| Hi-index | 0.00 |
We've been investigating how to use Gaussian mixture continuous-density hidden Markov models (CDHMMs) for handwritten Chinese character modeling and recognition. We've identified and developed a set of techniques that can be used to construct a practical CDHMM-based offline recognition system for a large vocabulary of handwritten Chinese characters. We have reported elsewhere the key techniques that contribute to the high recognition accuracy. In this paper, we describe how to make our recognizer compactwithout sacrificing too much of the recognition accuracy. We also report the results of a series of experiments that were performed to help us make a good decision when we face several design choices.