Fuzzy logic and graph based segmentation

In this paper, a mask-based automatic segmentation algorithm for color images using fuzzy color similarity was presented. Computational cost of conventional image segmentation algorithms is high and at the same time, they are user dependent. Although the computational cost of mask-based segmetation algorithm recently introduced is low, it needs two parameters to be determined: similarity threshold and normalization factor. With proposed algorithm, pixel color similarity was calculated by means of fuzzy rule and consequently, user dependency was reduced. experimental results obtained were compared with convetional approaches.