In this research, a fast, adaptive and user friendly segmentation methodology is developed for highly speckled SAR images. The developed region based centroidal Voronoi tessellation (R-BCVT) algorithm is a kind of polygon-based clustering approach in which the algorithm attempts to (1) split the image domain into j numbers of centroidal Voronoi polygons (2) assign each polygon a label randomly, then (3) classify the image into k cluster iteratively to satisfy optimum segmentation, and finally a k-mean clustering method refine the detected boundaries of homogeneous regions. The advantages of the novel method arise from adaptively, simplicity and rapidity as well as low sensitivity of the model to speckle noise.
AUTHOR KEYWORDS: Centroidal Voronoi tessellation; Clustering; Gamma distribution; SAR; Segmentation INDEX KEYWORDS: Algorithms; Computational geometry; Geometry; Image segmentation; Iterative methods; Synthetic aperture radar, Based clustering; Centroidal Voronoi Tessellation; Clustering; Developed regions; Gamma distribution; Homogeneous regions; K-mean clustering methods; SAR, Clustering algorithms PUBLISHER: International Society for Photogrammetry and Remote Sensing
Damghan University strives to be one of the top and outstanding universities in terms of scientific developments both theoretically and practically. Damghan University will have a transformative impact on society through innovation in education, research and entrepreneurship.