Abstract
This paper is concerned with the problem of improving recognition accuracy of hidden Markov models (HMM) for sequential pattern recognition. It is argued that maximum-likelihood estimation of the HMM parameters via the forward-backward algorithm may not lead to values which maximize recognition accuracy. We introduce a hybrid method with neural network postprocessor which is aimed at minimizing the number of recognition errors. This method exploits the discrimination capability of neural network classifier while using HMM formalism to capture the dynamics of input patterns. Although it has not been proved that the presented method is a kind of maximum mutual information estimation, experimental results with on-line handwriting characters suggest that it leads to fewer recognition errors than can be obtained with the conventional recognition method.
Original language | English |
---|---|
Pages | 2881-2884 |
Number of pages | 4 |
Publication status | Published - 1994 |
Event | Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7) - Orlando, FL, USA Duration: 1994 Jun 27 → 1994 Jun 29 |
Other
Other | Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7) |
---|---|
City | Orlando, FL, USA |
Period | 94/6/27 → 94/6/29 |
All Science Journal Classification (ASJC) codes
- Software