Abstract This paper explores a novel approach for automatic human recognition from multi-view frontal facial images taken at different poses. The proposed computational model is based on fusion of the Group Method of Data Handling (GMDH) neural networks trained on different subsets of facial features and with different complexities. To demonstrate the effectiveness of this approach, the performance is evaluated and compared using eigen-decomposition for feature extraction and reduction with a variety of GMDH-based models. The experimental results show that high recognition rates, close to 98%, can be achieved with very low average false acceptance rates, less than 0.12%. Performance is further investigated on different feature set sizes and it is found that with smaller feature sets (as few as 8 features), the proposed GMDH-based models outperform other classifiers including those using radial-basis functions and support-vector machines. Additionally, the capability of the group method of data handling algorithm to select the most relevant features during the model construction makes it more attractive to build much simplified models of polynomial units.

References

[1] Abate A., Nappi M., Riccio D., and Sabatino G., 2D and 3D Face Recognition: A survey, Pattern Recognition Letters, vol. 28, no. 14, pp. 1885-1906, 2007.

[2] AbTech, AIM User s Manual, AbTech Corporation, 1990.

[3] Barron A., Predicted Squared Error: A criterion for Automatic Model Selection, Self-Organizing Methods in Modeling, pp. 87-103, 1984.

[4] Cevikalp H., Neamtu M., Wilkes M., and Barkana A., Discriminative Common Vectors for Face Recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 27, no. 1, pp. 4-13, 2005.

[5] Chai Z., Sun Z., Vazquez H., He R., and Tan T., Gabor Ordinal Measures for Face Recognition, IEEE Transactions on Information Forensics and Security, vol. 9, no. 1, pp. 14-26, 2014.

[6] Chakrabarty A., Jain H., and Chatterjee A., Volterra Kernel Based Face Recognition Using Artificial Bee Colony Optimization, Engineering Applications of Artificial Intelligence, vol. 26, no. 3, pp. 1107-1114, 2013.

[7] Chan L., Salleh S., Ting C., and Ariff A., PCA and LDA-Based Face Verification Using Back- Propagation Neural Network, in Proceedings of the 10th International Conference on Information Sciences, Signal Processing and their Applications, Kuala Lumpur, pp. 728-732, 2010.

[8] Chen W., Yuen P., Fang B., and Wang P., Linear and Nonlinear Feature Extraction Approaches for Face Recognition, Pattern Recognition, Machine Intelligence and Biometrics, pp. 485-514, 2011.

[9] Cottrell G. and Fleming M., Face Recognition Using Unsupervised Feature Extraction, in Proceedings of the International Neural Network Conference, Paris, 1990.

[10] Farlow S., The GMDH Algorithm, Self- Organizing Methods in Modeling: GMDH Type Algorithms, CRC Press, 1984.

[11] Graham D. and Allinson N., Characterizing Virtual Egensignatures for General Purpose Face Recognition, Face Recognition: from Theory to Applications, Springer, 1998.

[12] Guo G., Li S., and Chan K., Support Vector Machines for Face Recognition, Image and Vision Computing, vol. 19, no. 9, pp. 631-638, 2001.

[13] Kim Y., Shin K., Lee E., and Park K., Multimodal Biometric System Based on the Recognition of Face and Both Irises, International Journal of Advanced Robotic Systems, vol. 9, no. 65, pp.1-6, 2012.

[14] Kirby M. and Sirovich L., Application of the Karhunen-Loeve Procedure for the Characterization of Human Faces, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 12, no. 1, pp. 103-108, 1990.

[15] Kondo T. and Ueno J., Medical Image Diagnosis of Lung Cancer by A revised GMDH- Type Neural Network Using Various Kinds of Neuron, Artificial Life and Robotics, vol. 16, no. 3, pp. 301-306, 2011.

[16] Kukreja S. and Gupta R., Comparative Study of Different Face Recognition Techniques, in Proceedings of the International Conference on Computational Intelligence and Communication Networks, Gwalior, pp. 271-273, 2011.

[17] Kumar D. and Shrutika J., Harmony Search Algorithm for Feature Selection in Face Recognition, in Proceedings of Communications in Computer and Information Science, Pune, pp. 554-559, 2011.

[18] Kurukulasooriya A. and Dharmarathne A., Image Searching with Eigen faces and Facial Characteristics, in Proceedings of Signal Processing, Image Processing and Pattern Recognition, Jeju Island, pp. 215-224, 2011.

[19] Lai I., Chang Y., Lee C., Chiou G., and Huang H., Source Identification and Characterization of Atmospheric Polycyclic Aromatic Hydrocarbons Along the Southwestern Coastal Area of Taiwan-with a GMDH Approach, Journal of Environmental Management, vol. 115, pp. 60-68, 2013.

[20] Lawrence S., Giles C., Tsoi A., and Back A., Face Recognition: A Convolutional Neural- Network Approach, IEEE Transactions on Neural Networks, vol. 8, no. 1, pp. 98-113, 1997.

[21] Liu Z., Zhao H., Pu J., and Wang H., Face Recognition under Varying Illumination, Neural Computing and Applications, vol. 23, no. 1, pp. 133-139, 2013.

