Class AlgorithmGraphBasedSegmentation

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

    public class AlgorithmGraphBasedSegmentation
    extends AlgorithmBase
    • Field Detail

      • sigma

        private float sigma
        The C++ source code for the port was downloaded from Pedro F. Felzenswalb's web page Graph Based Image Segmentation at http://cs.brown.edu/~pff/segment/ This code is ported with the permission of Pedro F. Felzenszwalb Reference: Pedro F. Felzenszwalb and Daniel P. Huttenlocher, International Journal of Computer Vision, 59(2), September, 2004. Port performed by William Gandler. This program takes a color image and produces a segmentation with a random color assigned to each region Typical parameters are: sigma = 0.5, k = 500, minSize = 20. Larger values for k result in larger components in the result.
      • k

        private float k
      • minSize

        private int minSize
      • xDim

        private int xDim
    • Constructor Detail

      • AlgorithmGraphBasedSegmentation

        public AlgorithmGraphBasedSegmentation​(ModelImage destImg,
                                               ModelImage srcImg,
                                               float sigma,
                                               float k,
                                               int minSize)
        Constructs graph based segmentation algorithm.
        Parameters:
        destImg - Image model where result image is to stored
        srcImg - Source image model
        sigma - Used to smooth the input image before segmenting it
        k - Value for the threshold function
        minSize - Minimum component size enforced by post-processing