Image retrieval via balance-evolution artificial bee colony algorithm and lateral inhibition

Image retrieval is a fundamental issue in pattern recognition. In this work, lateral inhibition (LI) model is adopted as a pre-processing step, which widens the gray level gradients so as to facilitate the image retrieval scheme. In searching for a perfect match between a predefined template and a reference image, we adopt metaheuristic algorithms for good seach capability. Artificial bee colony (ABC) algorithm is a bio-inspired optimization technique, which imitates the foraging behavior of honey bee swarms. It is well known that the algorithm is good at exploration but poor at exploitation. We present balance-evolution artificial bee colony (BE-ABC) algorithm that aims to strike a balance between exploration and exploitation rather than just focusing on improving the latter. BE-ABC algorithm adaptively manipulates the search intensity at the exploration and exploitation stages during the iterations. Besides that, it incorporates an overall degradation procedure to prevent premature convergence. Simulation results confirm that BE-ABC algorithm is more capable than several state-of-the-art metaheuristic algorithms in this image retrieval scheme.