CRF based text detection for natural scene images using convolutional neural network and context information

doi:10.1016/j.neucom.2017.12.058

CASIA OpenIR > 复杂系统管理与控制国家重点实验室 > 影像分析与机器视觉

	CRF based text detection for natural scene images using convolutional neural network and context information
	Wang, Yanna; Shi, Cunzhao; Xiao, Baihua; Wang, Chunheng; Qi, Chengzuo
发表期刊	NEUROCOMPUTING
	2018-06-21
卷号	295 页码:46-58
文章类型	Article
摘要	This paper presents a novel scene text detection method based on conditional random field (CRF) framework. We estimate the confidence of Maximally Stable Extremal Region (MSER) being text by leveraging convolutional neural network (CNN) to define the unary cost item. In addition, we establish the neighboring interactions for MSERs using four different features including color, shape, stroke and spatial features to define the pairwise cost item. Considering the special layout of texts appearing in natural scene images, we employ context information to recover missing text MSER candidates. Furthermore, text MSERs are grouped into candidate text lines which are verified with shape-specific classifiers by integrating gray and binary features. Experimental results on four public benchmark datasets show that the proposed method achieves the comparable performance. (C) 2018 Elsevier B.V. All rights reserved.
关键词	Scene Text Detection Mser Cnn Crf Context Information Shape-specific Classifiers
WOS标题词	Science & Technology ; Technology
DOI	10.1016/j.neucom.2017.12.058
关键词[WOS]	STABLE EXTREMAL REGIONS ; READING TEXT ; SEGMENTATION ; LOCALIZATION ; ALGORITHM
收录类别	SCI
语种	英语
项目资助者	National Natural Science Foundation of China (NSFC)(61601462 ; 61531019 ; 71621002)
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000430227300005
引用统计	被引频次：19[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/173211/22006
专题	复杂系统管理与控制国家重点实验室_影像分析与机器视觉
作者单位	Univ Chinese Acad Sci, Inst Automat Chinese Acad Sci CASIA, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
第一作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Wang, Yanna,Shi, Cunzhao,Xiao, Baihua,et al. CRF based text detection for natural scene images using convolutional neural network and context information[J]. NEUROCOMPUTING,2018,295:46-58.
APA	Wang, Yanna,Shi, Cunzhao,Xiao, Baihua,Wang, Chunheng,&Qi, Chengzuo.(2018).CRF based text detection for natural scene images using convolutional neural network and context information.NEUROCOMPUTING,295,46-58.
MLA	Wang, Yanna,et al."CRF based text detection for natural scene images using convolutional neural network and context information".NEUROCOMPUTING 295(2018):46-58.