Unsupervised language model adaptation for handwritten Chinese text recognition
Pattern Recognition
| Hi-index | 0.00 |
In this paper, we propose a hybrid language model for handwritten Chinese sentence recognition. This hybrid model is integrated from several independent language models, each of which is trained from a distinct type of corpus and models specifically the linguistic behavior for that type of corpus. By inferring the type of the string which the user has already written, we can make this hybrid language model contribute more precisely to the recognition engine. Our experiments show that the hybrid language model performs consistently well among different types of handwritten articles, and the overall performance is significantly better than a single standard language model. We also propose a candidate re-ranking process after recognition by reducing the language scores to improve the recognition accuracy. The experiment result also demonstrates that this re-ranking process effectively improves the performance of the recognition engine in terms of accuracy.