Quick object extraction in fuzzy framework

Through this paper a computationally efficient approach to object extraction in fuzzy settings is presented. The proposed approach is a `potential alternative´ (in terms of computational complexity) to the two most popular and reliable image segmentation algorithms namely `Udupa and Samarasekera´s Fuzzy connectedness algorithm´ and the `level set algorithm´. The research motivation behind the current work is reducing the computational time of these algorithms as these techniques are available since long and have proven their versatility but due to their computational complexity, they are not suitable for real time applications. The computational complexity of the proposed method is as good as finding the similarity/dissimilarity measure (gradient used here for simplicity) of the image and then thresholding it finite number of times. This is extremely less as compared to the above two state-of-art methods. A heuristic justification to the equivalence among these three algorithms is then presented. We keep proving rigorous equivalence among these three methods as our future work.