Gray Level Image Contrast Enhancement Using Hybrid BAT and Moth Flame Optimization

This study presents a novel hybrid method that optimizes contrast stretching parameters for image enhancement by combining the Bat algorithm (BA) and Moth Flame Optimization (MFO). The method described in this study leverages the exploratory capabilities of the BA and the exploitation strengths of MFO in order to achieve an optimal balance between exploration and exploitation. The BA employs echolocation-inspired movements and randomization factors to explore the search space, while the MFO exploits locally optimal solutions guided by light sources. By integrating BA and MFO, the algorithm achieves a balance between exploration and exploitation, leading to improved solution quality and faster convergence. The algorithm iteratively moves the bats and moths, applies contrast stretching using updated positions, and evaluates the fitness value. The best solutions are identified and stored throughout the iterations. The algorithm extracts the optimal contrast stretching parameters from the best solution and applies them to enhance the input image. The experimental results demonstrate the algorithm's effectiveness in improving image quality by 7.5 % and 24.2% with respect to BA and MFO. Thus the proposed hybrid algorithm offers a promising approach for image enhancement for various applications.