Research on the Choice of Wavelet Basis for Image Compression Algorithms

Abstract

Existing wavelet basis is analyzed based on image features. Defects of traditional wavelet basis are identified and improved. We propose to perform wavelet transform on the image using the D9/7 lifting wavelet and then compress the image using the compression algorithm. Results of simulations on several images indicate that the proposed method is superior to the traditional wavelet compression algorithm in terms of PSNR, compression and decompression efficiency. Meanwhile, the visual quality of the image reconstructed by the proposed algorithm is better than that from the traditional method.