Journal of Computer Science

Image Compression using Space Adaptive Lifting Scheme

Ramu Satyabama and Annadurai

DOI : 10.3844/jcssp.2011.1704.1710

Journal of Computer Science

Volume 7, Issue 11

Pages 1704-1710

Abstract

Problem statement: Digital images play an important role both in daily life applications as well as in areas of research and technology. Due to the increasing traffic caused by multimedia information and digitized form of representation of images; image compression has become a necessity. Approach: Wavelet transform has demonstrated excellent image compression performance. New algorithms based on Lifting style implementation of wavelet transforms have been presented in this study. Adaptively is introduced in lifting by choosing the prediction operator based on the local properties of the image. The prediction filters are chosen based on the edge detection and the relative local variance. In regions where the image is locally smooth, we use higher order predictors and near edges we reduce the order and thus the length of the predictor. Results: We have applied the adaptive prediction algorithms to test images. The original image is transformed using adaptive lifting based wavelet transform and it is compressed using Set Partitioning In Hierarchical Tree algorithm (SPIHT) and the performance is compared with the popular 9/7 wavelet transform. The performance metric Peak Signal to Noise Ratio (PSNR) for the reconstructed image is computed. Conclusion: The proposed adaptive algorithms give better performance than 9/7 wavelet, the most popular wavelet transforms. Lifting allows us to incorporate adaptivity and nonlinear operators into the transform. The proposed methods efficiently represent the edges and appear promising for image compression. The proposed adaptive methods reduce edge artifacts and ringing and give improved PSNR for edge dominated images.

Copyright

© 2011 Ramu Satyabama and Annadurai . This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.