An edge preserving requantization model for color image coding with orthogonal polynomials

In this paper, an edge preserving fast requantization algorithm is proposed for color image coding. In this work, a block classifier in the orthogonal polynomials based transform domain is proposed to classify the color image region as containing either smooth or edge. The smooth regions are clustered by finding the central tendency adjacent smooth regions separated by edge block. The reduced training vectors are obtained from both edge blocks and clustered smooth blocks for quantization process. The quantization codebook Q1 is then constructed from the reduced training vectors and so reduces the codebook training process. In this proposed work, the edge block training vectors and the quantization codebook Q1 are utilized to construct the requantization codebook Q2 so as to eliminate the edge degradation problem present in existing requantization techniques. The self-organizing feature map algorithm is employed in both quantization and requantization stage for codebook generation process. The computation time of color image encoding is further reduced in this proposed work by constructing a single codebook for all the R, G and B color components utilizing the inter-correlation property of the proposed transform. The experimental results demonstrate that the proposed work gives superior results compared with existing techniques.