A Regularization Blind Image Restoration Technique by Using Particle Swarm Optimization
Xuanhua Lei, Qingping Hu, Xiaojian Kong, Xiong Tianlin · Advances in intelligent systems research/Advances in Intelligent Systems Research · 2013
Image degradation in laser underwater imaging system is due to the scattering of water.Image restoration is an effective method to improve the quality of image, but its solving process is an ill-posed problem and the solution is not easily obtained in actual applications.A regularization blind image restoration method using particle swarm optimization was proposed in this paper.Regularization technique was adopted to solve ill-posed problem in the process of blind image restoration, the selection of regularization parameter still remains a difficult problem due to the amplification of noise in the inversion process.So two kind of particle swarm optimization were used to estimate regularization parameter and point spread function alternately.The results of image simulation and experiment show that the algorithm has a good effect of restoration for underwater image.