Minimum-risk training for semi-Markov conditional random fields with application to handwritten Chinese/Japanese text recognition | |
Zhou, Xiang-Dong (1) ; Zhang, Yan-Ming (2) ; Tian, Feng (3) ; Wang, Hong-An (3) ; Liu, Cheng-Lin (2) | |
刊名 | Pattern Recognition |
2014 | |
卷号 | 47期号:5页码:1904-1916 |
关键词 | Semi-Markov conditional random fields Minimum-risk training Character string recognition |
ISSN号 | 313203 |
通讯作者 | Zhou, X.-D.(zhouxiangdong@cigit.ac.cn) |
中文摘要 | 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 on the training set, which has unequal misclassification costs depending on the hypothesis and the ground-truth. Based on this framework, three non-uniform cost functions are compared with the conventional 0/1 cost, and training data selection is incorporated to reduce the computational complexity. In experiments of online handwriting recognition on databases CASIA-OLHWDB and TUAT Kondate, we compared the performances of the proposed method with several widely used learning criteria, including conditional log-likelihood (CLL), softmax-margin (SMM), minimum classification error (MCE), large-margin MCE (LM-MCE) and max-margin (MM). On the test set (online handwritten texts) of ICDAR 2011 Chinese handwriting recognition competition, the proposed method outperforms the best system in competition. © 2013 Elsevier Ltd. All rights reserved. |
英文摘要 | 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 on the training set, which has unequal misclassification costs depending on the hypothesis and the ground-truth. Based on this framework, three non-uniform cost functions are compared with the conventional 0/1 cost, and training data selection is incorporated to reduce the computational complexity. In experiments of online handwriting recognition on databases CASIA-OLHWDB and TUAT Kondate, we compared the performances of the proposed method with several widely used learning criteria, including conditional log-likelihood (CLL), softmax-margin (SMM), minimum classification error (MCE), large-margin MCE (LM-MCE) and max-margin (MM). On the test set (online handwritten texts) of ICDAR 2011 Chinese handwriting recognition competition, the proposed method outperforms the best system in competition. © 2013 Elsevier Ltd. All rights reserved. |
收录类别 | SCI ; EI |
语种 | 英语 |
WOS记录号 | WOS:000331667400011 |
公开日期 | 2014-12-16 |
内容类型 | 期刊论文 |
源URL | [http://ir.iscas.ac.cn/handle/311060/16721] |
专题 | 软件研究所_软件所图书馆_期刊论文 |
推荐引用方式 GB/T 7714 | Zhou, Xiang-Dong ,Zhang, Yan-Ming ,Tian, Feng ,et al. Minimum-risk training for semi-Markov conditional random fields with application to handwritten Chinese/Japanese text recognition[J]. Pattern Recognition,2014,47(5):1904-1916. |
APA | Zhou, Xiang-Dong ,Zhang, Yan-Ming ,Tian, Feng ,Wang, Hong-An ,&Liu, Cheng-Lin .(2014).Minimum-risk training for semi-Markov conditional random fields with application to handwritten Chinese/Japanese text recognition.Pattern Recognition,47(5),1904-1916. |
MLA | Zhou, Xiang-Dong ,et al."Minimum-risk training for semi-Markov conditional random fields with application to handwritten Chinese/Japanese text recognition".Pattern Recognition 47.5(2014):1904-1916. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论