IMAGE ENHANCEMENT USING IMPROVIESED PARTICLE SWARM OPTIMIZATION

Abstract

Due to non-ideal image acquisition process, for example poor illumination, coarse quantization etc the visual quality of image is compromised. This needs to be addressed by the process of image enhancement which includes processing the image to bring out specific details of the image. The image is processed so that the resultant image is more suitable than the original for a particular application. Image enhancement on spatial domain will be carried out. An optimal simplified approach for image enhancement of color images using adaptive contrast enhancement and improvised Particle Swarm Optimisation (PSO) is introduced. Particle swarm optimization (PSO) is a population based stochastic optimization technique developed by Dr. Eberhart and Dr. Kennedy in 1995, inspired by social behavior of bird flocking or fish schooling. PSO shares many similarities with evolutionary computation techniques such as Genetic Algorithms (GA). PSO is initialized with a group of random particles (solutions) and then searches for optima by updating generations. In every iteration, each particle is updated by following two "best" values. The first one is the best solution (fitness) it has achieved so far. This value is called pbest. Another "best" value that is tracked by the particle swarm optimizer is the best value, obtained so far by any particle in the population. This best value is a global best and called gbest. The equation for the updates of velocity and position of particles in PSO is modified. For that, the values of two variables, iteration IT and α are evaluated through a newly developed Fuzzy Inference System. In PSO, each iteration updated the velocity of the particle, the velocity is dependent on the acceleration of the particle, which in turn is dependent on force applied, this force is optimized using Newton’s law of gravity and motion. This makes the convergence of the PSO to yield better result as compared to the classical PSO, when applied for the enhancement of the images When a particle takes part of the population as its topological neighbors, the best value is a local best and is called lbest. The particles in the algorithm share the information with each other to find the local best and also to find the global best in the group. . A new objective function will be introduced and optimized using PSO to learn the parameters used for the enhancement of a given image. The proposed approach is evaluated using different test images. Different performance measures are used for the quantitative analysis of the proposed approach.