摘要
由于对字符提取骨架往往会失去受污损部位的重要信息,因此本文提出了一种基于蚁群算法的现代藏文字符轮廓提取算法,旨在用字符的轮廓线代替骨架线来表征字符。本算法用于印刷体藏文轮廓提取,取得了良好的效果,避免了传统细化算法造成的畸变,提高了轮廓提取的抗干扰能力,并且减小了计算量,加快了特征提取的速度。
When we extract the skeleton lines of characters, the important information of defiled components always lost. Therefore, a contour line extraction algorithm for Tibetan character based on ant colony algorithm is presented in this paper. Contour lines are used to present characters instead of skeleton lines. Experimental results show that the proposed algorithm can correctly extract contour lines of printed Tibetan character on the human perception. In addition, compared with the method based on thinning algorithm, the proposed algorithm is more robust and faster. The study on contour line extraction is very important part of Tibetan recognition.
出处
《微计算机应用》
2008年第5期38-41,共4页
Microcomputer Applications
基金
烟台市科学技术发展计划基金资助(2006120)
关键词
蚁群算法
轮廓提取
藏文识别
Ant colony algorithm, Contour lines extraction, Tibetan character recognition