Rough-Fuzzy Granulation, Rough Entropy and Image Segmentation

Summary form only given. This talk has two parts explaining the significance of rough sets in granular computing in terms of rough set rules and in uncertainty handling in terms of lower and upper approximations. The first part describes how the concept of rough-fuzzy granulation can be used for the problem of case generation, with varying reduced number of features, in a case based reasoning framework, and their application to multi-spectral image segmentation. Here the synergistic integration of EM algorithm, minimal spanning tree and rough set theoretic knowledge encoding via information granules provides efficient segmentation (in terms of computation time, uncertainty handling and quantitative index). The second part deals with devising a new definition of image entropy in a rough set theoretic framework, and its application to the problem of object extraction from images by minimizing both object and background roughness. Granules carry local information and reflect the inherent spatial relation of the image by treating pixels of a window as indiscernible or homogeneous. Maximization of homogeneity in both object and background regions during their partitioning is achieved through maximization of rough entropy; thereby providing optimum results for object background classification. The effect of granule size is also discussed