A comparative study of improved Embedded Zerotree Wavelet image coder for true and virtual images

摘要

The objective of this paper is to implement an improved Embedded Zerotree Wavelet (EZW) Image Coder for true and virtual images. EZW used here is specially designed for wavelet transform and effective image compression algorithm. It has property that the bits in the bit stream are generated in order of importance, yielding a fully embedded code. We have used here different Wavelet Filters such as Biorthogonal, Coiflets, Daubechies, Symlets and Reverse Biorthogonal Filters. We have applied above filters on two images one true Rice image (256×256) and one virtual Human Spine image (256×256). MATLAB program is written to achieve an image compression based on EZW algorithm. We have compared our result using various parameters such as Compression Ratio, Bits per Pixel, Mean Square Error, and Peak Signal to Noise Ratio. By using this algorithm, the highest PSNR values & Low MSE for a variety of images can be obtained.