Vector Quantization Based on Self-Adaptive Particle Swarm Optimization

This article presents a fuzzy self-adaptive particle swarm optimization (FSAPSO) learning algorithm to extract a near optimum codebook of vector quantization (VQ) for carrying on image compression. The fuzzy self-adaptive particle swarm optimization vector quantization (FSAPSOVQ) learning schemes, combined advantages of the fuzzy inference method (FIM), the simple VQ concept and the efficient selfadaptive particle swarm optimization (SAPSO), are considered at the same time to automatically create near optimum codebook to achieve the application of image compression. The proposed scheme uses the selfadaptive strategy that offers better efficiency in terms of convergence speed and also preventing the global best particle from getting stuck in local optima as in the particle swarm optimization. SAPSO algorithm is having two states (exploration and exploitation states) for each particle and a metric to measure a particle’s activity is defined which is used to choose which state it would reside. In order to balance a particle’s exploration and exploitation capability for different evolving phase, a self-adjusted inertia weight which varies dynamically with each particle’s evolution degree and the current swarm evolution degree is introduced into SAPSO learning algorithm. This FSAPSOVQ strategy is then compared with FPSOVQ and LindeBuzoGray (LBG) algorithms to show its efficiency for different standard test images. Peak-signal-to-noise ratio (PSNR) is taking as a parameter to show the efficiency of above mentioned VQ.