Drawing and Recognizing Chinese Characters with Recurrent Neural Network

doi:10.1109/TPAMI.2017.2695539

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

	Drawing and Recognizing Chinese Characters with Recurrent Neural Network
	Zhang, Xu-Yao1 ; Yin, Fei1 ; Zhang, Yan-Ming1 ; Liu, Cheng-Lin1,2 ; Bengio, Yoshua 3
发表期刊	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
	2018-04-01
卷号	40 期号:4 页码:849-862
文章类型	Article
摘要	Recent deep learning based approaches have achieved great success on handwriting recognition. Chinese characters are among the most widely adopted writing systems in the world. Previous research has mainly focused on recognizing handwritten Chinese characters. However, recognition is only one aspect for understanding a language, another challenging and interesting task is to teach a machine to automatically write (pictographic) Chinese characters. In this paper, we propose a framework by using the recurrent neural network (RNN) as both a discriminative model for recognizing Chinese characters and a generative model for drawing (generating) Chinese characters. To recognize Chinese characters, previous methods usually adopt the convolutional neural network (CNN) models which require transforming the online handwriting trajectory into image-like representations. Instead, our RNN based approach is an end-to-end system which directly deals with the sequential structure and does not require any domain-specific knowledge. With the RNN system (combining an LSTM and GRU), state-of-the-art performance can be achieved on the ICDAR-2013 competition database. Furthermore, under the RNN framework, a conditional generative model with character embedding is proposed for automatically drawing recognizable Chinese characters. The generated characters (in vector format) are human-readable and also can be recognized by the discriminative RNN model with high accuracy. Experimental results verify the effectiveness of using RNNs as both generative and discriminative models for the tasks of drawing and recognizing Chinese characters.
关键词	Recurrent Neural Network Lstm Gru Discriminative Model Generative Model Handwriting
WOS标题词	Science & Technology ; Technology
DOI	10.1109/TPAMI.2017.2695539
关键词[WOS]	HANDWRITING RECOGNITION COMPETITION ; OF-THE-ART ; ONLINE ; DATABASES ; ORDER
收录类别	SCI
语种	英语
项目资助者	Strategic Priority Research Program of the Chinese Academy of Sciences(XDB02060009) ; National Natural Science Foundation of China(61403380 ; 61573355)
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000426687100006
引用统计	被引频次：200[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/173211/15357
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
作者单位	1.Chinese Acad Sci, Inst Automat, NLPR, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing 100049, Peoples R China 3.Univ Montreal, MILA Lab, Montreal, PQ H3T 1J4, Canada
第一作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Zhang, Xu-Yao,Yin, Fei,Zhang, Yan-Ming,et al. Drawing and Recognizing Chinese Characters with Recurrent Neural Network[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2018,40(4):849-862.
APA	Zhang, Xu-Yao,Yin, Fei,Zhang, Yan-Ming,Liu, Cheng-Lin,&Bengio, Yoshua.(2018).Drawing and Recognizing Chinese Characters with Recurrent Neural Network.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,40(4),849-862.
MLA	Zhang, Xu-Yao,et al."Drawing and Recognizing Chinese Characters with Recurrent Neural Network".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 40.4(2018):849-862.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
xyz2017TPAMI.pdf（824KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载