtsuThreshold.makeHistogram(FImage fimg,
int numBins) |
void |
AdaptiveLocalThresholdMedian.processImage(FImage image) |
void |
AdaptiveLocalThresholdGaussian.processImage(FImage image) |
void |
AdaptiveLocalThresholdContrast.processImage(FImage image) |
void |
AdaptiveLocalThresholdBernsen.processImage(FImage image) |
void |
OtsuThreshold.processImage(FImage image) |
void |
AdaptiveLocalThresholdMean.processImage(FImage image) |
Modifier and Type | Class and Description |
---|---|
class |
AffineSimulation<I extends Image<P,I> & SinglebandImageProcessor.Processable<Float,FImage,I>,P>
Utility methods to simulate affine transformations defined by a rotation and
tilt, or series of rotations and tilts.
|
Modifier and Type | Method and Description |
---|---|
static <I extends Image<P,I> & SinglebandImageProcessor.Processable<Float,FImage,I>,P> |
AffineSimulation.transformImage(I image,
AffineParams params)
Compute a single transformed image for a given rotation and tilt.
|
static <I extends Image<P,I> & SinglebandImageProcessor.Processable<Float,FImage,I>,P> |
AffineSimulation.transformImage(I image,
float theta,
float t)
Compute a single transformed image for a given rotation and tilt.
|
static <I extends Image<P,I> & SinglebandImageProcessor.Processable<Float,FImage,I>,P> |
AffineSimulation.transformImage(I image,
int numTilts)
Compute the transformed images based on the given number of tilts.
|
Modifier and Type | Method and Description |
---|---|
FImage |
FProjectionProcessor.performBlendedProjection(int windowMinC,
int windowMaxC,
int windowMinR,
int windowMaxR,
Float backgroundColour)
Perform blended projection but only request data for pixels within the windowed range provided.
|
FImage |
FProjectionProcessor.performProjection(int windowMinC,
int windowMaxC,
int windowMinR,
int windowMaxR,
Float backgroundColour)
Perform projection but only request data for pixels within the windowed range provided.
|
static FImage |
RemapProcessor.remap(FImage in,
FImage xords,
FImage yords)
Transform an image using the given parameters.
|
static FImage |
RemapProcessor.remap(FImage in,
FImage out,
FImage xords,
FImage yords)
Transform an image using the given parameters, and write the results into
out . |
static FImage |
RemapProcessor.remap(FImage in,
FImage out,
FImage xords,
FImage yords,
ImageInterpolation interpolation)
Transform an image using the given parameters, and write te results into
out |
static FImage |
RemapProcessor.remap(FImage in,
FImage xords,
FImage yords,
ImageInterpolation.Interpolator interpolator)
Transform an image using the given parameters
|
static FImage |
RemapProcessor.remap(FImage in,
FImage xords,
FImage yords,
ImageInterpolation interpolation)
Transform an image using the given parameters
|
Modifier and Type | Method and Description |
---|---|
void |
RemapProcessor.processImage(FImage image) |
void |
SkewCorrector.processImage(FImage image)
Process an image.
|
static FImage |
RemapProcessor.remap(FImage in,
FImage xords,
FImage yords)
Transform an image using the given parameters.
|
static FImage |
RemapProcessor.remap(FImage in,
FImage out,
FImage xords,
FImage yords)
Transform an image using the given parameters, and write the results into
out . |
static FImage |
RemapProcessor.remap(FImage in,
FImage out,
FImage xords,
FImage yords,
ImageInterpolation interpolation)
Transform an image using the given parameters, and write te results into
out |
static FImage |
RemapProcessor.remap(FImage in,
FImage xords,
FImage yords,
ImageInterpolation.Interpolator interpolator)
Transform an image using the given parameters
|
static FImage |
RemapProcessor.remap(FImage in,
FImage xords,
FImage yords,
ImageInterpolation interpolation)
Transform an image using the given parameters
|
Constructor and Description |
---|
RemapProcessor(FImage xords,
FImage yords)
Construct with the given distortion map, and use
ImageInterpolation.InterpolationType.BILINEAR interpolation. |
RemapProcessor(FImage xords,
FImage yords,
ImageInterpolation.Interpolator interpolator)
Construct with the given distortion map and interpolator.
