基于改进遗传算法的电力设备红外图像分割研究

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 dis-advantages 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 seg-mentation threshold,reduce the amount of calculation,and shorten the time-consumption. The results of Matlab simulation ex-periment show that the improved genetic algorithm is superior to the traditional one in the aspects of electric equipment′s infra-red image segmentation time and effect.