MULTILEVEL THRESHOLDING FOR BRAIN MR IMAGE SEGMENTATION USING SWARM-BASED OPTIMIZATION ALGORITHMS

Abstract

Image segmentation, the process of dividing an image into various sets of pixels called segments, is an essential technique in image processing. Image segmentation reduces the complexity of the image and makes it easier to analyze by dividing the image into segments. One of the simplest yet powerful ways of image segmentation is multilevel thresholding, in which pixels are segmented into multiple regions according to their intensities. This study aims to explore and compare the performance of the well-known swarm-based optimization algorithms on the multilevel thresholding-based image segmentation task using brain MR images. Seven swarm-based optimization algorithms: Particle Swarm Optimization (PSO), Artificial Bee Colony (ABC), Gray Wolf Optimizer (GWO), Moth-Flame Optimization (MFO), Ant Lion Optimization (ALO), Whale Optimization (WOA), and Jellyfish Search Optimizer (JS) algorithms are compared by applying to brain MR images to determine threshold levels. In the experiments carried out with mentioned algorithms, minimum cross-entropy, and between-class variance objective functions were employed. Extensive experiments show that JS, ABC, and PSO algorithms outperform others.