With the growth of multimedia and internet, compression techniques have become the thrust area in the fields of computers. Multimedia combines many data types like text, graphics, still images, animation, audio and video. Image compression is a process of efficiently coding digital image to reduce the number of bits required in representing image. Its purpose is to reduce the storage space and transmission cost while maintaining good quality. Many different image compression techniques currently exist for the compression of different types of images. In the present research work back propagation neural network training algorithm has been used. The neural network model has been trained and tested for the different types of images. 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 report, edge information is extracted by comparing these blocks and input signal is also compressed into each 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, an accurate edge are evaluated and then a good image compression can be realized. Additionally, we introduce Genetic Algorithm to optimize the cluster structure.