基于小波系数特征结构分类的分形图像编码

Fractal and Zerotree Coding Based on the Characteristic Structure of Wavelet Coefficients

在对小波系数特征结构分析的基础上 ,针对小波系数的两大特点 ,分别利用分形和零树的方式进行小波系数编码。对于分形编码 ,针对小波高频系数无直流分量的特点 ,改变了传统误差距离的选取 ,通过加入误差校正矩阵 ,减少了误差累积现象。理论分析和实验结果表明 ,相对于一般的分形及零树编码方式 ,在图像效果方面和压缩比上 ,都有很大的提高。

Based on the characteristic structure of wavelet coefficients, combined with two characters, we use fractal and zerotree coding to code the image. When we use the fractal coding, we change the conventional MSE because there is no direct current in the wavelet coefficients and we use the error emendation matrix to revise wavelet coefficients. Theoretical analysis and experimental results presented in the paper show that there are a higher compressing rate and quality of the image than the commonly fractal and zerotree coding methods.