A Layer Segmentation Based Compression Algorithm
Abstract
In this paper, we proposed a layer segmentation based compression algorithm for gray images. Image textures and some high frequency noise are described in a high frequency layer while the coarse part of the image is included in the low frequency layer. A mixed dictionary and sparse coding is applied for high frequency layer coding and the low frequency layer is coded using the traditional wavelets based coding system. The results show that the proposed scheme achieves better rate-distortion performance compared with several competing compression system. Furthermore, in the sparse coding part, some edge-related atoms are added in the dictionary and a high sparseness factor is set for the edge blocks, making more accurate approximations for edges. We avoid further degradation of edges caused by compression.
Related Papers
- → Comparative analysis of image compression techniques(2002)27 cited
- → A survey on VLSI architecture and design for data compression(2022)2 cited
- → Survey on Fractal image compression(2020)1 cited
- → Usage analysis of SVD, DWT and JPEG compression methods for image compression(2021)1 cited
- → Empirical analysis of BWT-based lossless image compression(2010)