Class AlgorithmTamuraTexture

  • All Implemented Interfaces:
    java.awt.event.ActionListener, java.awt.event.WindowListener, java.lang.Runnable, java.util.EventListener

    public class AlgorithmTamuraTexture
    extends AlgorithmBase
    DOCUMENT ME!
    Version:
    0.1 July 6, 2012
    Author:
    William Gandler In the coarseness measurement a 32 wide pixel rim around the edge is excluded from the calculation. The contrast measurement uses all the pixels. The directionality measurement excludes a 1 wide pixel rim around the edge. All measurements are calculated for whole slice values and individual pixel values. Directionality uses the gradient filter for the whole slice result and the Sobel filter for the pixel result. References: 1.) "Textural Features Corresponding to Visual Perception" by Hideyuki Tamura, Shunji Mori, and Takashi Yamawaki, IEEE Transactions on Systems, Man, and Cybernetics, Vol. SMC-8, No. 6, June, 1978, pp. 460 - 473. 2.) "A Relevance Feedback Retrieval Method Based on Tamura Texture" by Ya-Li Qi, 2009 Second International Symposium on Knowledge Acquisition and Modeling, 2009, pp. 174-177.
    • Field Detail

      • coarsenessThreshold

        private double coarsenessThreshold
        coarsenessThreshold must be = coarsenessThreshold * Emax. If coarsenessThreshold = 1.0, select the largest k which gives Emax.
      • doCoarseness

        private boolean doCoarseness
      • doContrast

        private boolean doContrast
      • cSize

        private int cSize
      • doDirectionality

        private boolean doDirectionality
      • histogramBins

        private int histogramBins
      • histogramThreshold

        private double histogramThreshold
      • RGBOffset

        private int RGBOffset
    • Constructor Detail

      • AlgorithmTamuraTexture

        public AlgorithmTamuraTexture​(ModelImage[] destImage,
                                      ModelImage srcImg,
                                      boolean doCoarseness,
                                      double coarsenessThreshold,
                                      boolean doContrast,
                                      int cSize,
                                      boolean doDirectionality,
                                      int histogramBins,
                                      double histogramThreshold)
        Creates a new AlgorithmTamuraTexture object for black and white image.
        Parameters:
        destImage - array
        srcImg - source image model
        doCoarseness -
        coarsenessThreshold -
        doContrast -
        cSize -
        doDirectionality -
        histogramBins -
        histogramThreshold -
      • AlgorithmTamuraTexture

        public AlgorithmTamuraTexture​(ModelImage[] destImage,
                                      ModelImage srcImg,
                                      int RGBOffset,
                                      boolean doCoarseness,
                                      double coarsenessThreshold,
                                      boolean doContrast,
                                      int cSize,
                                      boolean doDirectionality,
                                      int histogramBins,
                                      double histogramThreshold)
        Creates a new AlgorithmTamuraTexture object for color image.
        Parameters:
        destImage - array
        srcImg - source image model
        RGBOffset - selects red, green, or blue channel
        doCoarseness -
        coarsenessThreshold -
        doContrast -
        cSize -
        doDirectionality -
        histogramBins -
        histogramThreshold -
    • Method Detail

      • finalize

        public void finalize()
        Prepares this class for destruction.
        Overrides:
        finalize in class AlgorithmBase
      • calculateSliceTamuraTexture

        private void calculateSliceTamuraTexture()