Fisher vector for scene character recognition: A comprehensive evaluation
Shi, Cunzhao; Wang, Yanna; Jia, Fuxi; He, Kun; Wang, Chunheng; Xiao, Baihua
Source PublicationPATTERN RECOGNITION
2017-12-01
Volume72Issue:2017Pages:1-14
SubtypeArticle
AbstractFisher vector (FV), which could be seen as a bag of visual words (BOW) that encodes not only word counts but also higher-order statistics, works well with linear classifiers and has shown promising performance for image categorization. For character recognition, although standard BOW has been applied, the results are still not satisfactory. In this paper, we apply Fisher vector derived from Gaussian Mixture Models (GMM) based visual vocabularies on character recognition and integrate spatial information as well. We, give a comprehensive evaluation of Fisher vector with linear classifier on a series of challenging English and digits character recognition datasets, including both the handwritten and scene character recognition ones. Moreover, we also collect two Chinese scene character recognition datasets to evaluate the suitability of Fisher vector to represent Chinese characters. Through extensive experiments we make three contributions: (1) we demonstrate that FV with linear classifier could outperform most of the state-of-the-art methods for character recognition, even the CNN based ones and the superiority is more obvious when training samples are insufficient to train the networks; (2) we show that additional spatial information is very useful for character representation, especially for Chinese ones, which have more complex structures; and (3) the results also imply the potential of FV to represent new unseen categories, which is quite inspiring since it is quite difficult to collect enough training samples for large-category Chinese scene characters. (C) 2017 Elsevier Ltd. All rights reserved.
KeywordCharacter Representation Character Recognition Fisher Vector (Fv) Gaussian Mixture Models (Gmm) Bag Of Visual Words (Bow)
WOS HeadingsScience & Technology ; Technology
DOI10.1016/j.patcog.2017.06.022
WOS KeywordTEXT RECOGNITION ; OBJECT RECOGNITION ; GENERATIVE MODELS ; REPRESENTATION ; CLASSIFICATION ; HISTOGRAM ; IMAGES
Indexed BySCI
Language英语
Funding OrganizationNational Natural Science Foundation of China (NSFC)(61601462 ; 61531019 ; 71621002)
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS IDWOS:000411545400001
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/19548
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
AffiliationChinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, 95 Zhongguancun East Rd, Beijing 100190, Peoples R China
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Shi, Cunzhao,Wang, Yanna,Jia, Fuxi,et al. Fisher vector for scene character recognition: A comprehensive evaluation[J]. PATTERN RECOGNITION,2017,72(2017):1-14.
APA Shi, Cunzhao,Wang, Yanna,Jia, Fuxi,He, Kun,Wang, Chunheng,&Xiao, Baihua.(2017).Fisher vector for scene character recognition: A comprehensive evaluation.PATTERN RECOGNITION,72(2017),1-14.
MLA Shi, Cunzhao,et al."Fisher vector for scene character recognition: A comprehensive evaluation".PATTERN RECOGNITION 72.2017(2017):1-14.
Files in This Item: Download All
File Name/Size DocType Version Access License
Fisher vector for sc(2285KB)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
[Shi, Cunzhao]'s Articles
[Wang, Yanna]'s Articles
[Jia, Fuxi]'s Articles
Baidu academic
Similar articles in Baidu academic
[Shi, Cunzhao]'s Articles
[Wang, Yanna]'s Articles
[Jia, Fuxi]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Shi, Cunzhao]'s Articles
[Wang, Yanna]'s Articles
[Jia, Fuxi]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Fisher vector for scene character recognition_ A comprehensive evaluation.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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