Improving adaptive skin color segmentation by incorporating results from face detection
Authors:
- G. SagererGSG. Sagerer
- 25 June 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 337-343
Abstract
The visual tracking of human faces is a basic function- ality needed for human-machine interfaces. This paper describes an approach that explores the combined use of adaptive skin color segmentation and face detection for im- proved face tracking on a mobile robot. To cope with inho- mogeneous lighting within a single image the color of each tracked image region is modeled with an individual, uni- modal Gaussian. Face detection is performed locally on all segmented skin-colored regions. If a face is detected, the appropriate color model is updated with the image pix- els in an elliptical area around the face position. Updating is restricted to pixels that are contained in a global skin color distribution obtained off-line. The presented method allows to track faces that undergo changes in lighting con- ditions while at the same time it provides information about the attention of the user, i.e. whether the user looks at the robot. This forms the basis for developing more sophisti- cated human-machine interfaces capable of dealing with unrestricted environments.Keywords
This publication has 27 references indexed in Scilit:
- A real-time face tracker2002
- Skin detection in video under changing illumination conditions2002
- A Multimodal System for Object Learning2002
- LAFTER: a real-time face and lips tracker with facial expression recognitionPattern Recognition, 2000
- Neural network-based face detectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998
- Is machine colour constancy good enough?1998
- Pfinder: real-time tracking of the human bodyIEEE Transactions on Pattern Analysis and Machine Intelligence, 1997
- Skin-color modeling and adaptation1997
- Feature extraction from faces using deformable templatesInternational Journal of Computer Vision, 1992
- Eigenfaces for RecognitionJournal of Cognitive Neuroscience, 1991