Document Type : Original Research Paper


Faculty of Computer Engineering, Shahid Rajaei Teacher Training University, Tehran, Iran


This paper proposed a new method for face recognition with principal component analysis in the feature extraction phase, and devised a modified version of Mixture of Experts in which each expert is an MLP, instead of linear networks in order to improve the performance of the expert networks, and consequently the whole network performance; Therewith, we use a Momentum term in training the MLP experts, which speeds up the adjustment of weight greatly. We explore three different Mixture of Experts constructing a neural network. Our proposed model, achieved a correct recognition rate on Yale and ORL datasets. Comparisons with other algorithms demonstrate that our method performs better in terms of higher recognition rate, with smaller number of epochs in human face recognition.


Main Subjects

[12] Cootes T., Walker K. and Taylor C., “ViewBased Active Appearance Models”, IEEE
International Conference on Automatic Face
and Gesture Recognition, Grenoble, France,
2000, pp. 227-232.
[13] Freund Y. and Schapire R., “A DecisionTheoretic Generalization of On-Line Learning
and an Application to Boosting”, Journal of
Computer and System Sciences, Vol. 55, No. 1,
1997, pp. 119-139.
[14] Meir R. and Raetsch G., “An Introduction to
Boosting and Leveraging”, Advanced Lectures
on Machine Learning, 2003, pp. 118-183.
[15] Haykin S., Neural Networks: A Comprehensive
Foundation, book, Prentice Hall PTR Upper
Saddle River, USA, 1998.
[16] Jacobs R., Jordan M., Nowlan S., and Hinton
G., “Adaptive Mixtures of Local Experts”,
Neural Comput3, 1991, pp. 79–87.
[17] Ebrahimpour R., Kabir E. and Yousefi M.,
“Teacher-Directed Learning in Viewindependent Face Recognition with Mixture of
Experts Using Overlapping Eigenspaces”,
Computer Vision and Image Understanding,
Vol. 111, 2008, pp. 195-206.
[18] Ebrahimpour R., Kabir E. and Yousefi M.,
“Teacher-Directed Learning in Viewindependent Face Recognition with Mixture of
Experts Using Single-view Eigenspaces”,
Journal of Franklin Institute, Vol. 345, 2008,
pp. 87-101.
[19] Ebrahimpour R., Kabir E., Esteky H. and
Yousefi M., “View-independent Face
Recognition with Mixture of Experts,
Neurocomputing”, Vol. 71, 2008, pp. 1103-
[20] Ebrahimpour R., Kabir E., Esteky H. and
Yousefi M., “A Mixture of Multilayer
Perceptron Experts Network For Modeling
Face/Nonface Recognition in Cortical Face
Processing Regions”, Intelligent Automation
and Soft Computing, Vol. 14, No. 2, 2008, pp.
[21] Ebrahimpour R., Kabir E. and Yousefi M.,
“Face Detection Using Mixture of MLP
Experts”, Neural Processing Letters, Vol. 26,
No. 1, 2007, pp. 69-82.
[1] Lu J., Plataniotis K. and Venetsanopoulos A.,
“Face Recognition Using LDA-Based
Algorithms”, IEEE Transaction on Neural
Networks, Vol. 14, No. 1, 2003, pp. 195-200.
[2] Turk M. and Pentland A., “Face Recognition
Using Eigenfaces”, the IEEE Conference on
Computer Vision and Pattern Recognition,
Maui, Hawaii, USA, 1991, pp 586-591.
[3] Sirovich L. and Kirby M., “Low-dimensional
procedure for the characterization of human
faces”, Journal of Optical Society of America,
Vol. 4, 1987, pp. 519–524.
[4] Romdahani S., Face recognition using principal
component analysis, Survey, 1999.
[5] Bartlett M., Movellan J. and Sejnowski T.,
“Face Recognition by Independent Component
Analysis”, IEEE Transaction on Neural
Networks, Vol. 13, No. 6, 2002, pp. 1450-
[6] Liu C. and Wechsler H., “Comparative
Assessment of Independent Component
Analysis (ICA) for Face Recognition s”, the
Second International Conference on Audio and
Video-based Biometric Person Authentication,
Washington D.C., USA, 2000, pp. 211-216.
[7] Baek K., Draper B.A., Beveridge J.R. and She
K., “PCA vs ICA: A comparison on the FERET
data set”, Joint Conference on Information
Sciences, Durham, NC, 2002.
[8] Lu J., Plataniotis K., Venetsanopoulos A. and Li
S., “Ensemble-Based Discriminant Learning
With Boosting for Face Recognition”, IEEE
transaction on neural networks, Vol. 17, NO. 1
, 2006.
[9] Wiskott L., Fellous J., Krueuger N. and
Malsburg C., “Face Recognition by Elastic
Bunch Graph Matching”, Chapter 11 in
Intelligent Biometric Techniques in
Fingerprint and Face Recognition, CRC
Press,1999, pp. 355-396.
[10] Wiskott L., Fellous J., Krueuger N. and
Malsburg C., “Face Recognition by Elastic
Bunch Graph Matching”, IEEE Transaction on
Pattern Analysis and Machine Intelligence,
Vol. 19, No. 7, 1999, pp. 776-779.
آموزش بازشناسی چهره با استفاده از ترکیب شبکه های عصبی مبتنی بر اختالط خبره ها رضا ابراهیم پور و همکاران
721 مجله فناوری آموزش، سال سوم، جلد 3 ،شماره2 ،زمستان 7331
[11] Cootes T. and Taylor C., “Statistical Models of
Appearance for Computer Vision”, Technical
Report, University of Manchester, 1999.
[27] Jonsson K., Kittler J., Li Y. P. and J. Matas,
Support vector machines for face
authentication, in Pridmore T. and Elliman D.
, editors, British Machine Vision Conference,
1999, pp. 543–553.
[28] Guo G.D., Zhang H.J. and Li S.Z.., “Pairwise
face recognition”, In Proceedings of 8th IEEE
International Conference on Computer Vision.
Vancouver, Canada. July 9-12, 2001.
[29] Kim K.I., Jung K. and Kim J., “Face
recognition using support vector machines
with local correlation kernels” , International
Journal of Pattern Recognition and Artificial
Intelligence, Vol. 16 No. 1, 2002, pp. 97-111.
[30] Lin S.H., Kung S.Y. and Lin L.J., “Face
recognition/detection by probabilistic
decision-based neural network”, IEEE Trans.
Neural Networks, vol. 8, 1997, pp. 114-132.
[22] Beale R. and Jackson T., “Neural computing:
an introduction”, Institute of Physics
Publishing, 1998.
[23] Kohavi R. and Provost F., “Glossary of terms”,
Machine Learning, 30, 1998, pp.271–274.
[24] Tang H., Lyu M. and King I., “Face
recognition committee machine”, In
Proceedings of IEEE International Conference
on Acoustics, Speech, and Signal Processing,
April 6-10, 2003, pp. 837-840.
[25] Huang R., Pavlovic V. and Metaxas D. N., “A
hybrid face recognition method using Markov
random fields”, 2004, pp. 157-160.
[26] Samaria F. and Harter A.C., “Parameterisation
of a stochastic model for human face
identification”, Second IEEE Workshop
Applications of Computer Vision, 1994.