Institutional Repository
| 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 Name | 12th International Conference on Document Analysis and Recognition (ICDAR) |
| Pages | 940-944 |
| Conference Date | AUG 25-28, 2013 |
| Conference Place | Washington, DC |
| Indexed Type | CPCI |
| Publish Place | IEEE |
| ISSN | 1520-5363 |
| 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 Abstract | 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.; 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 |
| URI | http://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. | |||||
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment