A NOVEL APPROACH FOR IMAGE COMPRESSION USING LIFTING TECHNIQUE AND TSVQ

Abstract

The objective of image compression is to reduce the redundant amount of data and to achieve low bit rate without any apparent loss of image quality. In this paper, the compression process is achieved by using wavelet transform with lifting technique for decomposition and tree-structured vector scheme for quantization. Huffman coding method is used for encoding stage. Wavelet technique provides the most promising tool for high-quality image compression. Lifting transform provides a flexible tool for the construction of sub-band decomposition and perfect reconstruction. TSVQ has its advantages over conventional vector quantization by minimizing the computational complexity. Huffman coding is used for efficient coding of images at lower bit rate with minimal loss of information. The performance of the proposed work has been assessed with parameters like bits per pixel (bpp), compression ratio (CR), peak signal to noise ratio (PSNR), codebook size (CS), and mean squared error (MSE). The experimental results show that the proposed work yields a higher compression with better quality reconstructed image than the other conventional compression methods.