Sparse Representation Approach for Variation-Robust Face Recognition Using Discrete Wavelet Transform
Face recognition has become one of the most challenging tasks in the pattern recognition field and it is very important for many applications such as: video surveillance, forensic applications criminal investigations, and in many other fields it is also very useful. In this paper we are using sparse representation approach based on discrete wavelet transform (DWT) to achieve more robustness to variation in lighting, directions and expressions, because sparse representation does not exterminate obstacles posed by several practical issues, such as lighting, pose, and especially facial expressions, which tend to distort almost all the features and can thus compromise the accuracy of sparse representation. The result of new proposed approach is compared with sparse representation approach to show that the proposed approach is more robust to illumination, direction and expression variations than sparse representation.
Keywords: Face recognition, L1-minimization, sparse representation, discrete wavelet transform (DWT).
Download Full-Text
ABOUT THE AUTHORS
Rania Salah El-Sayed
Department of Computer science, Faculty of Science, Al-Azhar University, Cairo. Egypt
Mohamedyoussri El-Nahas
Department of Information system, Faculty of Engineering , Al-Azhar University, Cairo. Egypt
Ahmed El Kholy
Department of Mathematics, Faculty of Science, Al-Azhar University, Cairo. Egypt
Rania Salah El-Sayed
Department of Computer science, Faculty of Science, Al-Azhar University, Cairo. Egypt
Mohamedyoussri El-Nahas
Department of Information system, Faculty of Engineering , Al-Azhar University, Cairo. Egypt
Ahmed El Kholy
Department of Mathematics, Faculty of Science, Al-Azhar University, Cairo. Egypt