基于乌鸦搜索优化算法的多级阈值图像分割方法  

Multi-Level Threshold Image Segmentation Method Based on Crow Search Optimization Algorithm

作　　者：康丽锋 吴锋 KANG Li-feng;WU Feng(College of Information Engineering, Jiaozuo Normal College, Jiaozuo Henan 454000, China;College of Information Engineering, Xinyang Agriculture and Forestry University, Xinyang Henan 464007, China)

机构地区：[1]焦作师范高等专科学校信息工程学院,河南焦作454000 [2]信阳农林学院信息工程学院,河南信阳464007

出　　处：《西南师范大学学报（自然科学版）》2021年第1期38-43,共6页Journal of Southwest China Normal University(Natural Science Edition)

基　　金：河南省科技攻关项目(172102210450).

摘　　要：针对传统Kapur熵在多阈值图像分割算法中存在运算量大、计算效率低以及精度不高等问题,提出了一种基于乌鸦搜索优化算法的多级阈值图像分割方法,该方法采用Kapur熵作为计算适应度的目标函数,通过引入乌鸦搜索优化算法求解目标函数最大化时的全局最优问题.实验结果表明:相对于其他方法,本文方法在多个评价指标上都有很好的性能体现,并且本文方法在保证较好分割效果的同时,计算效率明显提升.Aiming at the problems of traditional Kapur's entropy in multi-threshold image segmentation algorithm,such as large computational complexity,low computational efficiency and low precision,a multi-level threshold image segmentation method based on crow search optimization algorithm has been proposed.According to the algorithm,Kapur's entropy has been used as the objective function of computational fitness,and introduces the crow search optimization algorithm to solve the global optimal problem when the objective function is maximized.The experimental results show that compared with other methods,the proposed method has good performance on many evaluation indicators,and the calculation efficiency is obviously improved while ensuring better segmentation effect.

关 键 词：图像分割 多级阈值 乌鸦搜索算法 Kapur熵 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]