一种基于分类矢量量化的图像压缩算法  

An Algorithm of Image Compression Based on Classified Vector Quantization

作　　者：陈旭生[1] 李柏樵[1] 

机构地区：[1]信阳师范学院计算机与信息技术学院,信阳464000

出　　处：《现代计算机（中旬刊）》2013年第9期29-31,共3页Modern Computer

基　　金：河南省基础与前沿技术研究计划项目(No.132300410421;No.132300410422);信阳师范学院青年基金项目

摘　　要：数字化的图像数据量非常大,为了减少表达一幅图像所需的数据量,将分类矢量量化的方法应用于图像压缩。矢量量化的关键技术是码书设计问题,采用分类矢量量化的方法对小波变换后的高频子带数据进行压缩。通过设计合理的矢量构造方法,利用改进的SOFM算法进行码书设计,经实验证明能提高码书设计的时间效率和数据的压缩比。The digital image has a large amount of data, in order to reduc, e the data of the expression in the image, applies the classified vector quantization in image compression. The key technique of vector quantization is how to design the codehook. The compression of the technique in this paper is using the classified vector quantization in high frequency sub-band data which is after wavelet transform. Through to design the method of reasonable vector construction and use the algorithm of SOFM to design codebook. Experimental results show that the method can improve the compression ratio of the image and the efficiency of the algorithm, reduce the time complexity of the algorithm at the same time.

关 键 词：图像压缩 矢量量化 码书设计 矢量分类 

分 类 号：TN919.81[电子电信—通信与信息系统]