Image segmentation is a fundamental process in image processing, aiming to transform the image into a more comprehensible or simplified representation. This process groups pixels under common characteristics, facilitating the unique identification of regions or elements of interest. The quality of segmentation is crucial as it significantly influences the subsequent stages of image processing. Image segmentation plays a vital role in various advanced applications, including computer vision and the analysis of medical, topographical, and astronomical images. Given that there is no universal segmentation method guaranteeing optimal performance for all cases, selecting an appropriate technique for a specific type of image or application represents a complex and demanding challenge. In this work, we propose the use of Multi-Objective Evolutionary Algorithms (MOEAs) as a training tool that integrates operations representative of the usual techniques and strategies in image segmentation. This allows for the generation of operation sequences adapted to specific applications or types of images. The objective functions used to guide the evolutionary process are the maximization of sensitivity (TPR) and specificity(TNR), fundamental components of ROC analysis. Experiments were conducted with multiple images sharing common characteristics from image databases, specifically: i ) benign and malignant melanoma images, ii ) ophthalmoscopic retinal images, and iii ) binary cell form images. We compared the segmentation generated by our proposed algorithm with the ideal segmentation. The results are quite promising and demonstrate the feasibility of using MOEAs to generate sequences of segmentation operations valid for specific applications.

Pedro Esteban Gardel Sotomayor

Diego P. Pinto-Roa

Julio César Mello-Román

José Luis Vázquez Noguera

Ramón Quintana

Fredy Roa

CLEI electronic journal

CLEI Eletronic Journal (CLEIej)

Multi-objective Evolutionary Algorithms based Operation Sequence Design for Image Segmentation

基于多目标进化算法的图像分割操作序列设计

Multi-objective Evolutionary Algorithms based Operation Sequence Design for Image Segmentation

ivySCI AI Smartly Parses PDF, Answers Researchers' Questions, and Helps You Understand Papers in Seconds

Journal Info