End-to-end scene text recognition using tree-structured models

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

	End-to-end scene text recognition using tree-structured models
	Shi, Cunzhao; Wang, Chunheng; Xiao, Baihua; Gao, Song; Hu, Jinlong; Wang Chunheng
发表期刊	PATTERN RECOGNITION
	2014-09-01
卷号	47 期号:9 页码:2853-2866
文章类型	Article
摘要	Detecting and recognizing text in natural images are quite challenging and have received much attention from the computer vision community in recent years. In this paper, we propose a robust end-to-end scene text recognition method, which utilizes tree-structured character models and normalized pictorial structured word models. For each category of characters, we build a part-based tree-structured model (TSM) so as to make use of the character-specific structure information as well as the local appearance information. The TSM could detect each part of the character and recognize the unique structure as well, seamlessly combining character detection and recognition together. As the TSMs could accurately detect characters from complex background, for text localization, we apply TSMs for all the characters on the coarse text detection regions to eliminate the false positives and search the possible missing characters as well. While for word recognition, we propose a normalized pictorial structure (PS) framework to deal with the bias caused by words of different lengths. Experimental results on a range of challenging public datasets (ICDAR 2003, ICDAR 2011, SVT) demonstrate that the proposed method outperforms state-of-the-art methods both for text localization and word recognition. (C) 2014 Elsevier Ltd. All rights reserved.
关键词	End-to-end Scene Text Recognition Part-based Tree-structured Models (Tsms) Normalized Pictorial Structure
WOS标题词	Science & Technology ; Technology
关键词[WOS]	POSE ESTIMATION ; SEGMENTATION ; IMAGES ; LOCALIZATION ; DETECT ; WILD
收录类别	SCI
语种	英语
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000336872000006
引用统计	被引频次：24[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/173211/3759
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
通讯作者	Wang Chunheng
作者单位	Chinese Acad Sci, Inst Automat, 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	Shi, Cunzhao,Wang, Chunheng,Xiao, Baihua,et al. End-to-end scene text recognition using tree-structured models[J]. PATTERN RECOGNITION,2014,47(9):2853-2866.
APA	Shi, Cunzhao,Wang, Chunheng,Xiao, Baihua,Gao, Song,Hu, Jinlong,&Wang Chunheng.(2014).End-to-end scene text recognition using tree-structured models.PATTERN RECOGNITION,47(9),2853-2866.
MLA	Shi, Cunzhao,et al."End-to-end scene text recognition using tree-structured models".PATTERN RECOGNITION 47.9(2014):2853-2866.

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
PREnd-to-End Scene T（14024KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载