Application of Chaos Genetic Algorithm in Automatic Video Object Segmentation

We obtain the optimum filter scale and coefficients of wavelet filter by employing the chaos genetic algorithm, then, apply the chaos genetic algorithm to automatic selection of threshold value in the wavelet edge detection. Our algorithm is adaptive to different images, and is able to obtain better continuity of edges. Finally, the obtained edges of video object are applied to contour correction of automatic video object segmentation, in the mean while; we propose an effective automatic video object segmentation algorithm by integrating background constructing and registration technique. Experimental results are compared with the results of other algorithm, and demonstrate the performance of our algorithm.