Abstract: To study the traditional neural networks which were featured as slow convergence and poor generalized capacity in image compression, a novel method of image compression based on associative-memory-system neural network was proposed. Associative memory system was constructed by newton's forward interpolation polynomial, and was used to establish model for image data. First, image data were devided into many blocks. And then each block was utilized to train associative memory system and charecteristic data can be abstracted after training. Charecteristic data's number was less than original data block, most of charecteristic data were limited to a range near to zero. Finally, all the blocks' charecteristic data were ranged by special order and entropy encode was expoited to code these charecteristic data. Experiments show that the method is effective for image compression. Compared with previous neural networks used in image compression, this method is free of training in advance and converges more quickly.