适于图像压缩的二维8×8DCT查表快速算法研究  

A Fast 2D 8×8 DCT Algorithm Based on Look-Up Table for Image Compression

作　　者：纪秀花[1,2] 张彩明[1,2] 刘慧[1] 

机构地区：[1]山东经济学院计算机科学与技术学院,济南250014 [2]山东大学计算机科学与技术学院,济南250101

出　　处：《计算机研究与发展》2009年第4期618-628,共11页Journal of Computer Research and Development

基　　金：国家自然科学基金项目(60573114,60673003);国家“九七三”重点基础研究发展计划基金项目(2006CB303102);山东省教育厅科技基金项目(J07YJ10)~~

摘　　要：基于基本图像的概念及其对称性,提出一种计算二维8×8离散余弦变换(DCT)量化后系数的查表快速算法.新算法在消除乘法运算的同时也减少了加法运算量.通过设计查找表结构和组织数据,使得每次访问存储器得到的不是一个乘积数据而是一组乘积数据,有效地减少了查表次数;通过研究基本图像的对称性及DCT计算过程中数据的范围情况,减小了查找表(LUT)的长度.整个计算过程具有很强的并行性.在图像变换编码时,利用新算法可只计算需要被编码和传输的低频变换系数,以大大减少运算量.Discrete cosine transform （DCT） has been adopted as an essential part of the well-known image/video compression standards. It is a key factor that DCT can be implemented as fast as possible because of its large number of arithmetic operations in the real-time image transmission. A direct 8 × 8 2D DCT fast algorithm using look-up table （LUT） is introduced in this paper. The new algorithm is based on the conception and symmetry of basic images. With the new algorithm, the number of addition operations for the transform is reduced while multiplying operations for the transform are eliminated. By designing skillfully the structure of look-up table, one can get a group of product data per memory access, so that the number of looking up the table is reduced greatly. By using the symmetry of basic images and studying the ranges of data in computing the transform, the size of look-up table is decreased. As the new algorithm is executed without involving any multiplication, it is attractive in digital image applications for portable devices, where silicon area and power consumption are dominant issues in hardware design. Moreover, the new algorithm can be parallelized easily. In low bit-rate image compression, only the low-frequency DCT coefficients are computed, which will be encoded by adopting the new algorithm so as to reduce the arithmetic operations greatly.

关 键 词：DCT 基本图像 量化 查找表 图像压缩 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]