A Modified Embedded Zero-Tree Wavelet Method for Medical Image Compression

The Embedded Zero-tree Wavelet (EZW) is a lossy compression method that allows for progressive transmission of a compressed image. By exploiting the natural zero-trees found in a wavelet decomposed image, the EZW algorithm is able to encode large portions of insignificant regions of an still image with a minimal number of bits. The upshot of this encoding is an algorithm that is able to achieve relatively high peak signal to noise ratios (PSNR) for high compression levels. The EZW algorithm is to encode large portions of insignificant regions of an image with a minimal number of bits. Vector Quantization (VQ) method can be performed as a post processing step to reduce the coded file size. Vector Quantization (VQ) method can be reduces redundancy of the image data in order to be able to store or transmit data in an efficient form. It is demonstrated by experimental results that the proposed method outperforms several well-known lossless image compression techniques for still images that contain 256 colors or less.