DMCA
A Comparison of Active Shape Model and Scale Decomposition Based Features for Visual Speech Recognition (1998)
Cached
Download Links
- [ftp.sys.uea.ac.uk]
- [www.cs.cmu.edu]
- [www.iainm.com]
- DBLP
Other Repositories/Bibliography
| Venue: | In European Conference on Computer Vision |
| Citations: | 13 - 8 self |
BibTeX
@INPROCEEDINGS{Matthews98acomparison,
author = {Iain Matthews and J. Andrew Bangham and Richard Harvey and Stephen Cox},
title = {A Comparison of Active Shape Model and Scale Decomposition Based Features for Visual Speech Recognition},
booktitle = {In European Conference on Computer Vision},
year = {1998},
pages = {514--528},
publisher = {Springer-Verlag}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Two quite different strategies for characterising mouth shapes for visual speech recognition (lipreading) are compared. The first strategy extracts the parameters required to fit an active shape model (ASM) to the outline of the lips. The second uses a feature derived from a one-dimensional multiscale spatial analysis (MSA) of the mouth region using a new processor derived from mathematical morphology and median filtering. With multispeaker trials, using image data only, the accuracy is 45% using MSA and 19% using ASM on a letters database. A digits database is simpler with accuracies of 77% and 77% respectively. These scores are significant since separate work has demonstrated that even quite low recognition accuracies in the vision channel can be combined with the audio system to give improved composite performance [16].
Keyphrases
active shape model visual speech recognition scale decomposition digit database mathematical morphology separate work mouth shape new processor audio system mouth region one-dimensional multiscale spatial analysis image data letter database improved composite performance low recognition accuracy multispeaker trial median filtering quite different strategy first strategy vision channel
