Optimal Multi-level Image Segmentation using Bounded Heuristic Search Technique

Image thresholding is widely considered to obtain binary image from the gray level image. In this article, histogram based multi-level thresholding approach is proposed using Brownian Distribution (BD) based Bat Algorithm (BA). The optimal thresholds for the gray scale images are attained by maximizing Otsu’s between class variance function. The performance of the proposed algorithm is demonstrated by considering six benchmark (512 x 512) images and compared with the existing algorithms such as improved Particle Swarm Optimization (PSO), enhanced Bacterial Foraging Optimization (BFO) and Levy flight Bat Algorithm (LBA). The performance assessment between algorithms is carried using the parameters such as objective function, Peak Signal to Noise Ratio (PSNR), Structural Similarity Index (SSIM) and convergence of algorithms. The result evident, even though the convergence time is large, that BD guided BA provides better performance measure values for most of the images compared with the PSO, BFO and LBA algorithms considered in this study.