Multi-order co-occurrence activations encoded with Fisher Vector for scene character recognition
Wang, Yanna1,2; Shi, Cunzhao1,2; Wang, Chunheng1,2; Xiao, Baihua1,2; Qi, Chengzuo1,2
Source PublicationPATTERN RECOGNITION LETTERS
2017-10-01
Volume97Issue:2017Pages:69-76
SubtypeArticle
AbstractScene character recognition remains a challenging task due to many interference factors. Considering that characters are composed of a series of parts arranged in certain structures, in this paper, we propose a novel representation termed multi-order co-occurrence activations (MCA) encoded with Fisher Vector (FV), namely MCA-FV. It implicitly models the co-occurrence information of discriminative character parts at different orders to boost the recognition performance. We first extract convolutional activations as local descriptors of character parts from convolutional neural networks (CNNs). Then, we introduce MCA features to capture the multi-order co-occurrence cues among different discriminative character parts. Finally, we apply FV to encode co-occurrence features of each order and obtain a global representation of MCA-FV. The proposed method is evaluated on four scene character datasets including English and Chinese datasets. Experiment results demonstrate the effectiveness of the proposed method for scene character recognition. (C) 2017 Elsevier B.V. All rights reserved.
KeywordScene Character Recognition Multi-order Co-occurrence Activations Fisher Vector Cnn
WOS HeadingsScience & Technology ; Technology
DOI10.1016/j.patrec.2017.07.011
WOS KeywordTEXT RECOGNITION ; ORIENTED GRADIENTS ; REPRESENTATION ; STROKELETS ; HISTOGRAM
Indexed BySCI
Language英语
Funding OrganizationNational Natural Science Foundation of China (NSFC)(61601462 ; 61531019 ; 71621002)
WOS Research AreaComputer Science
WOS SubjectComputer Science, Artificial Intelligence
WOS IDWOS:000411765800011
Citation statistics
Cited Times:6[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/19587
Collection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
Affiliation1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Beijing, Peoples R China
First Author AffilicationChinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Wang, Yanna,Shi, Cunzhao,Wang, Chunheng,et al. Multi-order co-occurrence activations encoded with Fisher Vector for scene character recognition[J]. PATTERN RECOGNITION LETTERS,2017,97(2017):69-76.
APA Wang, Yanna,Shi, Cunzhao,Wang, Chunheng,Xiao, Baihua,&Qi, Chengzuo.(2017).Multi-order co-occurrence activations encoded with Fisher Vector for scene character recognition.PATTERN RECOGNITION LETTERS,97(2017),69-76.
MLA Wang, Yanna,et al."Multi-order co-occurrence activations encoded with Fisher Vector for scene character recognition".PATTERN RECOGNITION LETTERS 97.2017(2017):69-76.
Files in This Item: Download All
File Name/Size DocType Version Access License
Multi-order co-occur(1105KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Wang, Yanna]'s Articles
[Shi, Cunzhao]'s Articles
[Wang, Chunheng]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wang, Yanna]'s Articles
[Shi, Cunzhao]'s Articles
[Wang, Chunheng]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wang, Yanna]'s Articles
[Shi, Cunzhao]'s Articles
[Wang, Chunheng]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Multi-order co-occurrence activations encoded with Fisher Vector for scene character recognition.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.