A regularized image restoration algorithm based on improved hybrid particle swarm optimization

This paper proposes a regularized image restoration algorithm based on the improved hybrid particle swarm optimization (IHPSO). The proposed algorithm not only overcomes the premature phenomenon of particle swarm, ensures the global convergence, and also improves the quality of image restoration through trade off between the fidelity of image and smoothness reasonably. The simulation results demonstrate the effectiveness of the proposed algorithm, and the evaluation results based on peak signal to noise ratio (PSNR) of image show that the algorithm is better than traditional approaches.