SUPPORT VECTOR MACHINES, PCA AND LDA IN FACE RECOGNITION

Ján Mazanec - Martin Melišek - Miloš Oravec - Jarmila Pavlovičová

   In this paper, we consider the human face be biometric. We present the results of different statistical algorithms used for face recognition, namely PCA (Principal Component Analysis), LDA (Linear Discriminant Analysis) and SVM (Support Vector Machines). Pre-processed (normalization of size, unified position and rotation, contrast optimization and face masking) image sets from the FERET database are used for experiments. We take advantage of csuFaceIdEval and libsvm software that implement the mentioned algorithms. We also propose a combination of PCA and LDA methods with SVM which produces interesting results from the point of view of recognition success, rate, and robustness of the face recognition algorithm. We use different classifiers to match the image of a person to a class (a subject) obtained from the training data. These classifiers are in the form of both simple metrics (Mahalinobis cosine, LdaSoft) and more complex support vector machines. We present the results of face recognition of all these methods. We also propose the best settings in order to maximize the face recognition success rate.

Keywords: biometrics, face recognition, principal component analysis, linear discriminant analysis, support vector machines

[full-paper]