Scene text recognition by learning co-occurrence of strokes based on spatiality embedded dictionary

CORC > 自动化研究所 > 中国科学院自动化研究所 > 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团队

	Scene text recognition by learning co-occurrence of strokes based on spatiality embedded dictionary
	Gao, Song; Wang, Chunheng; Xiao, Baihua; Shi, Cunzhao; Zhou, Wen; Zhang, Zhong
刊名	IET COMPUTER VISION
	2015-02-01
卷号	9 期号:1 页码:138-148
关键词	character recognition dictionaries text detection scene text recognition high-level image understanding text information scene images local strokes spatiality embedded dictionary SED robust character recognition localised soft coding max pooling sparse dictionary CHARS74 K dataset ICDAR2003 dataset
英文摘要	Text information contained in scene images is very helpful for high-level image understanding. In this study, the authors propose to learn co-occurrence of local strokes for scene text recognition by using a spatiality embedded dictionary (SED). Unlike spatial pyramid partitioning images into grids to incorporate spatial information, the authors SED associates every codeword with a particular response region and introduces more precise spatial information for robust character recognition. After localised soft coding and max pooling of the first layer, a sparse dictionary is learned to model co-occurrence of several local strokes, which further improves classification performance. Experimental results on two scene character recognition datasets ICDAR2003 and CHARS74 K demonstrate that their character recognition method outperforms state-of-the-art methods. Besides, competitive word recognition results are also reported for four benchmark word recognition datasets ICDAR2003, ICDAR2011, ICDAR2013 and street view text when combining their character recognition method with a conditional random field language model.
WOS标题词	Science & Technology ; Technology
类目[WOS]	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
研究领域[WOS]	Computer Science ; Engineering
收录类别	SCI
语种	英语
WOS记录号	WOS:000349308600012
公开日期	2015-09-22
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/8050]
专题	自动化研究所_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团队
作者单位	Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Gao, Song,Wang, Chunheng,Xiao, Baihua,et al. Scene text recognition by learning co-occurrence of strokes based on spatiality embedded dictionary[J]. IET COMPUTER VISION,2015,9(1):138-148.
APA	Gao, Song,Wang, Chunheng,Xiao, Baihua,Shi, Cunzhao,Zhou, Wen,&Zhang, Zhong.(2015).Scene text recognition by learning co-occurrence of strokes based on spatiality embedded dictionary.IET COMPUTER VISION,9(1),138-148.
MLA	Gao, Song,et al."Scene text recognition by learning co-occurrence of strokes based on spatiality embedded dictionary".IET COMPUTER VISION 9.1(2015):138-148.