摘要
该文提出了一种基于双正交小波的矢量量化编码方法。该方法充分利用了不同尺度间小波系数的相关性并采用自组织特征映射神经网络进行矢量量化。实验表明,该方法获得较高的编码效率和重构图象质量。
In this paper, a vector quantization algorithm based on biorthogonal wavelet transform is put forward. The corelation of the wavelet coefficients amony different scales is fully utilized and the Self-Organizing feature map neural network is used. The results of expriment show that high coding efficiency and reconstructed image quality are both obtained.
出处
《华东师范大学学报（自然科学版）》
CAS
CSCD
北大核心
1999年第4期38-41,共4页
Journal of East China Normal University(Natural Science)
基金
华大集团立项项目
关键词
小波变换
矢量量化
编码
图象压缩
神经网络
wavelet transform vector quantization seif-organizing feature map neural network
