Thresholding wavelets for image compression

Abstract

The paper addresses the problem of thresholding Wavelet coefficients in a transform-based algorithm for still image compression. Processing data before the quantization phase is a crucial step in a compression algorithm, especially in applications which require high compression ratios. In the paper, after a review on the applications of Wavelets to image compression, a new solution to the problem of an accurate choice of thresholds is presented.It is based on the concept of local contrast and exploits the localization properties of Wavelets and a maximization of the entropy to find the optimal threshold for the Wavelet coefficients. The results are compared with standard thresholding techniques which do not include considerations about local distribution of pixel information within the image. At the end, examples of compression are given, where the algorithm includes the complete processing of transform coefficients (thresholding, quantization and coding).

Wavelet transform image coding based on fuzzy visual perception modeling

“…Therefore, one introduces the discretization parameters as a = b = nab0, with i, j E Z, and a0 = 2, b0 = 1 fixed. The wavelet decomposition is then f = ...V2c:V1c:V0c:V1c:V2 (5) each with resolution 2' . For each i, the Ni,, spans a space W, which is exactly the orthogonal complement in of , therefore ri1=fryw; (6) The coefficients (w,1j) describe the information lost when going from an approximation offwith resolution 2'' to the coarser approximation with resolution 2' .…”

“…It motivates us to develop an image compression scheme based on HVS. Some approaches in this nature can be found in [4] [5][6] [12].…”

A pattern tracking algorithm for lossless data compression

“…While lossy encoding of digital data (Sayood, 2000) is well handled by a variety of coding methods (Hankerson et al, 2003;Solomon, 2006) such as wavelet encoding (En-hui et al, 1997;Albanesi, 1997;Brechet et al, 2007;Zaki et al, 2001;Usevitch, 2001;Evangelista and Cavaliere, 1998;Chapa and Rao, 2000;Goswami and Chan, 1999;Kitanovski et al, 2008;Hosny et al, 1999;Fgee et al, 1999), it leads to errors in the decoded data that may be unacceptable for a given application. In applications where the collection of digital data is difficult, costly, or subject to federal law, unacceptable loss of information from lossy encoding methods may lead to exclusive use of lossless encoding (Solomon, 2007;Nunez and Jones, 2003).…”