一种结合改进OTSU法和改进遗传算法的图像分割方法

摘要

In order to automatically determine the optimal threshold in image segmentation, a novel method for image segmentation based on improved OTSU and improved genetic algorithm was presented in this paper. This improved genetic algorithm can be used to globally optimize 2-mension OTSU image segmentation functions, and can automatically adjust the parameters of genetic algorithm according to the fitness values of individuals and the decentralizing degree of individuals of the population and keep the variety of population for rapidly converging to get the optimal thresholds in image segmentation. It overcomes the shortcomings in traditional genetic algorithm. The theoretically analysis and simulate experiments show that the range of the thresholds is more stable and it less time consuming and better satisfies the request of real-time processing in image segmentation, compared with 2-mension OTSU image segmentation and genetic algorithm based image segmentation.%为了自动确定图像分割的最佳阈值,提出了一种结合改进OTSU法和改进遗传算法的图像分割方法,即利用这种改进遗传算法对二维OTSU图像分割函数进行全局优化,该方法能够根据个体适应度大小和群体的分散程度自动调整遗传控制参数,从而能够在保持群体多样性的同时加快收敛速度,最后得到图像分割的最佳阈值,克服了传统遗传算法的收敛性差、易早熟等问题.在理论分析和仿真数据实验中,与二维OTUS图像分割法和基于基本遗传算法的图像分割法相比,使用该方法得出的阈值范围更加稳定,阈值计算时间有极大的降低,更能满足图像处理的实时性要求.