计算机工程 ›› 2013, Vol. 39 ›› Issue (7): 274-278.doi: 10.3969/j.issn.1000-3428.2013.07.061

• 图形图像处理 • 上一篇    下一篇

布谷鸟搜索算法在多阈值图像分割中的应用

柳新妮,马 苗   

  1. (陕西师范大学计算机科学学院,西安710062)
  • 收稿日期:2012-07-30 出版日期:2013-07-15 发布日期:2013-07-12
  • 作者简介:柳新妮(1986-),女,硕士研究生,主研方向:智能信息处理;马 苗(通讯作者),教授、博士
  • 基金项目:
    国家自然科学基金资助项目(10974130);陕西省青年科技新星基金资助项目(2011kjxx17);陕西省自然科学基金资助项目(2011JQ8009)

Application of Cuckoo Search Algorithm in Multi-threshold Image Segmentation

LIU Xin-ni, MA Miao   

  1. (College of Computer Science, Shaanxi Normal University, Xi’an 710062, China)
  • Received:2012-07-30 Online:2013-07-15 Published:2013-07-12

摘要: 穷举式搜索在寻找多个分割阈值时,计算较为复杂。为解决该问题,提出一种基于布谷鸟搜索算法的多阈值图像分割算法。以Otsu法设计适应度函数,利用布谷鸟搜索算法的并行寻优性能寻找待分割图像的最优阈值。实验结果表明,与细菌觅食算法和人工蜂群算法相比,该算法的寻优速度更快,找到的阈值质量更高。

关键词: 布谷鸟搜索算法, 图像分割, 穷举式搜索, 多阈值, Otsu法

Abstract: Aiming at the problem of searching multiple thresholds by exhaustive search, a new image multi-threshold segmentation algorithm based on Cuckoo Search(CS) algorithm is proposed in this paper. This algorithm employs Otsu method as the fitness function, and uses the favorable parallel searching performance of CS algorithm to quickly and accurately find the optimal thresholds of the image to be segmented. Experimental results show that CS algorithm outforms Bacterial Foraging(BF) algorithm and Artificial Bee Colony(ABC) algorithm in terms of segmentation speed and segmentation thresholds.

Key words: Cuckoo Search(CS) algorithm, image segmentation, exhaustive search, multi-threshold, Otsu method

中图分类号: