The chapter of this book exposes the methodology to segment color images using metaheuristics. There are several methods for segmentation and the one used in this case is multilevel thresholding color image segmentation. In this method, the frequency histogram of the pixel intensities is used as a criterion to locate the thresholds that allow the images to be divided into completely different regions. In this case, the objective function established by Otsu is used for the segmentation of the color images and the pelican optimization algorithm for its optimization. This algorithm shows to be superior over the performance of the objective function in more than 70% of the cases and in the cases in which it does not show that superiority it is very close to the optimal results. With this algorithm, there is a balance in the performance of the objective function and the metrics (PSNR, SSIM, and FSIM). Furthermore, it can be successfully applied in medical images to facilitate the diagnosis of health professionals, as shown in the case of application in polyps in the intestine which can lead to cancer.