一种基于双正交重叠变换的嵌入式编码算法研究  

Study on Embedded Coding Compression Algorithm Based on Lapped Biorthogonal Transform

作　　者：黄臣[1] 田昕[1] 李涛[1] 田金文[1] 

机构地区：[1]华中科技大学图像识别与人工智能研究所,武汉430074

出　　处：《计算机与数字工程》2012年第3期1-3,共3页Computer & Digital Engineering

基　　金：国家自然科学基金项目(编号:61102064);中国博士后科学基金项目(编号:20100480907)资助

摘　　要：双正交变换为基于块的低复杂度变换,而且与传统的离散余弦变换相比,一定程度上减小了变换后图像的块效应,因而被采纳入联合图像专家组织JPEG(Joint Photographic Expert Group)最新制定的静态图像编码标准JPEG XR中。为了能够改善其无法实现码流长度控制的缺陷,文章深入研究了JPEG XR的编码技术,提出了一种针对固定压缩比的编码算法。主要思路是通过对双正交变换后的系数进行嵌入式位平面编码,取代了原先的量化步骤,使得压缩码流长度可以精确控制。Low-complexity block-based Lapped Biorthogonal Transform which can effectively reduce blocking effect is applied in Joint Photographic Expert Group＇s newest standard for static image coding,whose most admirable advantage is the convenience of being implemented in hardware and its low complexity in both memory-occupying and time-consuming.To avoid its weakness in the disability of compression rate control,a resolution was given,after deeply researching into this new algorithm,the Bit Plate Encoding was used to substitute the original quantization process to achieve accurate rate-controlling.

关 键 词：双正交重叠变换 位平面编码 定比压缩 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]