Class PCTSignatures

Namespace: Emgu.CV.XFeatures2D

Assembly: Emgu.CV.dll

Class implementing PCT (position-color-texture) signature extraction as described in: Martin Krulis, Jakub Lokoc, and Tomas Skopal. Efficient extraction of clustering-based feature signatures using GPU architectures. Multimedia Tools Appl., 75(13):8071–8103, 2016. The algorithm is divided to a feature sampler and a clusterizer. Feature sampler produces samples at given set of coordinates. Clusterizer then produces clusters of these samples using k-means algorithm. Resulting set of clusters is the signature of the input image. A signature is an array of SIGNATURE_DIMENSION-dimensional points.Used dimensions are: weight, x, y position; lab color, contrast, entropy.

public class PCTSignatures : SharedPtrObject, IDisposable

Inheritance: object

DisposableObject

UnmanagedObject

SharedPtrObject

PCTSignatures

Implements: IDisposable

Inherited Members: SharedPtrObject._sharedPtr

SharedPtrObject.SharedPtr

UnmanagedObject._ptr

UnmanagedObject.Ptr

DisposableObject.Dispose()

DisposableObject.ReleaseManagedResources()

object.GetType()

object.MemberwiseClone()

object.ToString()

object.Equals(object)

object.Equals(object, object)

object.ReferenceEquals(object, object)

object.GetHashCode()

Constructors

PCTSignatures(VectorOfPointF, VectorOfInt)

Creates PCTSignatures algorithm using pre-generated sampling points and clusterization seeds indexes.

public PCTSignatures(VectorOfPointF initSamplingPoints, VectorOfInt initClusterSeedIndexes)

Parameters

initSamplingPoints VectorOfPointF: Sampling points used in image sampling.
initClusterSeedIndexes VectorOfInt: Indexes of initial clusterization seeds. Its size must be lower or equal to initSamplingPoints.size().

PCTSignatures(VectorOfPointF, int)

Creates PCTSignatures algorithm using pre-generated sampling points and number of clusterization seeds. It uses the provided sampling points and generates its own clusterization seed indexes.

public PCTSignatures(VectorOfPointF initSamplingPoints, int initSeedCount)

Parameters

initSamplingPoints VectorOfPointF: Sampling points used in image sampling.
initSeedCount int: Number of initial clusterization seeds. Must be lower or equal to initSamplingPoints.size().

PCTSignatures(int, int, PointDistributionType)

Creates PCTSignatures algorithm using sample and seed count. It generates its own sets of sampling points and clusterization seed indexes.

public PCTSignatures(int initSampleCount = 2000, int initSeedCount = 400, PCTSignatures.PointDistributionType pointDistribution = PointDistributionType.Uniform)

Parameters

initSampleCount int: Number of points used for image sampling.
initSeedCount int: Number of initial clusterization seeds. Must be lower or equal to initSampleCount
pointDistribution PCTSignatures.PointDistributionType: Distribution of generated points.

Properties

ClusterMinSize

This parameter multiplied by the index of iteration gives lower limit for cluster size. Clusters containing fewer points than specified by the limit have their centroid dismissed and points are reassigned.

public int ClusterMinSize { get; set; }

Property Value

int

DistanceFunction

Distance function selector used for measuring distance between two points in k-means.

public PCTSignatures.PointDistributionType DistanceFunction { get; set; }

Property Value

PCTSignatures.PointDistributionType

DropThreshold

Remove centroids in k-means whose weight is lesser or equal to given threshold.

public float DropThreshold { get; set; }

Property Value

float

GrayscaleBits

Color resolution of the greyscale bitmap represented in allocated bits (i.e., value 4 means that 16 shades of grey are used). The greyscale bitmap is used for computing contrast and entropy values.

public int GrayscaleBits { get; set; }

Property Value

int

IterationCount

Number of iterations of the k-means clustering. We use fixed number of iterations, since the modified clustering is pruning clusters (not iteratively refining k clusters).

public int IterationCount { get; set; }

Property Value

int

JoiningDistance

Threshold euclidean distance between two centroids. If two cluster centers are closer than this distance, one of the centroid is dismissed and points are reassigned.

public float JoiningDistance { get; set; }

Property Value

float

MaxClustersCount

Maximal number of generated clusters. If the number is exceeded, the clusters are sorted by their weights and the smallest clusters are cropped.

public int MaxClustersCount { get; set; }