CASIA OpenIR  > 模式识别国家重点实验室  > 模式分析与学习
Discriminative quadratic feature learning for handwritten Chinese character recognition
Zhou, Ming-Ke; Zhang, Xu-Yao; Yin, Fei; Liu, Cheng-Lin
Source PublicationPATTERN RECOGNITION
2016
Volume49Issue:1Pages:7-18
SubtypeArticle
AbstractIn this paper, we propose a feature learning method for handwritten Chinese character recognition (HCCR), called discriminative quadratic feature learning (DQFL). Based on original gradient direction feature representation, quadratic correlation between features is used to promote the feature dimensionality, then discriminative feature extraction (DFE) is used for dimensionality reduction. By combining dimensionality promotion and reduction, we can learn a much more discriminative and nonlinear feature representation, which can then boost the classification accuracy significantly. For dimensionality promotion, two types of correlation are exploited, namely, statistical correlation and spatial correlation. Statistical correlation is computed on multiple local feature vectors in different regions of the character image; while spatial correlation encodes the dependency between features of two positions. Feature correlation increases the dimensionality by over 40,000. DFE then reduces the dimensionality to less than 300 without losing discriminability. Classification is performed using nearest prototype classifier (NPC), modified quadratic discriminant function (MQDF) and discriminative learning quadratic discriminant function (DLQDF). In experiments on the CASIA-HWDB1.1 standard dataset, the proposed DQFL method improves the test accuracies of NPC, MQDF and DLQDF by 4.94%, 1.83%, and 1.82%, respectively. The test accuracy is further improved by training set expansion. On the ICDAR 2013 Chinese handwriting recognition competition dataset, the proposed DQFLA+DLQDF classifier outperforms the best participating system based on deep convolutional neural network (CNN), while the test speed is much faster. (C) 2015 Elsevier Ltd. All rights reserved.
KeywordHandwritten Chinese Character Recognition Discriminative Feature Learning Quadratic Correlation Dimensionality Promotion Training Set Expansion
WOS HeadingsScience & Technology ; Technology
DOI10.1016/j.patcog.2015.07.007
WOS KeywordFEATURE-EXTRACTION ; NUMERAL RECOGNITION ; BENCHMARKING ; DATABASES ; ONLINE ; LINE
Indexed BySCI
Language英语
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS IDWOS:000363077400001
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/10335
Collection模式识别国家重点实验室_模式分析与学习
Corresponding AuthorLiu, Cheng-Lin
AffiliationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Zhou, Ming-Ke,Zhang, Xu-Yao,Yin, Fei,et al. Discriminative quadratic feature learning for handwritten Chinese character recognition[J]. PATTERN RECOGNITION,2016,49(1):7-18.
APA Zhou, Ming-Ke,Zhang, Xu-Yao,Yin, Fei,&Liu, Cheng-Lin.(2016).Discriminative quadratic feature learning for handwritten Chinese character recognition.PATTERN RECOGNITION,49(1),7-18.
MLA Zhou, Ming-Ke,et al."Discriminative quadratic feature learning for handwritten Chinese character recognition".PATTERN RECOGNITION 49.1(2016):7-18.
Files in This Item: Download All
File Name/Size DocType Version Access License
MKZhou2016-PR.pdf(1397KB)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
[Zhou, Ming-Ke]'s Articles
[Zhang, Xu-Yao]'s Articles
[Yin, Fei]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhou, Ming-Ke]'s Articles
[Zhang, Xu-Yao]'s Articles
[Yin, Fei]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhou, Ming-Ke]'s Articles
[Zhang, Xu-Yao]'s Articles
[Yin, Fei]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: MKZhou2016-PR.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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