LAUSR

This work introduces an improved ant lion optimizer (ALO), called BIALO, for industrial images. BIALO employs three strategies to improve the performance of the original ALO. First, a novel inertial weight is used to modify the ALO to better balance exploration and exploitation during the process of searching the best solutions. Second, the local search part of the bat algorithm plays an important role in accelerating the algorithm convergence rate. Additionally, the ALO is integrated with invasive weed optimization algorithm to further improve the searching precision. The proposed BIALO is applied to industrial image enhancement, where it acts as an efficient tool that searches for the best parameters in a local/global enhancement transformation. To test the performance of BIALO, we compare it with other metaheuristic algorithms, such as the genetic algorithm, particle swarm optimization, flower pollination algorithm, grasshopper optimization algorithm and the original ALO, on some benchmark industrial images. The experimental results establish that BIALO is able to achieve better outcomes than those of the other algorithms.