A knowledge-based recognition system for historical Mongolian documents
A knowledge-based recognition system for historical Mongolian documents
复制标题
基于知识的蒙古文历史文献识别系统
DOI：
10.1007/s10032-016-0267-1
复制
发表时间：
2016-09
影响因子：
2.3
通讯作者：
Bao, Feilong
中科院分区：
文献类型：
--
作者：
Su, Xiangdong;Gao, Guanglai;Wei, Hongxi;Bao, Feilong
本文提出了一种基于知识的蒙古文历史文献识别系统，该系统的特点是文字变异和文字重叠。该系统根据蒙古文构词的特点，采用整体识别和分词识别相结合的识别方法。使用整体方案识别不能分割成字形单元或不需要分割的几种类型的单词和孤立后缀。剩下的词采用基于分词的方法进行识别，这是本文的重点。在基于分词的方案中，我们利用字形特征的知识将单词切分成字形单元。卷积神经网络不仅在整体方案中用于单词识别，而且在基于分割的方案中也用于字形单元识别。在分析基于分割的识别错误的基础上，通过将三种策略结合到字形单元识别中，对系统进行了增强。这些策略包括合并基线信息、字形单元分组以及识别分段不足和分段过多的片段。该系统在蒙古文汉字测试样本上达到了80.86%的词准确率。
This paper proposes a knowledge-based system to recognize historical Mongolian documents in which the words exhibit remarkable variation and character overlapping. According to the characteristics of Mongolian word formation, the system combines a holistic scheme and a segmentation-based scheme for word recognition. Several types of words and isolated suffixes that cannot be segmented into glyph-units or do not require segmentation are recognized using the holistic scheme. The remaining words are recognized using the segmentation-based scheme, which is the focus of this paper. We exploit the knowledge of the glyph characteristics to segment words into glyph-units in the segmentation-based scheme. Convolutional neural networks are employed not only for word recognition in the holistic scheme, but also for glyph-unit recognition in the segmentation-based scheme. Based on the analysis of recognition errors in the segmentation-based scheme, the system is enhanced by integrating three strategies into glyph-unit recognition. These strategies involve incorporating baseline information, glyph-unit grouping, and recognizing under-segmented and over-segmented fragments. The proposed system achieves 80.86 % word accuracy on the Mongolian Kanjur test samples.
登录
查看更多内容
影响因子：
12
作者：
T. Saba;A. Rehman;Mohamed Elarbi-Boudihir
通讯作者：
T. Saba;A. Rehman;Mohamed Elarbi-Boudihir
DOI：
10.1109/icdar.2005.237
发表时间：
2005-08
期刊：
Eighth International Conference on Document Analysis and Recognition (ICDAR'05)
影响因子：
--
作者：
C. Cheng;M. Blumenstein
通讯作者：
C. Cheng;M. Blumenstein
DOI：
10.54097/hset.v17i.2576
发表时间：
2022-11
期刊：
Highlights in Science, Engineering and Technology
影响因子：
--
作者：
Jiahao You
通讯作者：
Jiahao You
DOI：
10.1109/cise.2009.5364627
发表时间：
2009-12
期刊：
2009 International Conference on Computational Intelligence and Software Engineering
影响因子：
--
作者：
Hongxi Wei;Guanglai Gao
通讯作者：
Hongxi Wei;Guanglai Gao
DOI：
10.1109/snpd.2007.12
发表时间：
2007-07
期刊：
Eighth ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing (SNPD 2007)
影响因子：
--
作者：
Xue-dong Tian;Yan Zhang
通讯作者：
Xue-dong Tian;Yan Zhang