Context based image segmentation using antlion optimization and sine cosine algorithm

Multilevel thresholding (MTH) is one of the most commonly used approaches to perform segmentation on images. However, as most methods are based on the histogram of the image to be segmented, MTH methods only consider the occurrence frequency of certain intensity level disregarding all spatial information. Contextual information can help to enhance the quality of the segmented image as it considers not only the value of the pixel but also its vicinity. The energy curve was designed to bring spatial information into a curve with the same properties as the histogram. In this paper, two recently proposed Evolutionary Computational Algorithms (ECAs) are coupled with two classical thresholding criteria to perform MTH over the energy curve. The selected ECAs are the Antlion Optimizer (ALO) and the Sine Cosine Algorithm (SCA). The proposed methods are evaluated intensively regarding quality, and a statistical analysis is presented to compare the results of the algorithms against similar approaches. Experimental evidence encourages the use ALO for MTH while it concludes that SCA does not outperform other ECAs form the state-of-the-art.