A decision-theoretic generalization of on-line learning and an application to boosting
Journal of Computer and System Sciences - Special issue: 26th annual ACM symposium on the theory of computing & STOC'94, May 23–25, 1994, and second annual Europe an conference on computational learning theory (EuroCOLT'95), March 13–15, 1995
Appearance-based hand sign recognition from intensity image sequences
Computer Vision and Image Understanding
FGR '02 Proceedings of the Fifth IEEE International Conference on Automatic Face and Gesture Recognition
Gesture Recognition via Pose Classification
ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 3
Recognition of Local Features for Camera-Based Sign Language Recognition System
ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 4
Nonstationary color tracking for vision-based human-computer interaction
IEEE Transactions on Neural Networks
Hi-index | 0.00 |
Digital signage is a very attractive medium for advertisement and general communications in public open spaces. In order to add interaction capabilities to digital signage displays, special considerations must be taken. For example, the signs' environment and placement might prevent direct access to conventional means of interaction, such as using a keyboard or a touch-sensitive screen. This paper describes a vision-based gesture recognition approach to interact with digital signage systems and discusses the issues faced by such systems. Using Haar-like features and the AdaBoosting algorithm, a set of hand gestures can be recognized in real-time and converted to gesture commands to control and manipulate the digital signage display. A demonstrative application using this gesture recognition interface is also depicted.