Print keyword spotting with dynamically synthesized pseudo 2D HMMs
We propose a new method of dynamically synthesizing Korean character image templates and then converting them into P2DHMMs in real-time. This method is more advantageous than whole character HMMs in memory requirement as well as training difficulty. (C) 2004 Elsevier B.V. All rights reserved.
- Publisher
- ELSEVIER SCIENCE BV
- Issue Date
- 2004-07
- Language
- English
- Article Type
- Article
- Keywords
HIDDEN MARKOV-MODELS; WORD RECOGNITION
- Citation
PATTERN RECOGNITION LETTERS, v.25, no.9, pp.999 - 1011
- ISSN
- 0167-8655
- Appears in Collection
- CS-Journal Papers(저널논문)
- Files in This Item
This item is cited by other documents in WoS
| ⊙ Detail Information in WoSⓡ | Click to see |  |
| ⊙ Cited 3 items in WoS | Click to see citing articles in |  |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.