An Improved Crayfish Optimization Algorithm and Its Application in Enhancing Low-light Image Quality

The Crayfish Optimization Algorithm (COA) is a metaheuristic optimization algorithm renowned for its rapid convergence and balanced exploration-exploitation trade-off. However, it frequently encounters issues of local optima entrapment when addressing certain problems. To overcome this limitation, we propose an enhanced version called the Improved Crayfish Optimization Algorithm (ICOA). In ICOA, a temperature regulation mechanism is introduced to modulate exploration and exploitation, with distinct temperature coefficients applied during the summer resort, competition, and foraging stages. Additionally, random mutation, dimensional mutation, and Cauchy mutation are incorporated into ICOA to maintain population diversity and enhance search capabilities. Experimental evaluations, including benchmark function tests and low-light image enhancement experiments, demonstrate that ICOA improves search accuracy by 8.97% and convergence speed by 32.52 %, exhibiting superior performance in low-light image enhancement applications.