基于对数熵最优小波包基树的图像编码压缩研究  

A Method of Wavelet Packet Tree Image Coding Based on logarithmic algorithm entropy standardization

作　　者：魏玉芬[1] 朱焕[1] 

机构地区：[1]黑龙江八一农垦大学文理学院,大庆163319

出　　处：《黑龙江八一农垦大学学报》2012年第3期68-70,79,共4页journal of heilongjiang bayi agricultural university

基　　金：黑龙江省高等教育学会"十二五"教育科学研究规划课题(HGJXHC 110223)

摘　　要：图像的能量主要集中在高频部分,传统的小波变换图像编码压缩方法主要侧重低频信号,而把高频部分看为不重要的信息,这就导致图像的细节失真。考虑到图像能量分布情况,提出以对数熵为代价函数,选择最优小波包树的图像编码压缩方法,仿真结果表明这种方法不仅可以提高的压缩比,而且重构的图像效果比较好。Traditional wavelet transform image coding compression method emphasized the low frequency signal and ignored the high ,in which was the energy of image mainly concentrated. It could lead to distortion of the image. Considering the energy distribution condition of the image, this paper proposed a new image coding compression method which based on logarithmic entropy for cost function to choose the optimum wavelet packet tree. The simulation results showed this method not only improved the compression ratio, but also promoted the effects of the reconstruct image.

关 键 词：小波包 图像编码 代价函数 对数熵 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]