[22] Lu Y., Zhou J., and Yu S., A Survey of Face Detection Extraction and Recognition, Computing and Informatics, vol. 22, no. 2, pp. 163-195, 2012.

[23] Luo M. and Zhang K., A hybrid Approach Combining Extreme Learning Machine and Sparse Representation for Image Classification, Engineering Applications of Artificial Intelligence, vol. 27, pp. 228-235, 2014.

[24] MageshKumar C., Thiyagarajan R., Natarajan, S., Arulselv S., and Sainarayanan G., Gabor Features and LDA Based Face Recognition with ANN Classifier, in Proceedings of the International Conference on Emerging Trends in Electrical and Computer Technology, Nagercoil, pp. 831-836, 2011.

[25] Martinez A. and Kak A., PCA Versus LDA, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, no. 2, pp. 228- 233, 2001. A Novel Approach for Face Recognition Using Fused GMDH-Based Networks 377

[26] Oh B., Toh K., Teoh A., and Kim J., Combining Local Face Image Features for Identity Verification, Neurocomputing, vol. 74, no. 16, pp. 2452-2463, 2011.

[27] Ortiz E. and Becker B., Face Recognition for Web-Scale Datasets, Computer Vision and Image Understanding, vol. 118, pp.153-170, 2014.

[28] Phillips P., Support Vector Machines Applied to Face Recognition, Technical Report NISTIR 6241, 1999.

[29] Ruiz-del-Solar J. and Navarrete P., Eigenspace- Based Face Recognition: A comparative Study of Different Approaches, IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews, vol. 35, no. 3, pp. 315- 325, 2005.

[30] Shah J., Sharif M., Raza M., and Azeem A., A Survey: Linear and Nonlinear PCA Based Face Recognition Techniques, The International Arab Journal of Information Technology, vol. 10, no. 6, pp. 536-545, 2013.

[31] Sharma M., Prakash S., and Gupta P., An Efficient Partial Occluded Face Recognition System, Neurocomputing, vol. 116, pp. 231-241, 2013.

[32] Shen L. and Bai L., Gabor Feature Based Face Recognition Using Kernel Methods, in Proceedings of the 6th IEEE International Conference on Automatic Face and Gesture Recognition, Seoul, pp. 170-176, 2004.

[33] Sun Y., Tang H., and Yin B., The 3D Face Recognition Algorithm Fusing Multi-Geometry Features, Acta Automatica Sinica, vol. 34, no. 12, pp. 1483-1489, 2008.

[34] Turk M. and Pentland A., Face Recognition Using Eigenfaces, in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Maui, pp. 586- 591,1991.

[35] Wiskott, L., Fellous J., Kuiger N., and Von der Malsburg C., Face Recognition by Elastic Bunch Graph Matching, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, no. 7, pp. 775-779, 1997.

[36] Witten I., Frank E., and Hall M., Data Mining: Practical Machine Learning Tools and Techniques, Morgan Kaufmann, 2011.

[37] Xu Y., Li Z., Pan J., and Yang J., Face Recognition Based on Fusion of Multi-Resolution Gabor Reatures, Neural Computing and Applications, vol. 23, no. 5, pp. 1251-1256, 2013.

[38] Xue M., Liu W., and Liu X., A novel Weighted Fuzzy LDA for Face Recognition Using the Genetic Algorithm, Neural Computing and Applications, vol. 22, no. 7-8, pp. 1531-1541, 2013.

[39] Yu Q., Yin Y., Yang G., Ning Y., and Li Y., Face and Gait Recognition Based on Semi- Supervised Learning, in Proceedings of Chinese Conference on Pattern Recognition, Beijing, pp. 284-291, 2012.

[40] Zhao W., Chellappa R., and Phillips P., and Rosenfeld A., Face Recognition: A Literature Survey, ACM Computing Surveys, vol. 35, no. 4, pp. 399-458, 2003. El-Sayed El-Alfy is an Associate Professor and Coordinator of the Intelligent Systems Research Group, King Fahd University of Petroleum and Minerals, Saudi Arabia. His research areas include intelligent systems, information security, pattern recognition, digital forensic, network optimization, and traffic engineering. He has been actively involved in research projects and has 160+ refereed publications. He is a senior member of IEEE and on the editorial board of a number of reputable journals including IEEE Trans. Neural Networks and Learning Systems. Zubair Baig is a member of the Security Research Institute and a Senior Lecturer of Cyber-Security in the School of Science at Edith Cowan University. He has 44 journal and conference articles and book chapters pertaining to Intelligent Network Security, Network Security/Performance Trade-off and Network Design and Optimization. His research interests are in the areas of cyber-security, artificial intelligence and optimization algorithms. He has served on numerous technical program committees of international conferences and has delivered a keynote talk on computer security. Radwan Abdel-Aal received his BS in electrical engineering from Cairo University, Egypt, in 1972, his MS in aviation electronics from Cranfield University, UK in 1974, and his PhD from Strathclyde University, UK in 1983. Between 1985 and 2005, he was a research scientist at the Research Institute of King Fahd University of Petroleum & Minerals (KFUPM), Dhahran, Saudi Arabia. In 2005, he joined the Computer Engineering Department at KFUPM where he is currently a Professor. His research interests include nuclear physics instrumentation and machine learning and data mining applications.