Machine-Printed Traditional Mongolian Characters Recognition Using BP Neural Networks

Machine-Printed Traditional Mongolian Characters Recognition Using BP Neural Networks
复制标题

DOI：
10.1109/cise.2009.5364627
复制
发表时间：
2009-12
期刊：
2009 International Conference on Computational Intelligence and Software Engineering
影响因子：
--
通讯作者：
Hongxi Wei;Guanglai Gao
Hongxi Wei;Guanglai Gao
中科院分区：
其他
文献类型：
--
作者：
Hongxi Wei;Guanglai Gao

文献摘要

被引文献

相似文献

提出了一种基于BP神经网络的机器打印繁体字识别新方法。首先，根据每个汉字在一个词中的位置（首、中、末）和一些稳定的结构特征，将传统蒙古语字符集分为五个子集。然后，使用具有特定结构的BP神经网络对每个子集进行训练和识别。因此，总共有5个BP神经网络，可以识别所有的蒙文繁体字。实验结果表明，BP神经网络对机印传统蒙古语汉字识别具有良好的效果。
This paper presents a new method to recognize machine-printed traditional Mongolian characters by using back-propagation (BP) neural networks. First, the set of traditional Mongolian characters is divided into five subsets according to each character's position (initial, medial or final) within a word and some steady structural features. Then, each subset is trained and recognized by using a BP neural network with particular architecture. Thus, there are five BP neural networks in total, which can recognize all the traditional Mongolian characters. The experimental results are provided and show that the BP neural networks have good performance for the machine-printed traditional Mongolian characters recognition.