An Image Compressing Algorithm Based on Classified Blocks with BP Neural Networks

This paper expounds the principle of BP neural network with applications to image compression and the neural network models. Then an image compressing algorithm based on improved BP network is developed. The blocks of original image are classified into three classes: background blocks, object blocks and edge blocks, considering the features of intensity change and visual discrimination. The BP algorithm is also improved for a better convergence effect and the simulation results indicate that the compression rate and the quality of reconstructed image is effectively improved.