An Automated Threshold Selection using Wavelet Based PSO for Image Compression

Image Compression addresses the problem of reducing the amount of data required to represent the digital image. Compression is achieved by the removal of one or more of three basic data redundancies known as coding redundancy, Inter pixel redundancy and psycho visual redundancy. Recent research in transformbased image compression has focused on the wavelet transform due to its superior performance over other transforms. In the recent survey, image is subjected to wavelet decomposition to obtain wavelet coefficients and then applied Hard or Soft thresholds for neglecting certain wavelet coefficients by manually selecting global and local threshold values. Here, the manual threshold selection becomes very difficult because it depends on the type of image and its statistical properties like mean and standard deviation. In this paper we proposed an automated threshold selection scheme using wavelet based Particle Swarm Optimization which maintains trade of between peak signal to noise ratio (PSNR) and compression ratio (CR). The above work is implemented using MATLAB 2009.