基于小波变换的矢量量化快速码字搜索算法  

Vector-Quantized Fast Codeword Search Algorithm Based on Wavelet Transform

作　　者：石敏[1] 谢胜利[1] 

机构地区：[1]华南理工大学电子与信息学院,广东广州510640

出　　处：《华南理工大学学报（自然科学版）》2005年第9期10-14,共5页Journal of South China University of Technology(Natural Science Edition)

基　　金：国家自然科学基金资助项目(60274006);广东省自然科学基金资助项目(020826);国家杰出青年自然科学基金资助项目(60325310);教育部跨世纪优秀人才资助项目

摘　　要：针对矢量量化过程中编码的复杂性,提出了一种基于小波变换的自适应快速码字搜索算法.该算法使用欧几里德距离的平方作为量化的失真测度,首先为输入矢量选择合理的初始匹配码字,然后利用多控制点的三角不等式和变换域中矢量的性质去排除不可能匹配的码字,最后通过搜索空间的逐次降低找到与输入矢量最匹配的码矢量.仿真结果表明:在需要很少预先计算量和额外存储量的条件下,文中算法的编码质量和全搜索算法相同,但是其计算量却极大地降低.An adaptive fast search algorithm for codewords is presented based on the wavelet transform, with the aim of overcoming the encoding complexity in the vector quantization （VQ） process. In the proposed algorithm, the squared Euclidean distance is used as the distortion measure of the quantization, and a rational initial matched codeword is chosen for the input vector. The triangle inequalities with multiple control vectors and the characteristics of the vectors in the transform domain are then utilized to reject non-matched codewords. The best-matched codeword is finally obtained by gradually reducing the search space. Simulated results show that, with little pre-calculation and memory cost, the proposed algorithm can significantly reduce the computational complexity of VQ encoding, and the quality of the encoded image approaches to that obtained by the full search algorithm.

关 键 词：小波变换 矢量量化 码字搜索 

分 类 号：TN919[电子电信—通信与信息系统]