Name
Title | ||
|---|---|---|
A Component-Based On-Line Handwritten Tibetan Character Recognition Method Using Conditional Random Field |
Abstract | ||
|---|---|---|
This paper presents a new component-based recognition method using conditional random field (CRF) for on-line handwritten Tibetan characters. The character pattern is over-segmented into a sequence of sub-structure blocks. Integrated segmentation and recognition method based on the CRF model is used to determine the component segmentation points from these block sequences. The CRF model combines component shape likelihood with geometrical likelihood. The parameters are learned using an energy minimization method. We build a component-based spelling rule model to ensure the correct component appearing at a specific structural position. A character-component generation model is presented to reduce component recognition error rate and accelerate the recognition process. Experimental results on MRG-OHTC database show that the proposed method gives promising performance comparing with the holistic method and the component-based conventional path evaluation method. |
Year | DOI | Venue |
|---|---|---|
2012 | 10.1109/ICFHR.2012.153 | ICFHR |
Keywords | Field | DocType |
block sequence,shape recognition,crf model,component segmentation point,energy minimization method,component shape likelihood,random processes,component-based on-line handwritten tibetan character recognition,image segmentation,mrg-ohtc database,recognition process,recognition method,component-based conventional path evaluation method,conditional random field,new component-based recognition method,geometrical likelihood,image sequences,component-based on-line handwritten tibetan,character-component generation model,handwritten character recognition,holistic method,character recognition method,natural language processing,component segmentation points,component-based spelling rule model,component recognition error rate,character pattern,geometry | Conditional random field,Pattern recognition,Computer science,Segmentation,Word error rate,Stochastic process,Image segmentation,Spelling rule,Artificial intelligence,Machine learning,Intelligent word recognition,Energy minimization | Conference |
ISSN | ISBN | Citations |
2167-6445 | 978-1-4673-2262-1 | 2 |
PageRank | References | Authors |
0.41 | 6 | 2 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Long-long Ma | 1 | 26 | 5.72 |
| Wu Jian | 2 | 23 | 2.93 |