Ligature Modeling for Online Cursive Script Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
Introduction to Bayesian Networks
Introduction to Bayesian Networks
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
Inference and Learning in Hybrid Bayesian Networks
Inference and Learning in Hybrid Bayesian Networks
Generation of Handwritten Characters with Bayesian network based On-line Handwriting Recognizers
ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 2
Learning Diagram Parts with Hidden Random Fields
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Recognition of degraded characters using dynamic Bayesian networks
Pattern Recognition
Recent results of online Japanese handwriting recognition and its applications
SACH'06 Proceedings of the 2006 conference on Arabic and Chinese handwriting recognition
Online composite sketchy shape recognition based on bayesian networks
ICNC'06 Proceedings of the Second international conference on Advances in Natural Computation - Volume Part II
GbRPR'05 Proceedings of the 5th IAPR international conference on Graph-Based Representations in Pattern Recognition
Hi-index | 0.00 |
In this paper, we propose a Bayesian network frameworkfor explicitly modeling components and their relationshipsof Korean Hangul characters. A Hangul character ismodeled with hierarchical components: a syllable model,grapheme models, stroke models and point models. Eachmodel is constructed with subcomponents and their relationshipsexcept a point model, the primitive one, which isrepresented by a 2-D Gaussian for X-Y coordinates of pointinstances. Relationships between components are modeledwith their positional dependencies. For on-line handwrittenHangul characters, the proposed system shows higherrecognition rates than the HMMsystem with chain code features:95.7% vs 92.9% on average.