Image compression analysis using multistage vector quantization based on discrete wavelet transform

Abstract

A fundamental goal of digital image compression is to reduce the bit rate for transmission or data storage while maintaining an acceptable fidelity or image quality. In this study a proposed coding (compression) scheme for grey scale image by combining discrete wavelet transform (DWT), multistage vector quantization (MSVQ) and Huffman coding is presented. These combinations are utilized to take the advantages provided by all of them to get high compression ratio with acceptable recovered image quality in term of Peak Signal to Noise Ratio (PSNR) instead of using each method separately. First, the discrete wavelet transform is performed on the original image using bi-orthogonal 9/7 filter (bior4.4) resulting in number of sub-bands according to the decomposition level that can be one, two or three in the proposed scheme. Huffman coding applied on the approximation sub-band, and on the indices of the last level detail sub-bands that are vector quantized by two stages using LBG algorithm which forms the basis of most vector quantizer designs, other detail sub-bands set to zero if the decomposition level is greater than one to increase the compression ratio.