Adaptive Spectral Transform for KLT, Wavelet-Based Color Image Compression

P.Sanoop Kumar, A. Ashakiran

Abstract


Image compression is very important for efficient transmission and storage of images. But different regions of a color image generally exhibit different spectral characteristics. The energy compaction of implementing a single spectral transform to all parts is predominantly inefficient from a compression context. Thus, it is proposed that, before the resultant coefficients are coded by an efficient wavelet coefficient coding scheme such as “Color Set Partitioning in Hierarchical Trees” (CSPIHT), different subsets of wavelet coefficients of a color image be dealt with different spectral transforms. The spatial partitioning of the set of high frequency coefficients of the color planes into spatially oriented subsets, which can be further partitioned into smaller directionally oriented subsets represents a quadtree [1]. A compression system of asymmetric intricacy, that integrates the proposed adaptive Spectral transform with the CSPIHT coefficient coding scheme yields average coding gains over a compression system which integrates the single spectral transform is derived from the entire image with the CSPIHT coefficient coding scheme.

Keywords: Karhunen–Loeve transform, Adaptive coding, color, image coding, quad tree, wavelet transform.


Full Text:

PDF


DOI: https://doi.org/10.26483/ijarcs.v4i10.1870

Refbacks

  • There are currently no refbacks.




Copyright (c) 2016 International Journal of Advanced Research in Computer Science