基于提升小波变换的嵌入式零树编码算法的改进

IMPROVED EMBEDDED ZEROTREE WAVELET CODING ALGORITHM BASED ON LIFTING WAVELET TRANSFORM

针对EZW算法本身没有考虑各个子带的特点而采用统一编码等诸多问题,以提升小波变换和EZW算法为基础,结合硬件实现的可行性,提出了一种EZW改进算法.通过采用提升小波变换,有效地降低传统小波分析的运算量和复杂性.其次,结合小波变换后各个子带的特点,分别对低频子带采用DPCM无损压缩,对高频子带采用零树扫描+游程编码;最后对同一幅灰度图像压缩并重构.结果表明,此方法不仅有效提高了重构图像的峰值信噪比,而且有效降低了硬件实现的复杂度.

A improved EZW method is presented to the inherent problems of EZW based on the lifting wavelet transform and EZW algorithm;the feasibility of hardware being combined,the lifting wavelet transform can reduce the volume and complexity of the traditional wavelet analysis effectively; and the DPCM lossless compression is made toward the low-frequency sub-band, while zero-tree scanning and RLE are made to high-frequency sub-band; finally, the compression and reconstruction to the same gray-scale image is finished. This method is not only effective to improve the PSNR of the reconstructed image,but also the complexity of the hardware is reduced.