首页> 外文期刊>Information Technology Journal >Manchu Text Extract Based on Fuzzy Clustering
【24h】

Manchu Text Extract Based on Fuzzy Clustering

机译:基于模糊聚类的满文提取

获取原文
       

摘要

Based on fuzzy clustering under the image background, this study proposes a new stroke extraction method of Manchu. Firstly, the digital image processing method is used to extract the Manchu word from an image background picture, do the de-noising, thinning, pruning and other pre-processed for fuzzy clustering. Then the mid-axis of Manchu character, termination point, interior points, intersection points is defined and finds the boundary point on mid-axis, use the stroke growth algorithm to separate the stroke so as to achieve the purpose of Manchu text stroke elaborates. To verify the feasibility of the method, this study carried out a text extraction on handwritten Manchu and printed Manchu. Simulation results show that the method is effective in separating the Manchu stroke and laid a solid foundation to the further study of Manchu identification.
机译:基于图像背景下的模糊聚类,提出了一种满族笔画提取方法。首先,采用数字图像处理方法从图像背景图片中提取满族词,进行去噪,细化,修剪等模糊聚类预处理。然后定义满汉字的中轴,终止点,内部点,交点,并在中轴上找到边界点,使用笔划增长算法将笔划分开,以达到满文笔画细化的目的。为了验证该方法的可行性,本研究对手写的满族和印刷的满族进行了文本提取。仿真结果表明,该方法可有效分离满族笔画,为进一步研究满族识别打下基础。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号