Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns
IEEE Transactions on Pattern Analysis and Machine Intelligence
Face recognition: A literature survey
ACM Computing Surveys (CSUR)
Robust Real-Time Face Detection
International Journal of Computer Vision
Introduction to Data Mining, (First Edition)
Introduction to Data Mining, (First Edition)
3D Facial Model Synthesis using Voronoi Approach
ISVD '06 Proceedings of the 3rd International Symposium on Voronoi Diagrams in Science and Engineering
GMM-based SVM for face recognition
ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 03
Face Description with Local Binary Patterns: Application to Face Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
Journal of Cognitive Neuroscience
Enhanced local texture feature sets for face recognition under difficult lighting conditions
IEEE Transactions on Image Processing
On the results of the first mobile biometry (MOBIO) face and speaker verification evaluation
ICPR'10 Proceedings of the 20th International conference on Recognizing patterns in signals, speech, images, and videos
Face verification using adapted generative models
FGR' 04 Proceedings of the Sixth IEEE international conference on Automatic face and gesture recognition
Handbook of Face Recognition
Face authentication using adapted local binary pattern histograms
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part IV
| Hi-index | 0.00 |
The classification task has a relevant importance in face verification systems and there are many approaches proposed to solve it. This paper shows a new approach for the classification task in video-based face verification systems using Support Vector Machines (SVM) as classifier and Gaussian Mixture Models (GMM) working as its kernel. The use of Local Binary Patterns (LBP) for face description, in conjunction with the generation of Gaussian supervectors as input points for the classifier, describes the temporal information contained in a video by a unique feature point, which seems to be a very compact and powerful form of representation. Our experimental results, performed on MOBIO database and protocol, shows the advantages of the proposed technique.