摘要
该文介绍了BP神经网络用于图像压缩的原理和基本模型,提出了一种基于子块分类的改进BP神经网络图像压缩算法:将图像子块分成背景子块、目标子块和边缘子块,结合各类子块的灰度变化特征、边缘特征以及人眼的视觉分辨特点,对各类子块分别采用不同的隐含层节点数,从而保证重建图像有较好的边缘细节和主观质量。实验结果证明本算法在取得较大的压缩比的同时恢复图像能有较好的质量。
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 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 human visual system.The simulation results show that the compression rate and the quality of reconstructing image are effectively improved.
出处
《杭州电子科技大学学报（自然科学版）》
2009年第2期32-35,共4页
Journal of Hangzhou Dianzi University：Natural Sciences
关键词
神经网络
图像压缩
子块分类
视觉特征
neural network
image compression
blocks classifing
visual features
