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.
Qiu G, Terrell T J. Improved image compression using backpropagation networks . Workshop on Neural Network Applications and Tools . 1993. 73~81
Hong Guowei, Hall G, Terrell T. Prediction by back-propagation neural network for lossless image compression . The 3rd International Conference on Signal Processing . 1996. 1026~1030
Erickson D S, Thyagarajan K S. A neural network approach to image compression . IEEE International Symposium on Circuits and Systems . 1992. 2921~2924
Christophe Amerijckx, Michel Verleysen. Image compression by self-organized kohonen map[J].IEEE Trans on Neural Networks.1998, 9(3):503-507
Xu Ningshou, Scott P D. Improving generalization capabilities of associative memories via sharp-angles spline functions . Proceedings of the Fifth International Workshop on Spectral Technique . Beijing, 1994. 265~290
Xu Ningshou, Li Yundong. Associative memory based on newton' s forword interpolation with applications to structural control . The Second Chinese Conf on Intelligent Control and Intelligent Automation . Xian, 1997. 325~329
Hama H, Xing Chunfeng, Liu Zhongkan. New high-order AMS based on newton's forward interpolation[J]. IEICE Trans on FECCS, 1998, E81-A(12):2688~2693