Abstract | ||
---|---|---|
In this paper, we propose a large vocabulary Mongolian offline handwriting recognition system, using hidden Markov models (HMMs)-deep neural networks (DNN) hybrid architectures which shows superior performance on auto speech recognize (ASR) tasks. We select 50 sub-characters from all shape of Mongolian letters as the smallest modeling unit. First, a set of intensity features are extracted from each of the segmented word, which is based on a sliding window moving across each word image. Then, Multiple contextdependent Gaussian mixture model (GMM)-HMMs are trained by the features. At last a DNN which have 4 hidden layers are trained as a frame classifier, where the class labels are state labels assigned to each input frame through forced alignment using the context-dependent model. In order to validate the proposed model, extensive experiments were carried out using the MHW database which contains 100,000 handwritten words in training set, 5,000 in test set I and 14,085 in Test set II. The DNN-HMM w hich is trained on raw image pixels yields best performance on Test set I with an accuracy of 97.61% and on Test set II with an accuracy of 94.14%. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1109/ICFHR.2016.0026 | 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR) |
Keywords | Field | DocType |
Mongolian,Handwriting Recognition,HMM,DNN | Computer science,Handwriting recognition,Artificial intelligence,Classifier (linguistics),Artificial neural network,Pattern recognition,Speech recognition,Feature extraction,Hidden Markov model,Vocabulary,Mixture model,Machine learning,Test set | Conference |
ISSN | ISBN | Citations |
2167-6445 | 978-1-5090-0982-4 | 0 |
PageRank | References | Authors |
0.34 | 9 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Fan Daoerji | 1 | 0 | 1.35 |
Guanglai Gao | 2 | 78 | 24.57 |