Liwicki, S. and Everingham, M. (2009) Automatic recognition of fingerspelled words in British Sign Language. In: Proceedings of CVPR4HB'09. 2nd IEEE Workshop on CVPR for Human Communicative Behavior Analysis, Thursday June 25th, 2009, Miami, Florida. , pp. 50-57.
Full text available as:![[img]](http://eprints.whiterose.ac.uk/style/images/fileicons/text.png)
|
Text
mark_everingham_2.pdf Available under License : See the attached licence file. Download (1149Kb) |
Abstract
We investigate the problem of recognizing words from video, fingerspelled using the British Sign Language (BSL) fingerspelling alphabet. This is a challenging task since the BSL alphabet involves both hands occluding each other, and contains signs which are ambiguous from the observer’s viewpoint. The main contributions of our work include: (i) recognition based on hand shape alone, not requiring motion cues; (ii) robust visual features for hand shape recognition; (iii) scalability to large lexicon recognition with no re-training. We report results on a dataset of 1,000 low quality webcam videos of 100 words. The proposed method achieves a word recognition accuracy of 98.9%.
| Item Type: | Proceedings Paper |
|---|---|
| Academic Units: | The University of Leeds > Faculty of Engineering (Leeds) > School of Computing (Leeds) |
| Depositing User: | Miss Jamie Grant |
| Date Deposited: | 07 Jul 2009 11:35 |
| Last Modified: | 08 Feb 2013 17:06 |
| Status: | Published |
| URI: | http://eprints.whiterose.ac.uk/id/eprint/8903 |
Actions (login required)
 |
View Item |
