org.openimaj.image.processing.threshold

Class OtsuThreshold

java.lang.Object

org.openimaj.image.processing.threshold.OtsuThreshold

All Implemented Interfaces:

ImageProcessor<FImage>, Processor<FImage>

@Reference(type=Article,
           author="Nobuyuki Otsu",
           title="A Threshold Selection Method from Gray-Level Histograms",
           year="1979",
           journal="Systems, Man and Cybernetics, IEEE Transactions on",
           pages={"62","66"},
           number="1",
           volume="9",
           customData={"keywords","Displays;Gaussian distribution;Histograms;Least squares approximation;Marine vehicles;Q measurement;Radar tracking;Sea measurements;Surveillance;Target tracking","doi","10.1109/TSMC.1979.4310076","ISSN","0018-9472"})
public class OtsuThreshold
extends Object
implements ImageProcessor<FImage>

Otsu's adaptive thresholding algorithm.

Author:

Jonathon Hare (jsh2@ecs.soton.ac.uk)

See Also:

http://en.wikipedia.org/wiki/Otsu's_method

Constructor Summary

Constructors

Constructor and Description
OtsuThreshold() Default constructor
OtsuThreshold(int numBins) Construct with the given number of histogram bins

Method Summary

Modifier and Type	Method and Description
static float	calculateThreshold(FImage img, int numBins) Estimate the threshold for the given image.
static float	calculateThreshold(float[] data, int numBins) Estimate the threshold for the given data.
static FloatFloatPair	calculateThresholdAndVariance(float[] data, int numBins) Estimate the threshold and inter-class variance for the given data.
static FloatFloatPair	computeThresholdAndVarianceFromHistogram(int[] histData, int total) Estimate the threshold and inter-class variance for the given histogram.
static float	computeThresholdFromHistogram(int[] histData, int total) Estimate the threshold for the given histogram.
protected static int[]	makeHistogram(FImage fimg, int numBins)
protected static int[]	makeHistogram(float[] data, int numBins, float min, float max)
void	processImage(FImage image) Process an image.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

OtsuThreshold

public OtsuThreshold()

Default constructor

OtsuThreshold

public OtsuThreshold(int numBins)

Construct with the given number of histogram bins

Parameters:

numBins - the number of histogram bins

Method Detail

makeHistogram

protected static int[] makeHistogram(FImage fimg,
                                     int numBins)

makeHistogram

protected static int[] makeHistogram(float[] data,
                                     int numBins,
                                     float min,
                                     float max)

calculateThreshold

public static float calculateThreshold(FImage img,
                                       int numBins)

Estimate the threshold for the given image.

Parameters:

img - the image

numBins - the number of histogram bins

Returns:

the estimated threshold

calculateThreshold

public static float calculateThreshold(float[] data,
                                       int numBins)

Estimate the threshold for the given data.

Internally, the data will be min-max normalised before the histogram is built, and the specified number of bins will cover the entire max-min range. The returned threshold will have min added to it to return it to the original range.

Parameters:

data - the data

numBins - the number of histogram bins

Returns:

the estimated threshold

calculateThresholdAndVariance

public static FloatFloatPair calculateThresholdAndVariance(float[] data,
                                                           int numBins)

Estimate the threshold and inter-class variance for the given data.

Internally, the data will be min-max normalised before the histogram is built, and the specified number of bins will cover the entire max-min range. The returned threshold will have min added to it to return it to the original range.

Parameters:

data - the data

numBins - the number of histogram bins

Returns:

the estimated threshold and variance

computeThresholdFromHistogram

public static float computeThresholdFromHistogram(int[] histData,
                                                  int total)

Estimate the threshold for the given histogram.

Parameters:

histData - the histogram

total - the total number of items in the histogram

Returns:

the estimated threshold

computeThresholdAndVarianceFromHistogram

public static FloatFloatPair computeThresholdAndVarianceFromHistogram(int[] histData,
                                                                      int total)

Estimate the threshold and inter-class variance for the given histogram.

Parameters:

histData - the histogram

total - the total number of items in the histogram

Returns:

the estimated threshold and variance

processImage

public void processImage(FImage image)

Description copied from interface: ImageProcessor

Process an image. Implementing classes must alter the image passed in-place or assign the output to the input using Image.internalAssign(Image).

Specified by:

processImage in interface ImageProcessor<FImage>

Parameters:

image - The image to process in place.