An image compression algorithm based on random neural network

Neural network is a secant subject relating a lot of technologies. Neural network coding is also a new technique. In this paper, we presented an image compression algorithm based on random neural network model. First, the theory of random neural network is analyzed. Second, random neural network model is applied to image compression. The network consists of an input layer and an output layer of equal sizes, with an intermediate layer of smaller size in between. At the end, the performance of the random neural network compression/decompression algorithm is compared with image compression algorithm based on BP neural network model. The experiments results show that the random neural network model is successful in compressing and decompressing image. The obtained visual and PNSR quality is acceptable.