摘要
木刻藏文经书文中出现字符间粘连、断裂、遮挡现象严重,为识别带来极大的困难。在字符切分、特征提取等文字识别方法基础上,增加了基于BP网络的训练方法,通过对大量的木刻藏文经书字符的训练,修正了数据,收敛了识别结果。实验结果显示,此方法有助于提高木刻藏文经书的文字识别正确率。
The woodcut blocked Tibetan text by book characters between adhesion,fracture,serious block to create great difficulties for the identification.The character segmentation,feature extraction and character recognition method on the basis of an increase based on BP neural network training methods,through the training woodcut Tibetan scriptures character,correction data,the convergence of the identification results,experimental results show that this method the woodcut Tibetan help to improve recognition accuracy by the text of the book.
出处
《微处理机》
2012年第5期35-38,43,共5页
Microprocessors
基金
国家自然科学基金资助项目(61165010)
国家自然科学基金资助项目(61063015)
国家自然科学基金资助项目(61163043)
教育部"长江学者与创新团队发展计划"资助项目(IRT0975)
关键词
木刻经文
文字识别
BP网络
模式识别
Wooden Blocked Tibetan
Character Recognition
BP Network
Pattern Recognition