|
Modifier and Type | Method and Description |
---|---|
static ImageProcessor<MBFImage> |
ProcessorUtilities.wrap(SinglebandImageProcessor<Float,FImage> proc)
|
Modifier and Type | Field and Description |
---|---|
protected FImage |
ConfigurableRendererMono.image
The image to draw into
|
Modifier and Type | Method and Description |
---|---|
FImage |
ConfigurableRendererMono.getImage()
Get the rendered image.
|
Constructor and Description |
---|
ConfigurableRendererMono(FImage image,
EnumSet<ConfigurableRenderOptions> options)
Constructor that takes an image to draw into and a set of options to draw.
|
Constructor and Description |
---|
FImageRenderer(FImage targetImage)
Construct with given target image.
|
FImageRenderer(FImage targetImage,
RenderHints hints)
Construct with given target image and rendering hints.
|
Modifier and Type | Field and Description |
---|---|
protected FImage |
AchantaSaliency.map |
protected FImage |
YehSaliency.map |
Modifier and Type | Method and Description |
---|---|
FImage |
LuoTangSubjectRegion.getROIMap() |
FImage |
AchantaSaliency.getSaliencyMap() |
FImage |
SaliencyMapGenerator.getSaliencyMap()
Get the generated saliency map
|
FImage |
DepthOfFieldEstimator.getSaliencyMap() |
FImage |
LuoTangSubjectRegion.getSaliencyMap() |
FImage |
YehSaliency.getSaliencyMap() |
Modifier and Type | Method and Description |
---|---|
void |
DepthOfFieldEstimator.analyseImage(FImage image) |
void |
LuoTangSubjectRegion.analyseImage(FImage image) |
Modifier and Type | Class and Description |
---|---|
class |
FelzenszwalbHuttenlocherSegmenter<I extends Image<?,I> & SinglebandImageProcessor.Processable<Float,FImage,I>>
Implementation of the segmentation algorithm described in:
Efficient Graph-Based Image Segmentation
Pedro F.
|
Modifier and Type | Method and Description |
---|---|
List<? extends PixelSet> |
ThresholdSegmenter.segment(FImage image) |
List<ConnectedComponent> |
ConnectedThresholdSegmenter.segment(FImage image) |
Constructor and Description |
---|
ConnectedThresholdSegmenter(Processor<FImage> thresholder,
ConnectedComponent.ConnectMode mode)
Construct with the given thresholding algorithm implementation and
connection mode.
|
ConnectedThresholdSegmenter(Processor<FImage> thresholder,
ConnectedComponentLabeler.Algorithm algorithm,
ConnectedComponent.ConnectMode mode)
Construct with the given thresholding algorithm implementation.
|
ThresholdSegmenter(Processor<FImage> thresholder)
Construct with the given thresholding algorithm implementation.
|
Modifier and Type | Method and Description |
---|---|
FImage |
LiuSamarabanduTextExtractorMultiscale.PyramidTextExtractor.getFeatureMap()
Get the feature map for the image.
|
FImage |
LiuSamarabanduTextExtractorBasic.textRegionDetection(FImage image)
Calculate the feature map that give the approximate localisation of
candidate text regions.
|
Modifier and Type | Method and Description |
---|---|
Map<Rectangle,FImage> |
LiuSamarabanduTextExtractorBasic.getTextRegions()
Returns a map of bounding box to image and textual string.
|
Map<Rectangle,FImage> |
LiuSamarabanduTextExtractorMultiscale.getTextRegions()
Get the text regions that can be extracted from an image.
|
Map<Rectangle,FImage> |
LiuSamarabanduTextExtractorBasic.textRegionLocalisation(FImage fmap,
FImage image)
Extract the regions that probably contain text (as given by the feature
map)
|
Modifier and Type | Method and Description |
---|---|
void |
LiuSamarabanduTextExtractorBasic.processFeatureMap(FImage fmap,
FImage image)
Process a feature map.
|
void |
LiuSamarabanduTextExtractorBasic.processImage(FImage image)
Process an image.
|
void |
LiuSamarabanduTextExtractorMultiscale.processImage(FImage image)
Process an image.
|
FImage |
LiuSamarabanduTextExtractorBasic.textRegionDetection(FImage image)
Calculate the feature map that give the approximate localisation of
candidate text regions.
