A Novel Evolutionary Arithmetic Optimization Algorithm for Multilevel Thresholding Segmentation of COVID-19 CT Images

One of the most crucial aspects image segmentation is multilevel thresholding. However, thresholding becomes increasingly more computationally complex as number thresholds grows. In order to address this defect, paper proposes a new approach based on Evolutionary Arithmetic Optimization Algorithm (AOA). The arithmetic operators in science were inspiration for AOA. DAOA proposed approach, which employs Differential Evolution technique enhance AOA local research. algorithm applied problem, using Kapur’s measure between class variance functions. suggested used evaluate images, eight standard test images from two different groups: nature and CT COVID-19 images. Peak signal-to-noise ratio (PSNR) structural similarity index (SSIM) are evaluation measures determine accuracy segmented method’s efficiency evaluated compared other methods. findings presented with threshold values (i.e., 2, 3, 4, 5, 6). According experimental results, process better produces higher-quality solutions than comparative approaches. Moreover, it achieved better-segmented PSNR, SSIM values. addition, ranked first method all cases.