Abstract
In this paper, new appearances based on neural networks (NN) algorithms are presented for face recognition. Face recognition is subdivided into two main stages: feature extraction and classifier. The suggested NN algorithms are the unsupervised Sanger principal component neural network (Sanger PCNN) and the self-organizing feature map (SOFM), which will be applied for features extraction of the frontal view of a face image. It is of interest to compare the unsupervised network with the traditional Eigenfaces technique. This paper presents an experimental comparison of the statistical Eigenfaces method for feature extraction and the unsupervised neural networks in order to evaluate the classification accuracies as comparison criteria. The classifier is done by the multilayer perceptron (MLP) neural network. Overcoming of the problem of the finite number of training samples per person is discussed. Experimental results are implemented on the Olivetti Research Laboratory database that contains variability in expression, pose, and facial details. The results show that the proposed method SOFM/MLP neural network is more efficient and robust than the Sanger PCNN/MLP and the Eigenfaces/MLP, when used a few number of training samples per person. As a result, it would be more applicable to utilize the SOFM/MLP NN in order to accomplish a higher level of accuracy within a recognition system.
Similar content being viewed by others
References
Alvarado GJ, Pedrycz W, Reformat M, Kwak KC (2006) Deterioration of visual information in face classification using eigenfaces and fisherfaces. Int J Mach Vis Appl 17(1):68–82
Valentin D, Abdi H, O’Toole AJ, Cottrell GW (1994) Connectionist models of face processing: a survey. Int J Pattern Recognit 27:1209–1230
Orozco-Alzate M, Germán C, Domínguez C (2006) Comparison of the nearest feature classifiers for face recognition. J. Int J Mach Vis Appl 17:279–285
Yang MH, Kriegman DJ (2002) Detecting faces in images: a survey. IEEE Trans Pattern Anal Mach Intell 24(1):34–58
Sakthivel S, Lakshmipathi R (2010) Enhancing face recognition using improved dimensionality reduction and feature extraction algorithms—an evaluation with ORL database. Int J Eng Sci Technol 2(6):2288–2295
Khattab DR, El-Latif YMA, Wahab MSA, Tolba MF (2008) Efficient face-based non-split connectivity compression for quad and triangle-quad meshes. In: Proceedings of the 3rd international conference on computer graphics theory and applications, pp 31–38
Khattab DR, El-Latif YMA, Wahab MSA, Tolba MF (2007) An enhanced edgebreaker compression algorithm for the connectivity of triangular meshes. In: Proceedings of the 2nd international conference on computer graphics theory and applications, proceedings, pp 109–115
Karande KJ, Talbar SN (2009) Independent component analysis of edge information for face recognition. Int J Image Proc 3(3):120–130
Liu C, Wechsler H (1999) Comparative assessment of independent component analysis (ICA) for face recognition. In: Proceedings of the 2nd international conference on audio- and video-based biometric person authentication, pp 211–216
Li J, Zhao B, Zhang H (2009) Face recognition based on PCA and LDA combination feature extraction. In: Proceedings of the 1st IEEE international conference on information science and engineering, pp 1240–1243
Zhang H, Deng W, Guo J, Yang J (2010) Locality preserving and global discriminant projection with prior information. Int J Mach Vis Appl 21:577–585
Jarillo G, Pedrycz W, Reformat M (2008) Aggregation of classifiers based on image transformations in biometric face recognition. Int J Mach Vis Appl 19:125–140
Lu J, Plataniotis KN, Venetsanopoulos AN (2003) Face recognition using kernel direct discriminant analysis algorithms. IEEE Trans Neural Netw 14(1):117–126
Bach FR, Jordan MI (2002) Kernel independent component analysis. Int J Mach Learn Res 3:41–48
Brunelli R, Falavigna D, Poggio T, Stringa L (1995) Automatic person recognition by acoustic and geometric features. Int J Mach Vis Appl 8:317–325
Moghaddam B, Nastar C, Pentlan A (2001) A Bayesian similarity measure for deformable image matching. Int J Image Vis Comput 19:235–244
