计算机工程与应用 ›› 2017, Vol. 53 ›› Issue (12): 203-207.DOI: 10.3778/j.issn.1002-8331.1601-0284

• 图形图像处理 • 上一篇    下一篇

双搜索人工蜂群算法的彩色图像多阈值分割

刘笃晋1,2,贺建英1,周思吉1,胡  月1   

  1. 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
  • 出版日期:2017-06-15 发布日期:2017-07-04

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

LIU Dujin1,2, HE Jianying1, ZHOU Siji1, HU Yue1   

  1. 1.School of Computer Science, Sichuan University of Arts and Science, Dazhou, Sichuan 635000, China
    2.College of Geophysics, Chengdu University of Technology, Chengdu 610059, China
  • Online:2017-06-15 Published:2017-07-04

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。

关键词: 双搜索方程, 人工蜂群算法, 彩色图像, 多阈值分割

Abstract: A novel Double search Artificial Bee Colony algorithm (DABC) for multi thresholding  color image  segmentation  is  proposed  to  solve  the  low precision and slow segmentation speed. In this method, because of insufficiency in ABC regarding its solution search equation, two new search equations are presented to generate candidate solutions in the employed bee phase and the onlookers phase, respectively. Additionally, some more reasonable artificial bee colony parameters are proposed to improve the performance of the artificial bee colony. Then  the proposed algorithm is tested on the images. The results are compared with that of Gbest-guided Artificial Bee Colony algorithm (GABC), the Artificial Bee Colony algorithm (ABC), the Particle Swarm Optimization algorithm (PSO). Compared to the other three multi  thresholding color image segmentation methods, the DABC has significantly improved the accuracy and speed, which is fully able to meet the actual needs.

Key words: double search equation, artificial bee colony algorithm(ABC), color image, multi-threshold segmentation