|
Map<Rectangle,FImage> |
LiuSamarabanduTextExtractorBasic.textRegionLocalisation(FImage fmap,
FImage image)
Extract the regions that probably contain text (as given by the feature
map)
|
Modifier and Type | Method and Description |
---|---|
void |
LiuSamarabanduTextExtractorMultiscale.PyramidTextExtractor.process(GaussianPyramid<FImage> pyramid)
Process the given pyramid.
|
Modifier and Type | Method and Description |
---|---|
void |
SWTTextDetector.analyseImage(FImage image) |
protected void |
SWTTextDetector.analyseImage(FImage image,
FImage swt) |
protected abstract void |
SWTTextDetector.Direction.detect(FImage image,
SWTTextDetector detector) |
protected static List<LetterCandidate> |
LetterCandidate.findLetters(List<ConnectedComponent> components,
FImage swt,
FImage image,
SWTTextDetector.Options options)
Filter the components to find likely letter candidates.
|
Constructor and Description |
---|
LetterCandidate(PixelSet cc,
float medianStrokeWidth,
FImage image) |
Modifier and Type | Field and Description |
---|---|
static ImageFromURL<FImage> |
ImageFromURL.FIMAGE_EXTRACTOR
Static instance of the
ImageFromURL for extracting FImage
s |
Modifier and Type | Method and Description |
---|---|
FImage |
FaceSimilarityTool.ImageGetter.getImage(List<T> list,
int index)
Get the image associated with the item
|
Modifier and Type | Method and Description |
---|---|
abstract FaceSimilarityEngine<?,?,FImage> |
PredefinedStrategy.strategy() |
Modifier and Type | Method and Description |
---|---|
List<DetectedFace> |
FaceDetectorTool.detectFaces(FImage img,
int minSize,
boolean displayResults)
Takes a single image and detects faces, returning a map that maps
a number (the face number) to the rectangle of the detected face.
|
Modifier and Type | Method and Description |
---|---|
Map<String,Map<String,Double>> |
FaceSimilarityTool.getDistances(File first,
List<File> others,
FaceSimilarityEngine<?,?,FImage> strategy)
Calculates the distance between all the faces in the first image with all
the faces in the given images.
|
Map<String,Map<String,Double>> |
FaceSimilarityTool.getDistances(List<File> inputFiles,
boolean withFirst,
FaceSimilarityEngine<?,?,FImage> strategy)
Calculates the distance between faces in the given images.
|
Map<String,Map<String,Double>> |
FaceSimilarityTool.getDistances(List<File> inputFiles,
FaceSimilarityEngine<?,?,FImage> strategy)
Calculates the distance between faces in the given images.
|
Map<String,Map<String,Double>> |
FaceSimilarityTool.getDistances(List<String> imageIdentifiers,
List<FImage> inputImages,
boolean withFirst,
FaceSimilarityEngine<?,?,FImage> strategy)
Calculates the distance between faces in the given images.
|
Map<String,Map<String,Double>> |
FaceSimilarityTool.getDistances(List<String> imageIdentifiers,
List<FImage> inputImages,
boolean withFirst,
FaceSimilarityEngine<?,?,FImage> strategy)
Calculates the distance between faces in the given images.
|
<T> Map<String,Map<String,Double>> |
FaceSimilarityTool.getDistances(List<T> inputList,
boolean withFirst,
FaceSimilarityTool.ImageGetter<T> iGetter,
FaceSimilarityEngine<?,?,FImage> strategy)
This is the actual comparison function that performs the nested loops as
necessary to match all the faces against each other.
|
Modifier and Type | Method and Description |
---|---|
FaceDetector<FACE,FImage> |
Aligners.AlignerDetectorProvider.getDetector() |
abstract FaceDetectors.FaceDetectorProvider<DetectedFace,FImage> |
FaceDetectors.AnyBasicFImageDetector.getOptions() |
Modifier and Type | Method and Description |
---|---|
protected ConnectedComponent |
ShapeFeatures.c(FImage mask) |
FeatureVector |
ShapeFeatures.ShapeFeaturesOp.execute(MBFImage image,
FImage mask)
Calculate a feature using the shape defined by the mask and possibly
the pixel values from the image.
|
abstract FeatureVector |
GlobalFeatureExtractor.extract(MBFImage image,
FImage mask)
Create the feature from the image and optional mask.
