A Framework for Classifier Fusion: Is It Still Needed?
Proceedings of the Joint IAPR International Workshops on Advances in Pattern Recognition
Face Recognition Using Support Vector Machines with the Feature Set Extracted by Genetic Algorithms
AVBPA '01 Proceedings of the Third International Conference on Audio- and Video-Based Biometric Person Authentication
SVM '02 Proceedings of the First International Workshop on Pattern Recognition with Support Vector Machines
Face recognition: component-based versus global approaches
Computer Vision and Image Understanding - Special issue on Face recognition
N-division output coding method applied to face recognition
Pattern Recognition Letters
Fast and accurate holistic face recognition using optimum-path forest
DSP'09 Proceedings of the 16th international conference on Digital Signal Processing
ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part I
Semantic awareness through computer vision
Proceedings of the 2nd ACM SIGCHI symposium on Engineering interactive computing systems
Supervised relevance maps for increasing the distinctiveness of facial images
Pattern Recognition
A symmetric transformation for LDA-based face verification
FGR' 04 Proceedings of the Sixth IEEE international conference on Automatic face and gesture recognition
Empirical remarks on output coding methods for face recognition
FGR' 04 Proceedings of the Sixth IEEE international conference on Automatic face and gesture recognition
Face authentication using adapted local binary pattern histograms
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part IV
Information fusion for local gabor features based frontal face verification
ICB'06 Proceedings of the 2006 international conference on Advances in Biometrics
Automatic face recognition by support vector machines
IWCIA'04 Proceedings of the 10th international conference on Combinatorial Image Analysis
Hi-index | 0.00 |
The paper studies Support Vector Machines (SVMs) in the context of face verification and recognition. Our study supports the hypothesis that the SVM approach is able to extract the relevant discriminatory information from the training data and we present results showing superior performance in comparison with benchmark methods. However, when the representation space already captures and emphasizes the discriminatory information (e.g. Fisher's linear discriminant), SVMs loose their superiority. The results also indicate that the SVMs are robust against changes in illumination provided these are adequately represented in the training data. The proposed system is evaluated on a large database of 295 people obtaining highly competitive results: an equal error rate of 1% for verification and a rank-one error rate of 2% for recognition (or 98% correct rank-one recognition).