基于DCT子空间失真测度的快速矢量编码算法  

A FAST ENCODING ALGORITHM FOR VECTOR QUANTIZATION BASED ON DCT SUBSPACE DISTORTION MEASURE

作　　者：周汀[1] 章倩苓[1] 闵昊[1] 陈旭昀[1] 

机构地区：[1]复旦大学专用集成电路与系统国家重点实验室

出　　处：《计算机学报》1997年第5期421-426,共6页Chinese Journal of Computers

基　　金：国家自然科学基金

摘　　要：在本文中，我们介绍了一种基于离散余弦变换（ＤＣＴ）子空间失真测度的快速矢量编码算法．该算法利用ＤＣＴ子空间映射，将失真测度维数从１６降至４，从而使编码计算复杂度降为１／４，并且结合部分失真算法进一步减小了编码计算复杂度．同时本文提出的最小覆盖集搜索算法大大改善了子空间失真测度算法等非最优矢量编码算法的信噪比特性．测试结果表明，相对于采用欧氏测度的穷尽搜索编码算法，该算法运算时间减少８５—８８％，算术运算数目减少９０％以上，信噪比损失仅为０．０４ｄＢ．This paper presents a new vector quantization encoding algorithm based on DCT subspace distortion measure. By mapping to DCT subspace, the dimensionality of the coder distortion measure is reduced from 16 to 4 and the computational complexity is reduced to 1/4 as well. A further improvement can be obtained by combined with partial distortion algorithm. Furthermore a searching method based on the minimum covering set is proposed to improve the performance of nonoptimal encoding algorithms such as subspace distortion measure algorithm in SNR. The test results show that the reduction of computation of the proposed algorithm is about 85-88% in the arithmetic operations and 90% in the encoding time against full searching method with Euclidean distance distortion measure, while the lost in SNR is about 0. 04 dB.

关 键 词：图象编码 矢量量化 离散余弦变换 图象处理 

分 类 号：TN919.8[电子电信—通信与信息系统]