嵌入式图像压缩编码的研究  

Research on the Embedded Image Compression Coding

作　　者：常淑娟[1] 和煦[1] 

机构地区：[1]西安邮电学院,陕西西安710121

出　　处：《现代电子技术》2008年第18期157-159,162,共4页Modern Electronics Technique

摘　　要：嵌入式零树小波编码(EZW)是基于小波变换的图像压缩编码方法,具有良好的局部特性和空间-频率特性,但正交变换用统一的方法分解高低频,没有充分利用高频的细节信息,而且用同样的方法扫描高频3个方向(水平、竖直、对角线)分量,不能完全利用小波变换后系数的特点。针对此,提出一种改进的EZW算法,即对原始图像采用固定格式的小波包分解,并给出一种新的小波零树结构;在对分解后的系数进行扫描时,充分利用高频信息的方向性特点,其水平分量采用水平扫描、竖直分量采用竖直扫描、对角线采用Z扫描,整体结构依然使用原始EZW的扫描顺序。通过仿真实验对比发现,提出的改进EZW算法比原始的EZW算法,无论在客观数据还是主观视觉上,都有一定的改善,从而验证了该改进算法的有效性。The Embedded Zerotree（EZW）is a image compression method based on the wavelet transform have a better partial and space- frequency characteristics, but it uses the same way to decompose the high and low frequency bands. It doesn＇t use the detailed information of high frequency and uses the same way to scan the three directions. So it can not use the characteristics of coefficients after the wavelet transform. For these,a new algorithm about EZW is raised in this thesis. The image data is decomposed with fixed format . The decomposed coefficient is scanned by using the old EZW sequence in the whole construction with utilizing the characteristics of direction and coefficients in the high frequency information. The horizontal component is scanned horizontally. The vertical component is scanned vertically. The diagonal component is scanned by Z scanning. The original and improved EZW algorithms are simulated and their performances are compared. The improvement is proved to be efficient through the comparison between the data and the vision.

关 键 词：图像压缩 小波变换 小波包 嵌入式零树小波编码(EZW) 

分 类 号：TN919.8[电子电信—通信与信息系统]