A Temporal Network of Support Vector Machine Classifiers for the Recognition of Visual Speech
SETN '02 Proceedings of the Second Hellenic Conference on AI: Methods and Applications of Artificial Intelligence
Applications of Support Vector Machines for Pattern Recognition: A Survey
SVM '02 Proceedings of the First International Workshop on Pattern Recognition with Support Vector Machines
A support vector machine-based dynamic network for visual speech recognition applications
EURASIP Journal on Applied Signal Processing
Face detection using a first-order RCE classifier
EURASIP Journal on Applied Signal Processing
On the performance of kernel methods for skin color segmentation
EURASIP Journal on Advances in Signal Processing
Face detection using kernel PCA and imbalanced SVM
ICNC'06 Proceedings of the Second international conference on Advances in Natural Computation - Volume Part I
Detecting Facial Expressions for Monitoring Patterns of Emotional Behavior
International Journal of Monitoring and Surveillance Technologies Research
Hi-index | 0.00 |
This paper presents an analysis of the performance of Support Vector Machines (SVMs) for the automatic detection of human faces in static color images of complex scenes. SVMs are a new interesting type of binary classifier based on a novel statistical learning technique that has been developed in recent years by V. Vapnik et al. at AT&T Bell Labs [2] [4] [6] [22]. Skin color-based image segmentation is initially performed for several different chrominance spaces by use of the single Gaussian chrominance model and of a Gaussian mixture density model, as described in [17]. Feature extraction in the segmented images is then implemented by use of invariant Orthogonal Fourier-Mellin Moments (OFMMs) [16] [20]. For all chrominance spaces, the application of SVMs to the invariant moments obtained from a set of 100 test images yields a higher face detection performance than when applying a 3-layer perceptron Neural Network (NN), depending on a suitable selection of the kernel function used to train the SVM and of the value of its associated parameter(s). The training of SVMs is easier and faster than that of a NN, always finds a global minimum, and SVMs have a better generalization ability [5].