Reading scene text with fully convolutional sequence modeling

doi:10.1016/j.neucom.2019.01.094

	Reading scene text with fully convolutional sequence modeling
	Gao, Yunze1,2 ; Chen, Yingying1,2 ; Wang, Jinqiao1,2 ; Tang, Ming1,2 ; Lu, Hanqing1,2
刊名	NEUROCOMPUTING
	2019-04-28
卷号	339 页码:161-170
关键词	Fully convolutional sequence modeling Scene text recognition
ISSN号	0925-2312
DOI	10.1016/j.neucom.2019.01.094
通讯作者	Chen, Yingying(yingying.chen@nlpr.ia.ac.cn)
英文摘要	Reading text in the wild is a challenging task in computer vision. Existing approaches mainly adopt connectionist temporal classification (CTC) or attention models based on recurrent neural network (RNN), and are computationally expensive and hard to train. In this paper, instead of the chain structure of RNN, we propose an end-to-end fully convolutional network with the stacked convolutional layers to effectively capture the long-term dependencies among elements of scene text image. The stacked convolutional layers are much more efficient than bidirectional long short-term memory (BLSTM) in modeling the contextual dependency. In addition, we design a discriminative feature encoder by incorporating the residual attention blocks into a small densely connected network to enhance the foreground text and suppress the background noise. Extensive experiments on seven standard benchmarks, the Street View Text, IIIT5K, ICDAR03, ICDAR13, ICDAR15, COCO-Text and Total-Text, validate that our method not only achieves state-of-the-art or highly competitive recognition performance, but significantly improves the efficiency and reduces the number of parameters as well. (C) 2019 Elsevier B.V. All rights reserved.
资助项目	National Natural Science Foundation of China[61772527] ; National Natural Science Foundation of China[61806200]
WOS关键词	RECOGNITION
WOS研究方向	Computer Science
语种	英语
出版者	ELSEVIER SCIENCE BV
WOS记录号	WOS:000461166500016
资助机构	National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/24984]
专题	中国科学院自动化研究所
通讯作者	Chen, Yingying
作者单位	1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, 95 Zhongguancun East Rd, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Gao, Yunze,Chen, Yingying,Wang, Jinqiao,et al. Reading scene text with fully convolutional sequence modeling[J]. NEUROCOMPUTING,2019,339:161-170.
APA	Gao, Yunze,Chen, Yingying,Wang, Jinqiao,Tang, Ming,&Lu, Hanqing.(2019).Reading scene text with fully convolutional sequence modeling.NEUROCOMPUTING,339,161-170.
MLA	Gao, Yunze,et al."Reading scene text with fully convolutional sequence modeling".NEUROCOMPUTING 339(2019):161-170.