Cascaded face detection using neural network ensembles
EURASIP Journal on Advances in Signal Processing
Facial feature extraction by a cascade of model-based algorithms
Image Communication
"More Like This" or "Not for Me": Delivering Personalised Recommendations in Multi-user Environments
UM '07 Proceedings of the 11th international conference on User Modeling
IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
| Hi-index | 0.43 |
We propose a near real-time face recognition system for embedding in consumer applications. The system is embedded in a networked home environment and enables personalized services by automatic identification of users. The aim of our research is to design and build a face recognition system that is robust for natural consumer environments and can be executed on low-cost hardware. For enabling distribution of computations, we propose a processing pipeline for face recognition, which consists of (I) face detection by stepwise pruning; (2) coarse-to-fine facial feature extraction for face normalization; and (3) face identification by cascaded discriminant analysis. The system has been applied in varying environments, such as an experimental home network, and achieves over 95% recognition rate and 3-4 frames/s processing speed.