Fisher vector for scene character recognition: A comprehensive evaluation

doi:10.1016/j.patcog.2017.06.022

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

	Fisher vector for scene character recognition: A comprehensive evaluation
	Shi, Cunzhao; Wang, Yanna; Jia, Fuxi; He, Kun; Wang, Chunheng; Xiao, Baihua
刊名	PATTERN RECOGNITION
	2017-12-01
卷号	72 期号:2017 页码:1-14
关键词	Character Representation Character Recognition Fisher Vector (Fv) Gaussian Mixture Models (Gmm) Bag Of Visual Words (Bow)
DOI	10.1016/j.patcog.2017.06.022
文献子类	Article
英文摘要	Fisher 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.
WOS关键词	TEXT RECOGNITION ; OBJECT RECOGNITION ; GENERATIVE MODELS ; REPRESENTATION ; CLASSIFICATION ; HISTOGRAM ; IMAGES
WOS研究方向	Computer Science ; Engineering
语种	英语
WOS记录号	WOS:000411545400001
资助机构	National Natural Science Foundation of China (NSFC)(61601462 ; 61531019 ; 71621002)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/19548]
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, 95 Zhongguancun East Rd, Beijing 100190, Peoples R China
推荐引用方式 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.