图像分割的遗传算法方法  

Image segmentation method by genetic algorithms

作　　者：吴成柯[1] 刘靖[1] 徐正伟[1] 周凌云 

机构地区：[1]西安电子科技大学通信工程学院

出　　处：《西安电子科技大学学报》1996年第1期34-41,共8页Journal of Xidian University

基　　金：国防预研基金

摘　　要：提出了一种用遗传算法进行图像分割的方法．首先叙述遗传算法的基本原理和它的算法流程；接着研究用遗传算法实现图像分割，提出了单门限和双门限分割的遗传算法，并与传统的Ｏｔｓｕ门限分割方法作了比较，最后给出了几个用遗传算法分割图像的实验结果．结果表明，文中所提出的分割方法不仅分割质量好，而且所需的时间短．An optimal image segmentation method by genetic algorithms (GAs) is presented. First,the principles and the flowchart of GAs are described. Then, adage segmentation is implementedby GAs' The method is adOPted for either single threshold or double threshold. We compare theme thod developed in the paper with the trnditionai segmentation method developed by Otsuabout their segmentation qualities and computational speeds.Finally, the developed method hasbeen 'experimented on several itoages with the results Of the experiments showing that the optimalimage segmentation by GAs is not only of hasher segmentation quality but alSo of higher compu-tational speed.

关 键 词：遗传算法 图像分割 机器视觉 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]