Bag of face recognition systems based on holistic approaches

This paper presents a comprehensive experimental study on face recognition to prove that holistic approaches are more robust than geometric and local approaches in order to address the problem of which method holistic or geometric can assist to face recognition. This work is done based on the motivation to integrate soft biometric traits into face recognition systems using same computing. A bag of features extraction and classification combined with each other to find the most appropriate technique that can enhance face recognition task. The experimental study shows that the texture information is discriminant in facial images representation, Gabor filter is more useful than Local Binary Pattern, a space dimensionality reduction using Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) is very interesting to increase recognition rates. The fusion between Gabor, PCA or LDA and Multi class Support Vector Machines (SVM) ranks top the list of all other combinations.These techniques will be performed later to integrate soft biometrics.