基于能量和方差标准的图像压缩方法

Image compression based on the criterion of variance and energy

在对图像进行小波包分解的基础上实现图像压缩 .根据小波系数的分布特点严格推导得出 :可以用能量和方差作为衡量小波系数重要性的标准 ,并据此对系数矩阵块进行选择分组 ,自适应地进行量化 ,而且不同的量化方式可以共用码表 .对低频部分扰动足够小的区域取均值 ,结合提出的存储方法 ,在不引入误差的情况下减少了编码负担 。

Image was compressed efficiently based on the wavelet packets decomposition. It was concluded from strict deduction that energy and variance served as the criterion for judging the importance of the coefficients based on the character of the wavelet coefficients. The coefficients could be grouped according to the criterion, after that they should be quantified adaptively. The same code table was used for different methods of quantification. Some part of low frequency was substituted by the average when they had tiny difference. The compression ratio could be improved by certain storage when the quality was guaranteed.