Article Preview
Top1. Introduction
Biometric face recognition technology has received significant attention in the past several years due to its potential in different applications. Automated human face recognition was applied in different fields including automated secured access to machines and buildings, automatic surveillance, forensic analysis, fast retrieval of records from databases in police departments, automatic identification of patients in hospitals, checking for fraud or identity and human-computer interaction (Gawali, 2014; Bedoui, 2008).
In recent years face recognition has received substantial attention from both research communities and the market, but still remained very challenging in real applications. Several face recognition algorithms have been developed during the past decades. Automatic recognition of human faces based on the 2D images processing is well developed this last years, and several techniques have been proposed. We find several global, local and hybrids methods: The Principal Component Analysis PCA also known under the name eigenfaces (Sirovich, 1990; Alain, 2009), two-dimensional version of PCA noted 2DPCA (Yang, 2004). The Stochastic Approach in (Laskri, 2002, Suri, 2011). In 1991, M. A. Turk et al. implemented the Principal Component Analysis (PCA) approach known under the name Eigenfaces (Turk, 1991). In 2001, G.D. Guo proposed a multi-class classification problem for a K-class classification test, Optimal-Pairwise Coupling (O-PWC) SVM (Guo, 2001). In 2003, J. Lu et al. implemented a method combines the strengths of the D-LDA and F-LDA approaches, while at the same time overcomes their shortcomings and limitations (Lu, 2003). Two-dimensional version (2DPCA) was presented by J. Yang et al. in 2004 for image representation (Yang, 2004). M. Visani et al. proposed Two-Dimensional Linear Discriminant Analysis (2DO-LDA) in 2004. This approach is chosen to jointly maximize the mean variation between classes and minimize the mean of the variations inside each class (Visani, 2004). H. Cevikalp et al. propose an approach called the Discriminative Common Vector method based on a variation of Fishers Linear Discriminant Analysis for the small sample size case in 2005 (Cevikalp, 2005). Linear Discriminant Analysis LDA also known under the name Fisherfaces was proposed by L. Bedoui et al. in 2008 (Bedoui, 2008). In 2010 M. Agarwalet al. implemented a method based on Principal Component Analysis (PCA) and Neural Network (NN) (Agarwal, 2010). In 2012 V.More et al, used modified fisher face and fuzzy fisher face FFLD for person identification (More, 2012). In 2014 W. Xu et al. propose an integrated algorithm based on the respective advantages of wavelets transform (WT), 2D Principle Component Analysis (PCA) and Support Vector Machines (SVM) (Xu et al., 2014).