MLP-based face recognition with Gabor filters and PCA
David González‐Ortega, Francisco Javier Díaz Pernas, Míriam Antón‐Rodríguez, Mario Martínez‐Zarzuela, J. F. Díez-Higuera · Pattern Recognition and Image Analysis · 2013
In this paper, we present a multiple scale neural architecture for face recognition. The architecture is composed of several stages: face detection, Difference of Gaussians, Gabor filter bank, Principal Component Analysis, and two-stage MLPs. The architecture was evaluated using two well-known face databases. A detailed study of all the parameters that influence the architecture performance was carried out. The architecture achieved a correct detection rate of 84% with face images changing in pose and gesture.