Abstract
Yawn is one of the common fatigue sign phenomena. The common technique to detect yawn is based upon the measurement of mouth opening. However, the spontaneous human action to cover the mouth during yawn can prevent such measurements. This paper presents a new technique to detect the covered mouth by employing the Local Binary Pattern (LBP) features. Subsequently, the facial distortions during the yawn process are identified by measuring the changes of wrinkles using Sobel edges detector. In this research the Strathclyde Facial Fatigue (SFF) database that contains genuine fatigue signs is used for training, testing and evaluation of the developed algorithms. This database was created from sleep deprivation experiments that involved twenty participants.
Original language | English |
---|---|
Title of host publication | 2013 IEEE International Conference on Signal and Image Processing Applications (ICSIPA) |
Publisher | IEEE |
Pages | 89-94 |
Number of pages | 4 |
ISBN (Print) | 9781479902675 |
DOIs | |
Publication status | Published - 10 Oct 2013 |
Event | 2013 IEEE International Conference on Signal and Image Processing Applications (ICSIPA) - Meloka, Malaysia Duration: 8 Oct 2013 → 10 Oct 2013 |
Conference
Conference | 2013 IEEE International Conference on Signal and Image Processing Applications (ICSIPA) |
---|---|
Country/Territory | Malaysia |
City | Meloka |
Period | 8/10/13 → 10/10/13 |
Keywords
- face recognition
- sleep
- edge detection
- artificial neural networks
- distortion measurement
- LBP features
- SFF database
- sobel edge detector