摘要
图像处理方面的核心科学中图像分割是相当重要的方面,是图像处理领域的关键技术,并且影像判断分析与模式识别也是在良好的图像分割的基础上完成的。利用改进遗传算法对二维Otsu图像分割函数进行全局优化,该方法可以根据单体适合度值和种群特点调整遗传群体运算的控制参数,进而在保持种群多样性的同时加快收敛速度,得到图像分割处理的最佳分割阈值。该方法克服了基本遗传算法的收敛性差、易早熟等问题。
The core scientific image segmentation is a very important aspect in image processing and it is a key technology in the field of image processing. The image analysis and pattern recognition is also made based on good image segmentation. The improved genetic algorithm is used to make optimization for the two-dimensional Otsu segmentation function; this method can adjust the control parameters of genetic population operations according to the monomer values and population characteristics,while to maintain the diversity of the population and accelerate the convergence speed,then to get the optimal segmentation threshold value of image segmentation process. The method overcomes the problems that the convergence is poor,prematurity and other issues in the basic genetic algorithm.
出处
《山西电子技术》
2015年第1期36-37,共2页
Shanxi Electronic Technology
关键词
遗传算法
图像分割
控制参数
多样性
genetic algorithms
image segmentation
control parameters
diversity
