A novel automatic face recognition system

Yıl 2022, Cilt: 11 Sayı: 3, 574 - 583, 18.07.2022

Engin Cemal Mengüç , Nurettin Acır

https://doi.org/10.28948/ngumuh.1094160

Öz

In this study, a new automatic face recognition system is proposed using the recently developed Lyapunov stability theory (LST) based artificial neural network (ANN) algorithm. For this purpose, the principal component analysis (PCA) method is first used to extract the most informative features and reduce computational complexity. Then, LST based ANN structure as a classifier is fed by the extracted features. The performance of the proposed face recognition system is evaluated on the ORL face dataset in comparison with other systems. Experimental results prove that the proposed face recognition system provides higher training and test recognition rates as well as higher training speed with the help of the adaptive adaptation gain rate parameter.

Anahtar Kelimeler

Face recognition, rtificial neural network, Lyapunov stability theory

Yeni bir otomatik yüz tanıma sistemi

Öz

Bu çalışmada, yakın zamanda geliştirilen Lyapunov kararlılık teorisi (LKT) tabanlı yapay sinir ağı (YSA) algoritması kullanılarak yeni bir otomatik yüz tanıma sistemi önerilmiştir. Bu amaç doğrultusunda, ilk olarak en bilgilendirici öznitelikleri çıkarmak ve hesap karmaşıklığını azaltmak için temel bileşen analizi (TBA) metodu kullanılmıştır. Ardından, çıkarılan öznitelikler ile LKT tabanlı YSA yapısı bir sınıflandırıcı olarak beslenmiştir. Önerilen yüz tanıma sisteminin başarımı, diğer sistemlerle karşılaştırmalı olarak ORL yüz veri kümesi üzerinde değerlendirilmiştir. Deneysel sonuçlar, önerilen yüz tanıma sisteminin, adaptif adaptasyon kazanç oranı parametresi yardımıyla, daha yüksek eğitim hızının yanı sıra daha yüksek eğitim ve test tanıma oranları sağladığını kanıtlamıştır.

