A combined approach based on fuzzy classification and contextual region Growing to image segmentation - 2016 PROJECT TITLE : A combined approach based on fuzzy classification and contextual region Growing to image segmentation - 2016 ABSTRACT: We have a tendency to present during this paper an image segmentation approach that combines a fuzzy semantic region classification and a context primarily based region-growing. Input image is 1st over-segmented. Then, previous domain information is used to perform a fuzzy classification of these regions to produce a fuzzy semantic labeling. This permits the proposed approach to operate at high level rather than using low-level features and consequently to remedy to the problem of the semantic gap. Each oversegmented region is represented by a vector giving its corresponding membership degrees to the different thematic labels and the whole image is therefore represented by a Regions Partition Matrix. The segmentation is achieved on this matrix rather than the image pixels through 2 main phases: focusing and propagation. The focusing aims at choosing seeds regions from which information propagation will be performed. The propagation section allows to spread toward others regions and using fuzzy contextual info the needed knowledge ensuring the semantic segmentation. An application of the proposed approach on mammograms shows promising results. Did you like this research project? To get this research project Guidelines, Training and Code... Click Here facebook twitter google+ linkedin stumble pinterest Matrix Algebra Image Resolution Image Representation Image Segmentation Image Classification Fuzzy Set Theory A three-layered graph-based learning approach For remote sensing image retrieval - 2016 Cell segmentation in digital holographic images - 2016