Application of improved mayfly algorithm in image enhancement
Yuehua Dong, Luomin Wang, Donglin Zhu · 2nd International Conference on Laser, Optics and Optoelectronic Technology (LOPET 2022) · 2022
Aiming at the problems of fuzzy boundary and color deviation in marine biological images, using the advantages of fast convergence speed and strong optimization performance of mayfly optimization algorithm, an improved mayfly algorithm (RCMA) based on reverse opposition-based learning is proposed in this paper. Firstly, the optimized initial mayfly population is obtained by reverse opposition-based learning to enhance the diversity of mayfly population and improve the convergence speed of the algorithm; Then the linear decreasing weight method is used to update the position of male and female mayflies, which reduces the risk of premature mayfly algorithm and avoids the oscillation phenomenon near the global optimal solution in the later stage of the algorithm; Finally, the double gamma function is introduced, and the improved mayfly algorithm is used to find the optimal gamma value, which is used to improve the contrast of the image and enhance the image. Simulation results show that the RCMA proposed in this paper has a certain enhancement effect.