双搜索人工蜂群算法的彩色图像多阈值分割  

Double search equation artificial bee colony algorithm for multi-threshold color image segmentation

作　　者：刘笃晋[1,2] 贺建英[1] 周思吉[1] 胡月[1] LIU Dujin;HE Jianying;ZHOU Siji;HU Yue(School of Computer Science, Sichuan University of Arts and Science, Dazhou, Sichuan 635000, China;College of Geophysics, Chengdu University of Technology, Chengdu 610059, China)

机构地区：[1]四川文理学院计算机学院,四川达州635000 [2]成都理工大学地球物理学院,成都610059

出　　处：《计算机工程与应用》2017年第12期203-207,213,共6页Computer Engineering and Applications

基　　金：国家自然科学基金(No.61152003);四川省教育厅资助科研项目(No.15ZB0323);2014年四川省大学生创新创业训练计划项目(No.201410644015)

摘　　要：针对彩色图像多阈值分割中普遍存在精度低、速度慢的问题,提出了一种新的基于双搜索人工蜂群(DABC)的彩色图像多阈值分割算法。首先由于人工蜂群算法单一的解搜索公式存在不足,对雇佣蜂和跟随蜂各提出了一种搜索公式,进而对人工蜂群算法的相关参数进行了改进,然后做了DABC算法、全局最优引导人工蜂群算法(GABC)、人工蜂群算法(ABC)、粒子群优化算法(PSO)这四种算法的彩色图像多阈值分割对比实验。实验结果表明,与其他三种算法相比,基于DABC的彩色图像多阈值分割方法在分割的精度和速度上都有明显提高,完全能满足实际的需要。A novel Double search Artificial Bee Colony algorithm(DABC)for multi thresholding color image segmentationis proposed to solve the low precision and slow segmentation speed.In this method,because of insufficiency inABC regarding its solution search equation,two new search equations are presented to generate candidate solutions in theemployed bee phase and the onlookers phase,respectively.Additionally,some more reasonable artificial bee colony parametersare proposed to improve the performance of the artificial bee colony.Then the proposed algorithm is tested on theimages.The results are compared with that of Gbest-guided Artificial Bee Colony algorithm(GABC),the Artificial BeeColony algorithm(ABC),the Particle Swarm Optimization algorithm(PSO).Compared to the other three multi thresholdingcolor image segmentation methods,the DABC has significantly improved the accuracy and speed,which is fullyable to meet the actual needs.

关 键 词：双搜索方程 人工蜂群算法 彩色图像 多阈值分割 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]