Recognizing online handwritten Chinese characters using RNNs with new computing architectures

doi:10.1016/j.patcog.2019.04.015

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 模式分析与学习

	Recognizing online handwritten Chinese characters using RNNs with new computing architectures
	Ren, Haiqing 1; Wang, Weiqiang 2; Liu, Chenglin3
发表期刊	PATTERN RECOGNITION
ISSN	0031-3203
	2019-09-01
卷号	93 页码:179-192
通讯作者	Wang, Weiqiang(wqwang@ucas.ac.cn)
摘要	Although online handwritten Chinese characters recognition has been explored for decades, it is still a challenging task to recognize handwritten Chinese characters accurately. In this paper, we propose an end-to-end recognizer for online handwritten Chinese characters recognition based on a new recurrent neural network (RNN). In the system, two new computing architectures are proposed based on traditional RNN system. One is the variance constraint, and the other is attention weight vector. The variance constraint is used to increase the representation ability of RNN, and the attention weight vector is used to describe the importance of hidden layer states at different time steps. Benefited from the two innovations, the recognition system obtains higher recognition accuracy with fewer parameters. Experiments are carried out on two handwritten Chinese character datasets, lAHCC-UCAS2016 dataset and ICDAR-2013 competition database. The experimental results show that the two innovations are effective, and the proposed end-to-end recognizer obtains better performance than the state-of-the-art methods. (C) 2019 Elsevier Ltd. All rights reserved.
关键词	Online handwritten Chinese character recognition Recurrent neural network New computing architectures
DOI	10.1016/j.patcog.2019.04.015
关键词[WOS]	RECOGNITION
收录类别	SCI
语种	英语
资助项目	National Key R&D Program of China[2017YFB1002203] ; NSFC[61772495] ; NSFC Key Projects of International (Regional) Cooperation and Exchanges[61860206004] ; National Key R&D Program of China[2017YFB1002203] ; NSFC[61772495] ; NSFC Key Projects of International (Regional) Cooperation and Exchanges[61860206004]
项目资助者	National Key R&D Program of China ; NSFC ; NSFC Key Projects of International (Regional) Cooperation and Exchanges
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000472697800014
出版者	ELSEVIER SCI LTD
引用统计	被引频次：18[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/26827
专题	多模态人工智能系统全国重点实验室_模式分析与学习
通讯作者	Wang, Weiqiang
作者单位	1.Univ Chinese Acad Sci, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Sch Comp & Controlling Engn, Beijing, Peoples R China 3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Ren, Haiqing,Wang, Weiqiang,Liu, Chenglin. Recognizing online handwritten Chinese characters using RNNs with new computing architectures[J]. PATTERN RECOGNITION,2019,93:179-192.
APA	Ren, Haiqing,Wang, Weiqiang,&Liu, Chenglin.(2019).Recognizing online handwritten Chinese characters using RNNs with new computing architectures.PATTERN RECOGNITION,93,179-192.
MLA	Ren, Haiqing,et al."Recognizing online handwritten Chinese characters using RNNs with new computing architectures".PATTERN RECOGNITION 93(2019):179-192.