吴国新,丁春艳,徐小力,王宁.东巴经典古籍象形文字智能识别研究[J].电子测量与仪器学报,2016,30(11):1774-1779
东巴经典古籍象形文字智能识别研究
Intelligent recognition on Dongba manuscripts hieroglyphs
  
DOI:10.13382/j.jemi.2016.11.020
中文关键词:  特征提取  文字识别  东巴象形文字  神经网络
英文关键词:Feature extraction  character recognition  Dongba hieroglyphs  neural network
基金项目:国家社科基金重大项目(12&ZD234)、现代测控技术教育部重点实验室开放项目(KF20161123201,KF20161123202)
作者单位
吴国新 北京信息科技大学现代测控技术教育部重点实验室北京100192 
丁春艳 中央民族大学北京100081 
徐小力 北京信息科技大学现代测控技术教育部重点实验室北京100192 
王宁 北京信息科技大学现代测控技术教育部重点实验室北京100192 
AuthorInstitution
Wu Guoxin Key Laboratory of Modern Measurement & Control Technology Ministry of Education, Beijing Information Science & Technology University, Beijing 100192,China 
Ding Chunyan Minzu University of China, Beijing 100081, China 
Xu Xiaoli Key Laboratory of Modern Measurement & Control Technology Ministry of Education, Beijing Information Science & Technology University, Beijing 100192,China 
Wang Ning Key Laboratory of Modern Measurement & Control Technology Ministry of Education, Beijing Information Science & Technology University, Beijing 100192,China 
摘要点击次数: 46
全文下载次数: 62
中文摘要:
      东巴象形文字被国际学界认为是当今世界上唯一还在使用的象形文字, 用象形文字书写的经典, 称为东巴经。 东巴象形文字多具图画特性, 结构复杂形式多样且笔划各异。 针对东巴文特有的结构进行了深入的研究, 主要讨论了东巴象形文的特征提取和文字识别。 特征提取是文字识别中很重要的环节, 文字识别中特征提取的方法有很多, 但由于东巴文字的字型有很多种特点, 提出了适合东巴文识别的最优特征提取方法: 特征点法、 投影法;识别方法: 高阶神经网络法。 通过实验对该方法进行了验证, 结果表明该方法的可行性。
英文摘要:
      Dongba hieroglyphs by international scholars believe is only used in the world today with hieroglyphics, pictographic writing classic, known as dongba script. It has the picture characteristics and the complex structure of different forms & strokes. According to the structure characteristic of Dongba we do some in depth study. Feature extraction and character recognition of Dongba Pictograph are mainly discussed. Feature extraction is a very important link in the character recognition. there are many methods in feature extraction, but due to the many kinds of characteristics of Dongba font proposed the optimal feature extraction method for Dongba identification: the characteristic point method, projection method; identification method: high order neural network method. The method has been verified by experimental. The results show that the method is feasible.
查看全文  查看/发表评论  下载PDF阅读器