基于小波变换的图像快速压缩算法  

Fast Image Compression Algorithm Based on Wavelet Transform

作　　者：张健[1,2] 张思杰[1] 汪振兴[1] 张滨[3] 刘青[4] 

机构地区：[1]重庆大学通信工程学院 [2]武警海南总队 [3]中国人民解放军92830部队 [4]重庆通信学院

出　　处：《电视技术》2011年第23期25-28,39,共5页Video Engineering

基　　金：国家自然科学基金项目(60971016)

摘　　要：结合目前广泛采用的嵌入式小波零树编码(EZW)和分层树集划分算法(SPIHT),提出了一种适用于图像小波变换高频压缩的提升算法。在经小波变换之后的矩阵中引入区间变化的概念,选取合适的数值取代区间中的数值,之后进行编码和传输。对于小波变换之后的图像在低频部分采用了DPCM算法,在高频部分采用了在EZW和SPIHT基础上改进的快速压缩算法,那么在编码时就可以用较短的时间保留原始图像的大部分能量,这对大幅图像的压缩和传输非常有利。虽然新算法与原先两种算法相比略微损失了部分保真度,但却在很大层度上降低了计算复杂度,缩短了编码时间。实验结果表明,此算法取得了较好的效果。In this paper, the widely used embedded wavelet zerotree coding （EZW） and set partitioning in hierarchical trees algorithm （SPIHT）, proposed a wavelet transform for image enhancement algorithm for high-frequency compression. The concept of interval changes is introducted in the matrix of wavelet transform, replaced with the approximate value of the coefficients of wavelet transform, and then encoding and transmission. After the wavelet transform for image ,it used the DPCM algorithm in low-frequency part, and used the proposed algorithm in the high frequency part , then compression can be used in a short period of time to keep most of the energy of the original image. Although this algorithm compared with the original lost two parts of fidelity, it reduced the complexity of the algorithm and the encoding time. It is very advantageous to compress a significant image and transmission. The results show that proposed Fast compression algorithm based on wavelet transform to obtain a more satisfactory result.

关 键 词：小波变换 图像压缩 分区 DPCM 高频 

分 类 号：TN919[电子电信—通信与信息系统]