Thesis (MScEng (Electrical and Electronic Engineering))--University of Stellenbosch, 2007. / In this thesis we present a human-computer interface (HCI) system for disabled
persons using only a basic web camera. Mouse movements are simulated
by small movements of the head, while clicks are simulated by eye
blinks. In this study, a system capable of face tracking, eye detection (including
iris detection), blink detection and finally skin detection and face
recognition has been developed. A detection method based on Haar-like features
are used to detect the face and eyes. Once the eyes have been detected,
a support vector machines classifier is used to detect whether the eye is open
or closed (for use in blink detection).
Skin detection is done using K-means clustering, while Eigenfaces is used
for face recognition.
It is concluded that using a web camera as a human-computer interface
can be a viable input method for the severely disabled.
| Identifer | oai:union.ndltd.org:netd.ac.za/oai:union.ndltd.org:sun/oai:scholar.sun.ac.za:10019.1/1988 |
| Date | 12 1900 |
| Creators | Ellis, Loftie |
| Contributors | Herbst, B. M., Du Preez, J. A., University of Stellenbosch. Faculty of Engineering. Dept. of Electrical and Electronic Engineering. |
| Publisher | Stellenbosch : University of Stellenbosch |
| Source Sets | South African National ETD Portal |
| Language | English |
| Detected Language | English |
| Type | Thesis |
| Format | 3059400 bytes, application/pdf |
| Rights | University of Stellenbosch |
Page generated in 0.0015 seconds