MLP-based face recognition with Gabor filters and PCA

Authors:
D. González-Ortega;F. J. Díaz-Pernas;M. Antón-Rodríguez;M. Martínez-Zarzuela;J. F. Díez-Higuera
Affiliations:
Higher School of Telecommunications Engineering, University of Valladolid, Valladolid, Spain;Higher School of Telecommunications Engineering, University of Valladolid, Valladolid, Spain;Higher School of Telecommunications Engineering, University of Valladolid, Valladolid, Spain;Higher School of Telecommunications Engineering, University of Valladolid, Valladolid, Spain;Higher School of Telecommunications Engineering, University of Valladolid, Valladolid, Spain
Venue:
Pattern Recognition and Image Analysis
Year:
2013

Citing 9
Cited 0

Evolutionary Pursuit and Its Application to Face Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
Face Recognition: Features Versus Templates

IEEE Transactions on Pattern Analysis and Machine Intelligence
Face recognition: A literature survey

ACM Computing Surveys (CSUR)
Optimal sampling of Gabor features for face recognition

Pattern Recognition Letters
Simple Gabor feature space for invariant object recognition

Pattern Recognition Letters
2D and 3D face recognition: A survey

Pattern Recognition Letters
Eigenfaces for recognition

Journal of Cognitive Neuroscience
Evaluation of Face Datasets as Tools for Assessing the Performance of Face Recognition Methods

International Journal of Computer Vision
A Comparative Study of Local Matching Approach for Face Recognition

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.