基于改进遗传算法的电力设备红外图像分割研究  

Research on electrical equipment infrared image segmentation based on improved genetic algorithm

作　　者：李祥 崔昊杨 皮凯云 许永鹏[2] 钱婷[3] 

机构地区：[1]上海电力学院电子与信息工程学院,上海200090 [2]上海交通大学电气工程系,上海200240 [3]上海电子信息职业技术学院通信与信息工程系,上海210411

出　　处：《现代电子技术》2017年第21期56-58,共3页Modern Electronics Technique

基　　金：国家自然科学基金项目(61107081);上海市地方能力建设项目(15110500900;14110500900)资助

摘　　要：针对传统的遗传算法对目标图像感兴趣部位(ROI)分割存在收敛速度慢、耗时长、分割过当等缺点,提出一种改进遗传算法的分割方法,该方法采用最佳熵阈值法确定分割阈值,从而减少计算量,缩短耗时。通过Matlab仿真实验所得结果表明,改进后的遗传算法在电力设备红外图像分割的时间和效果上均优于传统算法。Since the traditional genetic algorithm used to segment the region of interest(ROI)for target image has the disadvantages of slow convergence rate,long time-consumption and excessive segmentation,a segmentation method based on the improved genetic algorithm is presented. The optimal entropy threshold method is adopted in the method to determine the segmentation threshold,reduce the amount of calculation,and shorten the time-consumption. The results of Matlab simulation experiment show that the improved genetic algorithm is superior to the traditional one in the aspects of electric equipment′s infrared image segmentation time and effect.

关 键 词：遗传算法 最佳熵阈值 电力设备红外图像 图像分割 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]