Self-organized edge detection for an image compression

This paper proposes the new method of image compression. We have already developed self-organized image compression. Several nodes are yielded and self-organized according to a gray scale level of pixels. In this work, edge information is extracted by comparing these blocks and the input signal is also compressed into each of the nodes by the using similar self-organized clustering (SOC). The method of edge detection is not realized by the change of the pixel but by the difference of properties which have each cluster area. Only by using a quite simple algorithm, accurate edges are evaluated and then a good image compression can be realized. Additionally, we introduce a Genetic Algorithm (GA) to optimize the cluster structure. Also evaluation of the validity is discussed