A novel and efficient method for face recognition using original and symmetrical samples

In the practical case of face recognition applications, the human face can have only a limited number of training images. However, it is known that, in general, increasing the number of training images also increases the performance of face recognition systems. In this case, a new set of training samples can be generated from the original samples, using the symmetry property of the face. Although many face recognition methods have been proposed in the literature, a robust face recognition system is still a challenging task. In this thesis, recognition performance is improved by using the property of face symmetry. Moreover, by this way we observe that the effects of illumination and pose variations are reduced. The proposed method has three main stages: preprocessing, feature extraction and classification. A Two-Dimensional Discrete Wavelet Transform with Single-Level, Gaussian Low-Pass Filter and Difference of Gaussian are used, separately, for preprocessing. The Local Binary Pattern, Gray Level Co-Occurrence Matrix, Gabor Filter and Histogram of Oriented Gradients are used for feature extraction, and finally, the Euclidean distance and cosine similarity are used for classification. The proposed method is tested and evaluated using the Olivetti Research Laboratory (ORL), Yale and AR datasets. The proposed method is a new approach for face recognition using symmetry. Also, a new algorithm for feature extraction is proposed and the experimental results show that it is faster than state of the art methods in the literature. The new proposed algorithm can use the benefit of symmetry property either in the image space or in the feature space. This thesis also examines the importance of the preprocessing stage in a face recognition system. The experimental results show that the proposed method has a recognition accuracy rates higher than the state-of-the art methods in the literature.