Bayesian Network Modeling of Strokes and their Relationships for On-line Handwriting Recognition
ICDAR '01 Proceedings of the Sixth International Conference on Document Analysis and Recognition
GbRPR'05 Proceedings of the 5th IAPR international conference on Graph-Based Representations in Pattern Recognition
| Hi-index | 0.00 |
In structural character recognition, a character is usuallyviewed as a set of strokes and the spatial relationshipsbetween them. In this paper, we propose a stochastic modelingscheme by which strokes as well as relationships arerepresented by utilizing the hierarchical characteristics oftarget characters. Based on the proposed scheme, a handwrittenHangul (Korean) character recognition system isdeveloped. The effectiveness of the proposed scheme isshown through experimental results conducted on a publicdatabase.