Parameter Selection of Image Fog Removal Using Artificial Fish Swarm Algorithm

摘要

Although image defogging is widely used in many working systems, existing defogging methods have some limitations due to the lack of enough information to solve the equation of fog formation model. To overcome the limitations, a novel defogging parameter selection algorithm based on artificial fish swarm algorithm (AFSA) is proposed in this paper. Two representative defogging algorithms are used to test the effectiveness of the method. The proposed method first selects the two main parameters and then optimizes them using the AFS algorithm. An assessment index of image defogging effect is used as the food concentration of the AFSA. Thus, these parameters may be adap-tively and automatically adjusted for the defogging algorithms. A comparative study and qualitative evaluation demonstrate that better quality results are obtained by using the proposed method.