ISCAS OpenIR
Minimum Risk Training for Handwritten Chinese/Japanese Text Recognition Using Semi-Markov Conditional Random Fields
Zhou, Xiang-Dong; Tian, Feng; Liu, Cheng-Lin; Wang, Hong-An
2013
Conference Name12th International Conference on Document Analysis and Recognition (ICDAR)
Pages940-944
Conference DateAUG 25-28, 2013
Conference PlaceWashington, DC
Indexed TypeCPCI
Publish PlaceIEEE
ISSN1520-5363
Department[Zhou, Xiang-Dong; Tian, Feng; Wang, Hong-An] Chinese Acad Sci, Beijing Key Lab Human Comp Interact, Inst Software, Beijing 100190, Peoples R China.
English AbstractSemi-Markov conditional random fields (semi-CRFs) are usually trained with maximum a posteriori (MAP) criterion which adopts the 0/1 cost for measuring the loss of misclassification. In this paper, based on our previous work on handwritten Chinese/Japanese text recognition (HCTR) using semi-CRFs, we propose an alternative parameter learning method by minimizing the risk, in which the misclassification costs are not equal, but different depending on the hypothesis and the ground-truth. The proposed method is lattice-based, i.e., the hypothesis space is the entire lattice on which the semi-CRF is defined. Experimental results on two online handwriting databases: CASIA-OLHWDB and TUAT Kondate demonstrate that minimum-risk training can yield superior string recognition rates compared to MAP training.; Semi-Markov conditional random fields (semi-CRFs) are usually trained with maximum a posteriori (MAP) criterion which adopts the 0/1 cost for measuring the loss of misclassification. In this paper, based on our previous work on handwritten Chinese/Japanese text recognition (HCTR) using semi-CRFs, we propose an alternative parameter learning method by minimizing the risk, in which the misclassification costs are not equal, but different depending on the hypothesis and the ground-truth. The proposed method is lattice-based, i.e., the hypothesis space is the entire lattice on which the semi-CRF is defined. Experimental results on two online handwriting databases: CASIA-OLHWDB and TUAT Kondate demonstrate that minimum-risk training can yield superior string recognition rates compared to MAP training.
Language英语
Content Type会议论文
URIhttp://ir.iscas.ac.cn/handle/311060/16509
Collection中国科学院软件研究所
Recommended Citation
GB/T 7714
Zhou, Xiang-Dong,Tian, Feng,Liu, Cheng-Lin,et al. Minimum Risk Training for Handwritten Chinese/Japanese Text Recognition Using Semi-Markov Conditional Random Fields[C]. IEEE,2013:940-944.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhou, Xiang-Dong]'s Articles
[Tian, Feng]'s Articles
[Liu, Cheng-Lin]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhou, Xiang-Dong]'s Articles
[Tian, Feng]'s Articles
[Liu, Cheng-Lin]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhou, Xiang-Dong]'s Articles
[Tian, Feng]'s Articles
[Liu, Cheng-Lin]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

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