|
Modifier and Type | Method and Description |
---|---|
FeatureVector |
WeberContrastExtractor.extract(MBFImage image,
FImage mask) |
FeatureVector |
HaarFacesExtractor.extract(MBFImage image,
FImage mask) |
FeatureVector |
SharpnessExtractor.extract(MBFImage image,
FImage mask) |
FeatureVector |
LocalHistogramExtractor.extract(MBFImage image,
FImage mask) |
FeatureVector |
RuleOfThirdsExtractor.extract(MBFImage image,
FImage mask) |
FeatureVector |
HueStatsExtractor.extract(MBFImage image,
FImage mask) |
FeatureVector |
EDCHExtractor.extract(MBFImage image,
FImage mask) |
FeatureVector |
RoiProportionExtractor.extract(MBFImage image,
FImage mask) |
FeatureVector |
ModifiedLuoSimplicityExtractor.extract(MBFImage image,
FImage mask) |
FeatureVector |
MaxHistogramExtractor.extract(MBFImage image,
FImage mask) |
FeatureVector |
HistogramExtractor.extract(MBFImage image,
FImage mask) |
FeatureVector |
SharpPixelProportionExtractor.extract(MBFImage image,
FImage mask) |
FeatureVector |
ColourfulnessExtractor.extract(MBFImage image,
FImage mask) |
FeatureVector |
LrIntensityBalanceExtractor.extract(MBFImage image,
FImage mask) |
FeatureVector |
ColourContrastExtractor.extract(MBFImage image,
FImage mask) |
FeatureVector |
AverageBrightnessExtractor.extract(MBFImage image,
FImage mask) |
FeatureVector |
HorizontalIntensityDistributionExtractor.extract(MBFImage image,
FImage mask) |
FeatureVector |
ColourFacesExtractor.extract(MBFImage image,
FImage mask) |
FeatureVector |
NaturalnessExtractor.extract(MBFImage image,
FImage mask) |
FeatureVector |
LuoSimplicityExtractor.extract(MBFImage image,
FImage mask) |
Modifier and Type | Method and Description |
---|---|
char |
KNNCharacterClassifier.classify(FImage img)
Classify the given image with the nearest neighbour classifier.
|
double[] |
KNNCharacterClassifier.getImageVector(FImage img)
Get the feature vector for a single image.
|
void |
KNNCharacterClassifier.ImageTrainer.imageCreated(FImage img)
Implementation of the
FontSimulator.FontSimListener interface. |
Modifier and Type | Method and Description |
---|---|
protected FImage |
MDS.render(List<IndependentPair<String,Point2d>> pts,
int sz) |
Modifier and Type | Method and Description |
---|---|
protected FImage |
QuantisedSIFTPatchExtractor.loadCorrespondingImage(File feature) |
Modifier and Type | Method and Description |
---|---|
protected FImage |
FImageFileBackedVideo.loadImage(File f) |
Modifier and Type | Method and Description |
---|---|
static VideoDisplay<FImage> |
VideoDisplay.createVideoDisplay(FImage[] images)
Convenience function to create a VideoDisplay from an array of images
|
Modifier and Type | Method and Description |
---|---|
static VideoDisplay<FImage> |
VideoDisplay.createVideoDisplay(FImage[] images)
Convenience function to create a VideoDisplay from an array of images
|
Constructor and Description |
---|
GreyscaleSlitScanProcessor(FImage timemap)
Default constructor for using the video processor in an ad-hoc manner.
|
GreyscaleSlitScanProcessor(FImage timemap,
int cacheSize)
Default constructor for using the video processor in an ad-hoc manner.
|
GreyscaleSlitScanProcessor(Video<MBFImage> video,
FImage timemap,
int cacheSize)
Constructor for creating a video processor which is chainable.
|
Modifier and Type | Method and Description |
---|---|
void |
MotionEstimator.analyseFrame(FImage frame)
Analyse the given frame and make no changes to the frame.
|
Modifier and Type | Method and Description |
---|---|
Point2d |
MotionEstimatorAlgorithm.PHASE_CORRELATION.estimateMotion(VideoSubFrame<FImage> img2sub,
VideoSubFrame<FImage>... imagesSub)
Calculate the estimated motion vector between
images
which [0] is first in the sequence and img2 which is
second in the sequence. |
protected Map<Point2d,Point2d> |
GridMotionEstimator.estimateMotionField(MotionEstimatorAlgorithm estimator,
VideoFrame<FImage> vf,
VideoFrame<FImage>[] array)
This method needs to be overridden for specific layouts of motion
field within the image.
