计算机应用 ›› 2011, Vol. 31 ›› Issue (07): 1844-1846.DOI: 10.3724/SP.J.1087.2011.01844

• 图形图像技术 • 上一篇    下一篇

基于蚁群优化算法的复杂背景图像文字检测方法

李敏花,柏猛   

  1. 山东科技大学 电气信息系, 济南 250031
  • 收稿日期:2011-01-24 修回日期:2011-03-01 发布日期:2011-07-01 出版日期:2011-07-01
  • 通讯作者: 李敏花
  • 作者简介:李敏花(1981-),女,山东济宁人,讲师, 博士,主要研究方向:图像理解与分析;柏猛(1981-),男,山东济宁人,讲师,博士,主要研究方向:人工智能、机器视觉。
  • 基金资助:

    山东科技大学“春蕾计划”;国家自然科学基金资助项目

Text detection from images with complex background by ant colony optimization algorithm

Min-hua LI,Meng BAI   

  1. Department of Electrical and Information Engineering, Shandong University of Science and Technology, Jinan Shandong 250031, China
  • Received:2011-01-24 Revised:2011-03-01 Online:2011-07-01 Published:2011-07-01
  • Contact: Min-hua LI

摘要: 针对复杂背景图像中的文字检测问题,提出一种基于蚁群优化算法的复杂背景图像文字检测方法。该方法首先采用蚁群优化算法提取图像边缘;然后在边缘图像上提取特征,采取由粗到精多级检测、验证的策略进行文字检测。与基于Soble算子、Canny算子等方法的对比实验结果表明,所提出的基于蚁群优化算法的文字检测方法可有效地实现复杂背景图像中的文字检测。

关键词: 文字检测, 边缘检测, 蚁群算法, 复杂背景

Abstract: To detect text from images with different backgrounds, a text detection method with ant colony optimization algorithm was proposed. Before text detection, an ant colony optimization algorithm was adopted to detect image edges, and then features were extracted from the edge image. Afterwards, a coarsetofine strategy was applied to detect the text lines from image. Finally, the experimental results show that the proposed method achieves more precise detection than Soblebased, Cannybased and othor two detection methods.

Key words: text detection, edge detection, ant colony algorithm, complex background