Abstract
An approach for segmentation and recognition of on-line vocalized outlines of Pitman shorthand is presented. The approach is to use a trained neural network for the segmentation of the vocalized outlines for the detection of over-segmentation; and to use another trained neural network for the recognition of Pitman shorthand consonant signs; while the word recognition was based on the estimation of the overall confidence on the stroke classification. Experimental results on a test set containing 68 most frequently used English words showed that on average, the approach can achieve an accuracy rate of 89.6%.
Original language | English |
---|---|
Pages (from-to) | 532-536+550 |
Journal | Zhejiang Daxue Xuebao (Gongxue Ban)/Journal of Zhejiang University (Engineering Science) |
Volume | 37 |
Issue number | 5 |
Publication status | Published - 1 Sept 2003 |
Externally published | Yes |
Keywords
- Handwriting recognition
- Neural networks
- Shorthand
ASJC Scopus subject areas
- Engineering(all)