Consecutive Convolutional Activations for Scene Character Recognition

doi:10.1109/ACCESS.2018.2848930

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

	Consecutive Convolutional Activations for Scene Character Recognition
	Zhang, Zhong 1; Wang, Hong 1; Liu, Shuang 1; Xiao, Baihua2
刊名	IEEE ACCESS
	2018
卷号	6 页码:35734-35742
关键词	Consecutive Convolutional Activations Convolutional Neural Network Scene Character Recognition
DOI	10.1109/ACCESS.2018.2848930
文献子类	Article
英文摘要	Driven by the rapid growth of communication technologies and the wide applications of intelligent mobile terminals, the scene character recognition has become a significant yet very challenging task in people's lives. In this paper, we design a novel feature representation scheme termed consecutive convolutional activations (CCA) for character recognition in natural scenes. The proposed CCA could integrate both the low-level and the high-level patterns into the global decision by learning character representations from several successive convolutional layers. Concretely, one shallow convolutional layer is first selected for extracting the convolutional activation features, and then, the next consecutive deep convolutional layers are utilized to learn weight matrices for these convolutional activation features. Finally, the Fisher vectors are employed to encode the CCA features so as to obtain the image-level representations. Extensive experiments are conducted on two English scene character databases (ICDAR2003 and Chars74K) and one Chinese scene character database ("Pan+ChiPhoto"), and the experimental data indicate that the proposed method achieves a superior performance than the previous algorithms.
WOS关键词	TEXT RECOGNITION ; REPRESENTATION ; RETRIEVAL ; SPEECH
WOS研究方向	Computer Science ; Engineering ; Telecommunications
语种	英语
WOS记录号	WOS:000439022000042
资助机构	National Natural Science Foundation of China(61501327 ; Natural Science Foundation of Tianjin(17JCZDJC30600 ; Fund of Tianjin Normal University(135202RC1703) ; Open Projects Program of National Laboratory of Pattern Recognition(201700001 ; China Scholarship Council(201708120039 ; Tianjin Higher Education Creative Team Funds Program ; 61711530240) ; 15JCQNJC01700) ; 201800002) ; 201708120040)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/21848]
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	1.Tianjin Normal Univ, Tianjin Key Lab Wireless Mobile Communicat & Powe, Tianjin 300387, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Zhong,Wang, Hong,Liu, Shuang,et al. Consecutive Convolutional Activations for Scene Character Recognition[J]. IEEE ACCESS,2018,6:35734-35742.
APA	Zhang, Zhong,Wang, Hong,Liu, Shuang,&Xiao, Baihua.(2018).Consecutive Convolutional Activations for Scene Character Recognition.IEEE ACCESS,6,35734-35742.
MLA	Zhang, Zhong,et al."Consecutive Convolutional Activations for Scene Character Recognition".IEEE ACCESS 6(2018):35734-35742.