Package | Description |
---|---|
org.openimaj.image.feature.local.aggregate |
Implementations of techniques that aggregate the local descriptors
of an image into a single (typically fixed length) vector
representation.
|
org.openimaj.ml.clustering | |
org.openimaj.ml.clustering.assignment.hard | |
org.openimaj.ml.clustering.assignment.soft | |
org.openimaj.ml.clustering.dbscan | |
org.openimaj.ml.clustering.kdtree | |
org.openimaj.ml.clustering.kmeans |
K-Means in OpenIMAJ is designed to be both extremely fast and flexible.
|
org.openimaj.ml.clustering.rac | |
org.openimaj.ml.clustering.rforest |
Modifier and Type | Method and Description |
---|---|
static <L extends Location,T> |
BagOfVisualWords.computeQuantisedFeatures(HardAssigner<T,?,?> assigner,
List<? extends LocalFeature<L,? extends ArrayFeatureVector<T>>> features)
Utility method to construct a list of quantised local features (local
features with visual word assignments) from a list of features and a
HardAssigner . |
Constructor and Description |
---|
BagOfVisualWords(HardAssigner<T,?,?> assigner)
Construct with the given assigner.
|
VLAD(HardAssigner<T,?,?> assigner,
CentroidsProvider<T> centroids,
boolean normalise)
Construct with the given assigner and the centroids associated with the
assigner.
|
VLAD(HardAssigner<T,?,?> assigner,
T[] centroids,
boolean normalise)
Construct with the given assigner and the centroids associated with the
assigner.
|
Modifier and Type | Method and Description |
---|---|
HardAssigner<double[],double[],IntDoublePair> |
DoubleCentroidsResult.defaultHardAssigner() |
HardAssigner<T,float[],IntFloatPair> |
FeatureVectorCentroidsResult.defaultHardAssigner() |
HardAssigner<short[],float[],IntFloatPair> |
ShortCentroidsResult.defaultHardAssigner() |
HardAssigner<long[],double[],IntDoublePair> |
LongCentroidsResult.defaultHardAssigner() |
HardAssigner<float[],float[],IntFloatPair> |
FloatCentroidsResult.defaultHardAssigner() |
HardAssigner<int[],float[],IntFloatPair> |
IntCentroidsResult.defaultHardAssigner() |
HardAssigner<byte[],float[],IntFloatPair> |
ByteCentroidsResult.defaultHardAssigner() |
HardAssigner<DATATYPE,?,?> |
SpatialClusters.defaultHardAssigner()
Get the default hard assigner for this clusterer.
|
Modifier and Type | Class and Description |
---|---|
class |
ConstrainedFloatAssigner<DATATYPE>
An assigner that wraps another hard assigner and only produces valid
assignments if the closest cluster is within (or outside) of a given
threshold distance.
|
class |
ExactByteAssigner
A
HardAssigner that assigns points to the closest
cluster based on the distance to the centroid. |
class |
ExactDoubleAssigner
A
HardAssigner that assigns points to the closest
cluster based on the distance to the centroid. |
class |
ExactFeatureVectorAssigner<T extends FeatureVector>
A
HardAssigner that assigns points to the closest cluster based on
the distance to the centroid. |
class |
ExactFloatAssigner
A
HardAssigner that assigns points to the closest
cluster based on the distance to the centroid. |
class |
ExactIntAssigner
A
HardAssigner that assigns points to the closest
cluster based on the distance to the centroid. |
class |
ExactLongAssigner
A
HardAssigner that assigns points to the closest
cluster based on the distance to the centroid. |
class |
ExactShortAssigner
A
HardAssigner that assigns points to the closest
cluster based on the distance to the centroid. |
class |
HierarchicalByteHardAssigner
|
class |
HierarchicalDoubleHardAssigner
|
class |
HierarchicalFloatHardAssigner
|
class |
HierarchicalIntHardAssigner
|
class |
HierarchicalLongHardAssigner
|
class |
HierarchicalShortHardAssigner
|
class |
KDTreeByteEuclideanAssigner
A
HardAssigner that uses a ByteNearestNeighboursKDTree to
generate approximately correct cluster assignments. |
class |
KDTreeDoubleEuclideanAssigner
A
HardAssigner that uses a DoubleNearestNeighboursKDTree to
generate approximately correct cluster assignments. |
class |
KDTreeFloatEuclideanAssigner
A
HardAssigner that uses a FloatNearestNeighboursKDTree to
generate approximately correct cluster assignments. |
class |
KDTreeIntEuclideanAssigner
A
HardAssigner that uses a IntNearestNeighboursKDTree to
generate approximately correct cluster assignments. |
class |
KDTreeLongEuclideanAssigner
A
HardAssigner that uses a LongNearestNeighboursKDTree to
generate approximately correct cluster assignments. |
class |
KDTreeShortEuclideanAssigner
A
HardAssigner that uses a ShortNearestNeighboursKDTree to
generate approximately correct cluster assignments. |
Constructor and Description |
---|
ConstrainedFloatAssigner(HardAssigner<DATATYPE,float[],IntFloatPair> internalAssigner,
float threshold)
Construct the ConstrainedFloatAssigner with the given assigner and
threshold.
