Face Recognition by Neural Networks based on Gabor filters and Random Projection
Hamid Ouanan, Mohammed Ouanan, Brahim Aksasse · International journal of mathematics and computation · 2015
This article is part of the context of biometrics whose objective is the recognition of people through their faces. We propose an approach based on the texture characteristics, using the Gabor filters (GF), specifically; we construct a vector descriptor combining the amplitude and the phase of the convolution of the face image with a family of Gabor filters characterized by different orientations and resolutions. Moreover, to reduce the dimensionality of the descriptor vector, we make use of Random Projection (RP). Finally Multi-layer perceptron (MLP) based Back Propagation Neural Network (BPNN) has been used for classification.