Please use this identifier to cite or link to this item: https://doi.org/10.1109/AFGR.2008.4813464
Title: Tracking facial features under occlusions and recognizing facial expressions in sign language
Authors: Nguyen, T.D.
Ranganath, S. 
Issue Date: 2008
Source: Nguyen, T.D.,Ranganath, S. (2008). Tracking facial features under occlusions and recognizing facial expressions in sign language. 2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008 : -. ScholarBank@NUS Repository. https://doi.org/10.1109/AFGR.2008.4813464
Abstract: This paper presents work towards recognizing facial expressions that are used in sign language recognition. Facial features are tracked to effectively capture temporal visual cues on the signer's face during signing. A Bayesian framework is proposed as a feedback mechanism to the Kanade- Lucas-Tomasi (KLT) tracker for reliably tracking facial features in the presence of head motions and temporary occlusions by hand. This mechanism relies on a set of face shape subspaces learned by Probabilistic Principal Component Analysis with an update scheme to adapt to persons withdifferent face shapes. The results show that the proposed tracker can track facial features with large head motions, substantial facial deformations, and temporary facial occlusions by hand. The tracked results were input to a recognition system comprising HMMs and a NN to recognize four common American Sign Language facial expressions. © 2008 IE.
Source Title: 2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008
URI: http://scholarbank.nus.edu.sg/handle/10635/72066
ISBN: 9781424421541
DOI: 10.1109/AFGR.2008.4813464
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

12
checked on Dec 18, 2017

Page view(s)

20
checked on Dec 16, 2017

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.