Deep neural network based hidden Markov model for offline handwritten Chinese text recognition
Authors:
- 1 December 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3428-3433
Abstract
This paper proposes a novel segmentation-free approach using deep neural network based hidden Markov model (DNN-HMM) for offline handwritten Chinese text recognition. In the general Bayesian framework, three key issues are comprehensively investigated, namely feature extraction, character modeling, and language modeling. First, as for the feature extraction on the basis of each frame or sliding window, the gradient-based features are extracted for the DNN-based classifier. Second, the text line is sequentially modeled by HMMs with each representing one character class. Meanwhile the DNN-based classifier is adopted to calculate the posterior probability of all HMM states. Finally, the character n-gram language model is integrated with the DNN-HMM character model for the Bayesian decision. The experiments on the ICDAR 2013 competition task of CASIA-HWDB database show that the proposed approach can achieve the best published recognition results to our knowledge, yielding a character error rate (CER) of 6.50%, which significantly outperforms the previously best reported oversegmentation approach (with a CER of 9.25%) and the segmentation-free approach using multidimensional long-short term memory recurrent neural network (MDLSTM-RNN) approach (with a CER of 10.6%).Keywords
This publication has 25 references indexed in Scilit:
- Off-line recognition of realistic Chinese handwriting using segmentation-free strategyPattern Recognition, 2009
- Forty years of research in character and document recognition—an industrial perspectivePattern Recognition, 2008
- OpenFst: A General and Efficient Weighted Finite-State Transducer Library2007
- Connectionist temporal classification2006
- Online recognition of chinese characters: the state-of-the-artIEEE Transactions on Pattern Analysis and Machine Intelligence, 2004
- Discriminative Learning Quadratic Discriminant Function for Handwriting RecognitionIEEE Transactions on Neural Networks, 2004
- Handwritten digit recognition: benchmarking of state-of-the-art techniquesPattern Recognition, 2003
- Weighted finite-state transducers in speech recognitionComputer Speech & Language, 2002
- Maximum likelihood estimation for multivariate mixture observations of markov chains (Corresp.)IEEE Transactions on Information Theory, 1986
- An inequality with applications to statistical estimation for probabilistic functions of Markov processes and to a model for ecologyBulletin of the American Mathematical Society, 1967