Automatic Gray Image Contrast Enhancement using Particle Swarm and Cuckoo Search Optimization Algorithms

Abstract

In this paper, we report on the investigation of two different metaheuristic based algorithms for Gray Image (GI) enhancement. First, we investigated the Particle Swarm Optimization (PSO) algorithm under certain parameter settings for the GI enhancement task and followed with the Cuckoo Search (CS) algorithm for the same task. Then, we proposed an algorithmic procedure for computing a new set of objective measures for quantifying the performance of any image enhancement algorithm. Comparative analyses were conducted alongside classical approaches such as the Linear Contrast Stretching (LCS) and the Histogram Equalization (HS) techniques. Our findings revealed that the CS and the PSO algorithms provide better performance than the popularly used LCS and HE techniques. However, between the PSO and the CS algorithm, the CS performed better on more images than the PSO. These results obtained using the proposed metrics were seen to be clearly consistent with the enhanced images and thus, we concluded that autonomous GI enhancement methods based on metaheuristic optimization algorithms produce efficient results, and can effectively replace our dependence on subjective human judgment.