Wang R, Shan S, Chen X, Gao W (2008) Manifold-manifold distance with application to face recognition based on image set. In: Proceedings of the IEEE international conference on computer vision and pattern recognition (CVPR)
Eleyan A, Demirel H (2005) Face recognition system based on PCA and feedforward neural networks. In: Proceedings of the 8th international work-conference on artificial neural networks, pp 935–942
Wong J, Cho S (2010) A Face emotion tree structure representation with probabilistic recursive neural network modeling. Int J Neural Comput Appl 19:33–54
Ebrahimpour R, Kabir E, Yousefi MR (2011) Improving mixture of experts for view-independent face recognition using teacher-directed learning. Int J Mach Vis Appl 22:421–432
Shan S, Gao W, Zhao D (2003) Face recognition based on face-specific subspace. Int J Imag Syst Technol 13:23–32
Turk M, Pentland A (1991) Eigenfaces for face recognition. Int J Cogn Neurosci 3(1):71–86
Pentland A, Moghadam B, Starner T (1994) View based and modular eigenspaces for face recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 84–91
Draper BA, Baek K, Bartlett MS (2003) Recognizing faces with PCA and ICA. Int J Comput Vis Image Underst 91:115–137
Rencher AC (2002) Methods Of multivariate analysis, 2nd edn. Wiley, New York
Oravec M, Pavlovičová J (2007) Face Recognition methods based on feedforward neural networks, principal component analysis and self-organizing map. Radio Eng 16(1):51–57
Delac K, Grgic M, Grgic S (2005) Independent comparative study of PCA, ICA, and LDA on the FERET data set. Int J Imag Syst Technol 15:252–260
Jiang X, Mandal B, Kot A (2009) Complete Discriminant evaluation and feature extraction in kernel space for face recognition. Int J Mach Vis Appl 20:35–46
Alvarado GJ, Pedrycz W, Reformat M, Kwak K (2006) Deterioration of visual information in face classification using eigenfaces and fisherfaces. Int J Mach Vis Appl 17(1):68–82
Sanger TD (1989) Optimal unsupervised learning in a single-layer linear feedforward neural network. Int J Neural Netw 2:459–473
Rizk MRM, Koosha EM (2006) A Comparison of principal component analysis and generalized hebbian algorithm for image compression and face recognition, In: Proceedings of the IEEE international conference on computer engineering and systems, pp 214–219
Chitaliya NG, Trivedi AI (2010) Feature extraction using wavelet-PCA and neural network for application of object classification and face recognition. In: Proceedings of the 2nd IEEE international conference on computer engineering and applications, vol 1, pp 510–514
Wilhelm T, Böhme H, Gross H (2005) Classification of face images for gender, age, facial expression, and identity. In: Proceedings of the international conference on artificial neural networks (ICANN’05), pp 569–574
Latha P, Ganesan L, Annadurai S (2010) Face recognition using neural networks. Int J Signal Process 3(5):153–160
Kumar D, Rai CS, Kumar S (2010) Analysis of unsupervised learning techniques for face recognition. Int J Imag Syst Technol J 20:261–267
Mu X, Artiklar M, Watta P, Hassoun MH (2006) An RCE-based associative memory with application to human face recognition. Int J Neural Process Lett 23:257–271
Oja E (1982) A Simplified neuron model as a principal component analyzer. J Math Biol 15:267–273
Kohonen T, Oja E, Simula O, A Visa, J Kangas (1996) Engineering applications of the self-organizing map. Proc IEEE 84:1358–1384
AT&T Laboratories Cambridge database of faces. http://www.uk.research.att.com:pub/data/att_faces.zip
Huang J, Yuen PC, Lai JH, Li C (2004) Face recognition using local and global features. EUR J Appl Signal Process 4:530–541
Gandhe ST, Talele KT, Keskar AG (2007) Intelligent face recognition techniques: a comparative study. Int J Graph Vis Image Process (GVIP) 7(2):53–60
Shastri BJ, Levine MD (2007) Face recognition using localized features based on non-negative sparse coding. Int J Mach Vision Appl 18:107–122
Kohonen T (1995) Self-organizing maps. Berlin, Springer
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Ebied, H.M., Revett, K. & Tolba, M.F. Evaluation of unsupervised feature extraction neural networks for face recognition. Neural Comput & Applic 22, 1211–1222 (2013). https://doi.org/10.1007/s00521-012-0889-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-012-0889-2