Shaking snakes using color edge for contour extraction

We propose greedy-algorithm-based shaking snakes for estimating image contours. The proposed snake model shakes a search area over which an energy function is to be minimized. Thus, it can work effectively even though an initial contour is not close enough to a target object. We also use color edges as an image energy term which enables snakes to avoid undesirable local minima when the contour spans a region where gray edges are weak or missing. Experimental results show that the suggested approach is very effective in estimating image contours accurately.