Minimum-risk training for semi-Markov conditional random fields with application to handwritten Chinese/Japanese text recognition |
| |
Authors: | Xiang-Dong Zhou Yan-Ming Zhang Feng Tian Hong-An Wang Cheng-Lin Liu |
| |
Affiliation: | 1. Intelligent Media Technique Research Center, Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing 400714, PR China;2. National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, 95 Zhongguan East Road, Beijing 100190, PR China;3. Beijing Key Lab of Human–Computer Interaction, Institute of Software, Chinese Academy of Sciences, Beijing 100190, PR China |
| |
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 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. |
| |
Keywords: | Semi-Markov conditional random fields Minimum-risk training Character string recognition |
本文献已被 ScienceDirect 等数据库收录! |
|