Weighted centroid neural network for edge preserving image compression

Abstract

A new image compression algorithm based on an unsupervised competitive neural network to prevent the edge degradation is proposed. The proposed unsupervised competitive neural network, called weighted centroid neural network (WCNN), utilizes the characteristics of image blocks from edge areas. The mean/residual VQ (M/R VQ)) scheme is utilized in this proposed approach as the frame work of the proposed algorithm. A novel measure for calculating edge strength is devised by using the residue of an image block data from the M/R scheme. The edge strength of an image block data is then utilized as a tool to allocate the proper code vectors in the proposed WCNN. The WCNN successfully allocates more code vectors to the image block data from edge area while it allocates less code vectors to the image block data from shade or non-edge area when compared to conventional the neural network based VQ algorithm. As a result, a simple application of WCNN to image compression problem gives improved edge characteristics in reproduced images over conventional neural network based VQ algorithms.