Anahtar Kelimeler

Yüz tanıma, Yapay sinir ağı, Lyapunov kararlılık teorisi

Kaynakça

• P. N. Belhumeur, J. P. Hespanha and D. J. Kriegman, Eigenfaces vs. fisherfaces: Recognition using class specific linear projection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19 (7), 711–720, 1997. doi: 10.1109/34.598228
• C. F. Bobis, R. C. Gonezalez, J. A. Cancelas, I. Alvarez and J. M. Enguita, Face recognition using binary thresholding for features extraction. In Proceedings of the IEEE International Conference on Image Analysis and Processing (ICIAP), pp. 1077-1080, IEEE, 1999. doi: 10.1109/ICIAP.1999.797742
• S. Cagnoni, A. Poggi, and G. L. Porcari, A modified modular eigenspace approach to face recognition. In Proceedings of the 10th International Conference on Image Analysis and Processing (ICIAP), pp. 490-495, IEEE, 1999. doi: 10.1109/ICIAP.1999.797643
• S. C. Yan, H. Wang, X. O. Tang and T. Huang, Exploring features descriptors for face recognition. In Proceedings of the 32nd IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 629-632, 2007. doi 10.1109/ICASSP .2007.365986
• M. Kirby and L. Sirovich, Application of the Karhunen-Loeve procedure for the characterization of human faces. IEEE Transactions on Pattern Analysis and Machine Intelligence, 12, 103–108, 1990. doi: 10.1109/34.41390
• W. Hu, O. Farooq and S. Datta, Wavelet based sub-space features for face recognition. In Proceedings of the International Congress on Image and Signal Processing (ICSP), pp. 426-430, IEEE, 2008. doi: 10.1109/CISP.2008.618
• A. S. Mian, M. Bennamoun and R. Owens, An efficient multimodal 2D-3D hybrid approach to automatic face recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29 (11), 1927–1943, 2007. doi: 10.1109/TPAMI.2007.1105
• K. H. Lim, K. P. Seng, L. Ang and S. W. Chin, Lyapunov theory-based multilayered neural network. IEEE Transactions on Circuits and Systems II: Express Brief, 56 (4), 305-309, 2009. doi: 10.1109/TCSII.2009. 2015400
• L. Ang, K. H. Lim, K. P. Seng and S. W. Chin, A Lyapunov theory-based neural network approach for face recognition. Intelligent Systems for Automated Learning and Adaptation, IGI Global Press, pp. 23–48, 2010. doi: 10.4018/978-1-60566-798-0.ch002
• M. J. Er, S. Wu, J. Lu and H. L. Toh, Face recognition with radial basis function (RBF) neural networks. IEEE Transactions on Neural Networks, 13 (3), 697–710, 2002. doi: 10.1109/TNN.2002.1000134
• M. J. Er, W. L. Chen and S. Q. Wu, High-speed face recognition based on discrete cosine transform and RBF neural network. IEEE Transactions on Neural Networks, 16 (3), 679–691, 2005. doi: 10.1109/TNN. 2005.844909
• J. Zhou, Y. Liu and Y. H. Chen, Face recognition using kernel PCA and hierarchical RBF network. In Proceedings of the 6th IEEE International Conference on Computer Information Systems and Industrial Management Applications (CISIM), 239-244, 2007. doi: 10.1109/CISIM.2007.28
• S. H. Lin, S. Y. Kung and L. J. Lin, Face recognition/detection by probabilistic decision- based neural network. IEEE Transactions on Neural Networks, 8, 114–132, 1997. doi: 10.1109/72.554196
• S. A. Nazeer, N. Omar and M. Khalid, Face recognition system using artificial neural network approach. In Proceedings of the International Conference on Signal Processing, Communication and Networking (ICSCN), 420-425, 2007. doi: 10.1109/ICSCN.2007.350774
• R. Chellappa, C. Wilson and S. Sirohey, Human and machine recognition of faces: A survey. Proceedings of the IEEE, 83 (5), 705–740, 1995. doi: 10.1109/5.381 842
• D. Valentin, H. Abdi, A. J. O’toole and G. W. Cottrell, Connectionist models of face processing: A survey. Pattern Recognition, 27, 1209–1230, 1994. doi: 10.10 16/0031-3203(94)90006-X
• J. Bilski and L. Rutkowski, A fast training algorithm for neural networks. IEEE Transactions on Circuits and Systems II: Analog Digital and Signal Processing, 45 (6), 749-753, 1998. doi: 10.1109/82.686696
• C. Charalambous, Conjugate gradient algorithm for efficient training of artificial neural networks. IEE Proceedings, 139 (3), 301–310, 1992. doi: 10.1049/ip-g-2.1992.0050
• G. Lera and M. Pinzolas, Neighborhood based Levenberg-Marquardt algorithm for neural network training. IEEE Transactions on Neural Networks, 13 (5), 1200-1203, 2002. doi: 10.1109/TNN.2002.103195 1
• S. Osowski, P. Bojarczak and M. Stodolski, Fast second order learning algorithm for feedforward multilayer neural network and its applications. Neural Networks, 9 (9), 1583–1596, 1992. doi: 10.1016/S0893 -6080(96)00029-9
• L. Behera, S. Kumar and A. Patnaik, On the adaptive learning rate that guarantees convergence in feedforward networks. IEEE Transactions on Neural Networks, 17 (5), 1116–1125, 2006. doi: 10.1109/TNN .2006.878121
• X. Jing and L. Cheng, An optimal-PID control algorithm for training feed-forward neural networks. IEEE Transactions on Industrial Electronics, 60 (6), 2273-2283, 2013. doi: 10.1109/TIE.2012.2194973
• K. P. Seng, Z. Man and H. R. Wu, Lyapunov theory-based radial basis function networks for adaptive filtering. IEEE Transactions on Circuits Systems I: Fundamental Theory Applications, 49 (8), 1215-1220, 2002. doi: 10.1109/TCSI.2002.801255
• N. Acır and E. C. Mengüç, Lyapunov theory based adaptive learning algorithm for multilayer neural networks. Neural Network World, 24 (6), 619–636, 2014. doi: 10.14311/NNW.2014.24.035
• E. C. Mengüç and N. Acır, A novel adaptive filter design using Lyapunov stability theory. Turkish Journal of Electrical Engineering and Computer Sciences, 23 (3), 719-728, 2015. doi: 10.3906/elk-1212 -29
• E. C. Mengüç and N. Acır, Real-time implementation of Lyapunov stability theory-based adaptive filter on FPGA. IEICE Transactions on Electronics, 99 (1), 129-137, 2016. doi: 10.1587/transele.E99.C.129
• E. C. Mengüç and N. Acır, An augmented complex-valued Lyapunov stability theory based adaptive filter algorithm. Signal Processing, 137, 10-21, 2017. doi:10 .1016/j.sigpro.2017.01.031
• E. C. Mengüç and N. Acır, A generalized Lyapunov stability theory-based adaptive FIR filter algorithm with variable step sizes. Signal, Image and Video Processing, 11 (8), 1567-1575, 2017. doi: 10.1007/s11 760-017-1121-8
• E. C. Mengüç and N. Acır, A novel adaptive filter algorithm for tracking of chaotic times series. 2011 IEEE 19th Signal Processing and Communications Applications Conference (SIU), 490-493, 2011. doi: 10 .1109/SIU.2011.5929694
• H. K. Khalil, Nonlinear Systems. Macmillan, New York, NY, 1992.
• ORL Database of Faces, The database of faces Olivetti Research Laboratory. http://www.cl.cam.ac.uk/rese arch/dtg/attarchive/facedatabase.html, Accessed 3 March 2015.
• C. S. Leung, A. C. Tsoi and L. W. Chan, Two regularizes for recursive least squared algorithms in feedforward multilayered neural networks. IEEE Transactions on Neural Networks, 12 (6), 1314-1332, 2001. doi: 10.1109/72.963768