초록
영어
A novel printed Chinese character recognition method based on Degraded Hidden Markov Model
is proposed in this paper, which can be applied to engineering. We extract one‐dimensional
strokes sequence as the feature of the character under some rules and then take it as the input of
the classifier we designed. As for the design of the classifier, we adopt the ergodic model instead
of the traditional left‐right model, the performance of the classifier is proved by our experiment, and the recognition rate under out method is less affected by font.
목차
Abstract
1. Introduction
2. Feature Extract
3. Design of Classifier
3.1 Describing the model
3.2 Training HMM model
4. Experiment and Discussion
5. Conclusion
References
1. Introduction
2. Feature Extract
3. Design of Classifier
3.1 Describing the model
3.2 Training HMM model
4. Experiment and Discussion
5. Conclusion
References
저자정보
참고문헌
자료제공 : 네이버학술정보