|
protected abstract Map<Point2d,Point2d> |
MotionEstimator.estimateMotionField(MotionEstimatorAlgorithm estimator,
VideoFrame<FImage> frame,
VideoFrame<FImage>[] array)
This method needs to be overridden for specific layouts of motion
field within the image.
|
Constructor and Description |
---|
GridMotionEstimator(Video<FImage> v,
MotionEstimatorAlgorithm alg,
int x,
int y,
boolean fixed)
Construct a chained grid-based motion estimator.
|
MotionEstimator(Video<FImage> v,
MotionEstimatorAlgorithm alg)
Create a chainable motion estimator.
|
Modifier and Type | Method and Description |
---|---|
FImage |
FMeanVarianceField.getMean()
Get the mean field of all the frames that have been analysed so far.
|
FImage |
FMeanVarianceField.getVariance()
Get the variance field of all the frames that have been analysed so far.
|
Modifier and Type | Method and Description |
---|---|
void |
FMeanVarianceField.analyseFrame(FImage frame) |
Modifier and Type | Method and Description |
---|---|
List<Rectangle> |
BasicObjectTracker.initialiseTracking(Rectangle bounds,
FImage img)
Initialise this tracker with a particular area on a particular
image.
|
List<Rectangle> |
BasicObjectTracker.trackObject(FImage img)
Reset this tracker using the given image
|
Modifier and Type | Method and Description |
---|---|
void |
TrackingContext.computeGradients(FImage img,
float sigma,
FImage gradx,
FImage grady)
_KLTComputeGradients
|
MBFImage |
FeatureList.drawFeatures(FImage img)
KLTWriteFeatureListToPPM
|
void |
KLTTracker.replaceLostFeatures(FImage img)
KLTReplaceLostFeatures
Main routine, visible to the outside.
|
void |
KLTTracker.selectGoodFeatures(FImage img)
KLTSelectGoodFeatures
Main routine, visible to the outside.
|
void |
KLTTracker.trackFeatures(FImage img1,
FImage img2)
KLTTrackFeatures
Tracks feature points from one image to the next.
|
void |
KLTTracker.trackFeatures(FImage img1,
FImage img2,
PyramidSet pyr1,
PyramidSet pyr2)
KLTTrackFeatures
Tracks feature points from one image to the next.
|
Constructor and Description |
---|
PyramidSet(FImage image,
TrackingContext tc) |
Modifier and Type | Method and Description |
---|---|
FImage |
MBFImageToFImageVideoTranslator.translateFrame(MBFImage nextFrame)
Translates the MBFImage video frame to an FImage video frame
using
Transforms.calculateIntensity(MBFImage) . |
Modifier and Type | Method and Description |
---|---|
MBFImage |
FImageToMBFImageVideoTranslator.translateFrame(FImage nextFrame) |
Constructor and Description |
---|
FImageToMBFImageVideoTranslator(Video<FImage> in)
Create a translator using the input video.
|
Modifier and Type | Method and Description |
---|---|
static HeightMap3D |
HeightMap3D.createFromFImage(FImage img)
Create a height map from an FImage.
|
Modifier and Type | Class and Description |
---|---|
class |
AdaptiveMoGBackgroundEstimator<IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>> |
class |
EfrosLeungInpainter<IMAGE extends Image<?,IMAGE> & SinglebandImageProcessor.Processable<Float,FImage,IMAGE>>
FIXME: Finish implementation (it works but is incredibly slow!)
|
Modifier and Type | Method and Description |
---|---|
void |
LOCKY.findInterestPoints(FImage image) |
void |
LOCKY.findInterestPoints(FImage image,
Rectangle window) |
String |
Snap.getGridRef(FImage image)
Estimate a grid reference from an image using the MapSnapper algorithm.
|
protected void |
EfrosLeungInpainter.performInpainting(FImage image) |
void |
BrightnessClusteringTransform.processImage(FImage image) |
Constructor and Description |
---|
MovingEdges(FImage[] sequence,
Processor<FImage> proc,
int niters,
float kappa) |
Constructor and Description |
---|
MovingEdges(FImage[] sequence,
Processor<FImage> proc,
int niters,
float kappa) |
Modifier and Type | Method and Description |
---|---|
static List<FImage> |
RandomPatchSampler.loadPatches(File file) |
Modifier and Type | Method and Description |
---|---|
DoubleFV |
TestImageClass.extractFeature(FImage bigpatch) |