Teaching machines to write like humans using L-attributed grammar

doi:10.1016/j.engappai.2020.103489

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

	Teaching machines to write like humans using L-attributed grammar
	Shao, Yunxue 1; Liu, Cheng-Lin2,3
发表期刊	ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
ISSN	0952-1976
	2020-04-01
卷号	90 页码:10
通讯作者	Shao, Yunxue(csshyx@njtech.edu.cn)
摘要	Reading and writing are easy for humans. The automatic reading of handwritten characters has been studied for several decades. Machine learning algorithms for reading tasks often require a huge amount of data to perform with similar accuracy to humans, yet it is also difficult to gain sufficient meaningful data. Automatic writing tasks have not been studied as extensively. In this paper, we teach machines to write like teaching a child by telling the machine the method for writing each character using L-attributed grammar. With the aid of the proposed TMTW (Teaching Machines To Write) interacting system, a human as a teacher only needs to provide the writing sequence of parts and control lines. The proposed system automatically perceives the relationships between control lines and parts, and constructs the grammars. Top-down derivation and the stroke generation method are applied to generate varying characters based on the learned grammars. For as long as a machine can write, it can be applied in robot control or training sample generation for automatic reading tasks. The MNIST and CASIA datasets are used to demonstrate the effectiveness of the proposed system on different languages. The machine written samples are used to train a network, which is evaluated on the MNIST test set. A test error rate of 1.23% is achieved using only approximately 20 grammars on average for each digit. Using the generated and handwritten samples together as a training set can reduce the test error rate to 0.61%. Similar experiments are conducted using the CASIA data set, and the results demonstrated that the proposed method is effective in generating characters with a complex structure.
关键词	Automatic writing Handwritten character recognition L-attributed grammar Top-down derivation
DOI	10.1016/j.engappai.2020.103489
关键词[WOS]	CHINESE CHARACTERS ; RECOGNITION ; ONLINE
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China (NSFC)[61563039]
项目资助者	National Natural Science Foundation of China (NSFC)
WOS研究方向	Automation & Control Systems ; Computer Science ; Engineering
WOS类目	Automation & Control Systems ; Computer Science, Artificial Intelligence ; Engineering, Multidisciplinary ; Engineering, Electrical & Electronic
WOS记录号	WOS:000528194400011
出版者	PERGAMON-ELSEVIER SCIENCE LTD
引用统计	被引频次：1[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/173211/39362
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	Shao, Yunxue
作者单位	1.Nanjing Tech Univ, Sch Comp Sci & Technol, Nanjing, Peoples R China 2.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Shao, Yunxue,Liu, Cheng-Lin. Teaching machines to write like humans using L-attributed grammar[J]. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE,2020,90:10.
APA	Shao, Yunxue,&Liu, Cheng-Lin.(2020).Teaching machines to write like humans using L-attributed grammar.ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE,90,10.
MLA	Shao, Yunxue,et al."Teaching machines to write like humans using L-attributed grammar".ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 90(2020):10.