Face recognition methods analysis

Shima Zarei(1*),

(1) Universita Degli Studi di Siena
(*) Corresponding Author


Face Recognition is one of the most important issues in Image processing tasks. It is important because it uses for various purposes in real world such as Criminal detection or for detecting fraud in passport and visa check in airports. Face book is a nice example of Face recognition application, when it sends notification to one user’s friends who are recognized by their images that user uploaded in face book page. To solve Face Recognition problem different methods are introduced such as Principal Component Analysis (PCA), Independent Component Analysis (ICA), Support Vector Machine (SVM), Linear Discriminant Analysis (LDA), and Hidden Markov Models (HMM) which are explained and analyzed. Also algorithms like; Eigen face, Fisher face and Local Binary Pattern Histogram (LBPH) which are simplest and most accurate methods are implemented in this project for AT&T dataset to recognize the most similar face to other faces in this data set. To this end these algorithms are explained and advantages and disadvantages of each one are analyzed as well. Consequently, the best method is selected with comparison between the results of face reconstruction by Engine face, Fisher face and Local binary pattern histogram methods. In this project Eigen face method has best result. It should be noted that for implementing face recognition algorithms color map methods are used to distinguish the facial features more precisely. In this work Rainbow color map in Eigen Face algorithm and HSV color map in Fisher Face algorithm are utilized and results shows that HSV color map is more accurate than rainbow color map.


Face Recognition; Eigen Face; Fisher Face; LBPH; PCA

Full Text:



Kong, Seong G and Heo, Jingu and Abidi, Besma R and Paik, Joonki and Abidi, Mongi A, Recent advances in visual and infrared face recognition a review, Computer Vision and Image Understanding, Elsevier, vol.97, pp.103-135, 2005.

G. Bradski and A. Kaehler. Learning OpenCV: Computer vision with the OpenCV library. ” O’ Reilly Media, Inc.”, 2008.

K. Etemad and R. Chellappa. Discriminant analysis for recognition of human face images. JOSA A, vol.14, pp.1724-1733, 1997.

G. Guo, S. Z. Li, and K. Chan. Face recognition by support vector machines. In Automatic Face and Gesture Recognition, Proceedings Fourth IEEE International Conference on, IEEE, pp. 196-2011, 2000.

A. Hyv¨arinen. Independent component analysis: recent advances. Phil. Trans. R. Soc. A, vol. 371, pp.20110534, 2013.

P. Navarrete and J. Ruiz-del Solar. Analysis and comparison of eigenspacebased face recognition approaches. International Journal of Pattern Recognition and Artificial Intelligence, vol.16, pp.817-830, 2002.

A. V. Nefian and M. H. Hayes. Hidden markov models for face recognition, In Acoustics, Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on, IEEE, vol.16, pp. 2721-2724, 1998.

N. Stekas and D. van den Heuvel. Face recognition using local binary patterns histograms (lbph) on an fpga-based system on chip (soc), In Parallel and Distributed Processing Symposium Workshops, IEEE International, IEEE, pp.300–304, 2016.

M. Turk and A. Pentland. Eigenfaces for recognition. Journal of cognitive neuroscience, vol.3, pp.71-86, 1991.

Zhao, Wenyi and Krishnaswamy, Arvindh and Chellappa, Rama and Swets, Daniel L and Weng, J, Discriminant analysis of principal components for face recognition, Face Recognition, pp.73-85, 1998.

Belhumeur, Peter N and Hespanha, Joao P and Kriegman, David J,Eigenfaces vs. fisherfaces: Recognition using class specific linear projection,1997.

Cevikalp, Hakan and Neamtu, Marian and Wilkes, Mitch and Barkana, Atalay, Discriminative common vectors for face recognition, IEEE Transactions on pattern analysis and machine intelligence, vol.27, pp.4-13, 2005.

Shan, Caifeng, Learning local binary patterns for gender classification on real-world face images, Pattern recognition letters, vol.33, pp.431-437, 2012.

Nefian, Ara V and Hayes, Monson H, Maximum likelihood training of the embedded HMM for face detection and recognition, Image Processing, Proceedings. 2000 International Conference on, IEEE, vol.1, pp.33-36, 2000.

Deniz, Oscar and Castrillon, M and Hernandez, Mario,Face recognition using independent component analysis and support vector machines, vol.24, pp.2153-2157, 2003.

Bartlett, Marian Stewart and Movellan, Javier R and Sejnowski, Terrence J, Face recognition by independent component analysis, IEEE transactions on neural networks a publication of the IEEE Neural Networks Council, Howard Hughes Medical Institute, vol.13, pp.1450, 2002.

Ahonen, Timo and Hadid, Abdenour and Pietikainen, Matti, Face description with local binary patterns: Application to face recognition,IEEE Transactions on Pattern Analysis & Machine Intelligence, IEEE, pp.2037-2041, 2006.

Zhao, Wenyi and Chellappa, Rama and Phillips, P Jonathon and Rosenfeld, Azriel, Face recognition: A literature survey, ACM computing surveys (CSUR), ACM, vol.35, pp.399-458, 2003.

A. Bouzalmat, J. Kharroubi, and A. Zarghili, Comparative study of pca, ica, lda using svm classifier, vol.2, Journal of Emerging Technologies in Web Intelligence, pp.64-68, 2014.

Yu, Hua and Yang, Jie, A direct LDA algorithm for high-dimensional data—with application to face recognition,Pattern recognition,Pergamon, vol.34, pp.2067-2070, 2001.

DOI: http://dx.doi.org/10.33292/ijarlit.v1i1.13

Article Metrics

Abstract view : 299 times
PDF - 168 times


  • There are currently no refbacks.