Back to Search
Start Over
Minimum-risk training for semi-Markov conditional random fields with application to handwritten Chinese/Japanese text recognition.
- Source :
-
Pattern Recognition . May2014, Vol. 47 Issue 5, p1904-1916. 13p. - Publication Year :
- 2014
-
Abstract
- 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. [Copyright &y& Elsevier]
Details
- Language :
- English
- ISSN :
- 00313203
- Volume :
- 47
- Issue :
- 5
- Database :
- Academic Search Index
- Journal :
- Pattern Recognition
- Publication Type :
- Academic Journal
- Accession number :
- 94024310
- Full Text :
- https://doi.org/10.1016/j.patcog.2013.12.002