Feature extraction from faces using deformable templates
International Journal of Computer Vision
Speechreading using probabilistic models
Computer Vision and Image Understanding - Special issue on physics-based modeling and reasoning in computer vision
Extraction of Visual Features for Lipreading
IEEE Transactions on Pattern Analysis and Machine Intelligence
Avoiding Replay-Attacks in a Face Recognition Systenm using Head-Pose Estimation
AMFG '03 Proceedings of the IEEE International Workshop on Analysis and Modeling of Faces and Gestures
Robust Real-Time Face Detection
International Journal of Computer Vision
Integrating audio and visual information to provide highly robust speech recognition
ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 02
Audio-visual speech recognition using MPEG-4 compliant visual features
EURASIP Journal on Applied Signal Processing
Synergy of Lip-Motion and Acoustic Features in Biometric Speech and Speaker Recognition
IEEE Transactions on Computers
Lip-reading with discriminative deformable models
Machine Graphics & Vision International Journal
Editorial: Hybrid intelligent algorithms and applications
Information Sciences: an International Journal
Audio-visual speech modeling for continuous speech recognition
IEEE Transactions on Multimedia
IEEE Transactions on Image Processing
Recognition of visual speech elements using adaptively boosted hidden Markov models
IEEE Transactions on Circuits and Systems for Video Technology
Hi-index | 0.00 |
The following paper proposes a novel procedure for liveness verification in video authentication systems. Decision on granting or denying access to the system is based on visual information only. System prompts random sequences of predefined syllables in which isolated visems are to be recognized. Features that represent outer lip contour are extracted on the basis of dynamic programming and B-spline approximation. Experiments for Polish language utterances show that seven classes of visems can be recognized with 76% of efficiency. Average false acceptance rate for liveness does not exceeds 9% and false rejection rate 7%.