|
ConstrainedFloatAssigner(HardAssigner<DATATYPE,float[],IntFloatPair> internalAssigner,
float threshold,
boolean greater)
Construct the ConstrainedFloatAssigner with the given assigner and
threshold.
|
Modifier and Type | Field and Description |
---|---|
protected Map<CentroidsProvider<int[]>,HardAssigner<int[],float[],IntFloatPair>> |
HierarchicalIntPathAssigner.assigners |
protected Map<CentroidsProvider<float[]>,HardAssigner<float[],float[],IntFloatPair>> |
HierarchicalFloatPathAssigner.assigners |
protected Map<CentroidsProvider<byte[]>,HardAssigner<byte[],float[],IntFloatPair>> |
HierarchicalBytePathAssigner.assigners |
protected Map<CentroidsProvider<long[]>,HardAssigner<long[],double[],IntDoublePair>> |
HierarchicalLongPathAssigner.assigners |
protected Map<CentroidsProvider<double[]>,HardAssigner<double[],double[],IntDoublePair>> |
HierarchicalDoublePathAssigner.assigners |
protected Map<CentroidsProvider<short[]>,HardAssigner<short[],float[],IntFloatPair>> |
HierarchicalShortPathAssigner.assigners |
Modifier and Type | Method and Description |
---|---|
HardAssigner<double[],?,?> |
DoubleDBSCANClusters.defaultHardAssigner() |
Modifier and Type | Method and Description |
---|---|
HardAssigner<double[],?,?> |
KDTreeClusters.defaultHardAssigner() |
Modifier and Type | Method and Description |
---|---|
HardAssigner<float[],float[],IntFloatPair> |
FloatKMeans.Result.defaultHardAssigner() |
HardAssigner<short[],float[],IntFloatPair> |
ShortKMeans.Result.defaultHardAssigner() |
HardAssigner<int[],float[],IntFloatPair> |
IntKMeans.Result.defaultHardAssigner() |
HardAssigner<byte[],float[],IntFloatPair> |
ByteKMeans.Result.defaultHardAssigner() |
HardAssigner<double[],double[],IntDoublePair> |
SphericalKMeansResult.defaultHardAssigner() |
HardAssigner<long[],double[],IntDoublePair> |
LongKMeans.Result.defaultHardAssigner() |
HardAssigner<T,float[],IntFloatPair> |
FeatureVectorKMeans.Result.defaultHardAssigner() |
HardAssigner<double[],double[],IntDoublePair> |
DoubleKMeans.Result.defaultHardAssigner() |
Modifier and Type | Class and Description |
---|---|
class |
ClusterLimitedIntRAC
Similar to
IntRAC but explicitly specify the limit the number of
clusters. |
class |
IntRAC
An implementation of the RAC algorithm proposed by Ramanan and Niranjan.
|
Modifier and Type | Method and Description |
---|---|
HardAssigner<int[],?,?> |
IntRAC.defaultHardAssigner() |
Modifier and Type | Class and Description |
---|---|
class |
IntRandomForest
An implementation of the RandomForest clustering algorithm proposed by Jurie et al.
|
Modifier and Type | Method and Description |
---|---|
HardAssigner<int[],?,?> |
IntRandomForest.defaultHardAssigner() |