Special Issue on Neuro-Computing and Hybrid Methods for Evolving IntelligenceNo Access

EVOLUTIONARY MULTI-OBJECTIVE OPTIMISATION OF NEURAL NETWORKS FOR FACE DETECTION

STEFAN WIEGAND

Institut für Neuroinformatik, Ruhr-Universität Bochum, 44780 Bochum, Germany

Search for more papers by this author

CHRISTIAN IGEL

Institut für Neuroinformatik, Ruhr-Universität Bochum, 44780 Bochum, Germany

Search for more papers by this author

, and

UWE HANDMANN

Viisage Technology AG, 44801 Bochum, Germany

Search for more papers by this author

https://doi.org/10.1142/S1469026804001288Cited by:27 (Source: Crossref)

Abstract

For face recognition from video streams speed and accuracy are vital aspects. The first decision whether a preprocessed image region represents a human face or not is often made by a feed-forward neural network (NN), e.g. in the Viisage-FaceFINDER^® video surveillance system. We describe the optimisation of such a NN by a hybrid algorithm combining evolutionary multi-objective optimisation (EMO) and gradient-based learning. The evolved solutions perform considerably faster than an expert-designed architecture without loss of accuracy. We compare an EMO and a single objective approach, both with online search strategy adaptation. It turns out that EMO is preferable to the single objective approach in several respects.

Keywords:

Remember to check out the Most Cited Articles!
Check out these titles in artificial intelligence!

References

Viisage Technology AG, http://www.viisage.com . Google Scholar
M. Hiisken, M. Brauckmann, S. Gehlen, K. Okada and C. von der Malsburg, Evaluation of implicit 3D modeling for pose invariant face recognition, in Defense and Security Symposium 2004: Biometric Technology for Human Identification, eds. A. K. Jain and N. K. Ratha, Vol. 5404, Proceedings of SPIE (The International Society for Optical Engineering, 2004) . Google Scholar
M. Ladeset al., IEEE Trans. Comput. 42, 301 (1993), DOI: 10.1109/12.210173. Google Scholar
W. Zhaoet al., ACM Computing Surveys (CSUR) 35(4), 399 (2003), DOI: 10.1145/954339.954342. Crossref, Google Scholar
U. Handmannet al., Image Vision Comput. 18(5), 367 (2000), DOI: 10.1016/S0262-8856(99)00032-3. Crossref, Google Scholar
H. M. Hunke, Locating and tracking of human faces with neural networks, Master's thesis, University of Karlsruhe (1994) . Google Scholar
S. Wiegand, C. Igel and U. Handmann, Evolutionary optimization of neural networks for face detection, 12th European Symposium, on Artificial Neural Networks (ESANN 2004), ed. M. Verleysen (d-side publications, 2004) pp. 139–144. Google Scholar
C. C. Coello , D. Van Veldhuizen and G. Lamont , Evolutionary Algorithms for Solving Multi-objective Problems ( Kluwer Academic Publishers , New York , 2002 ) . Crossref, Google Scholar
K. Deb , Multi-Objective Optimization using Evolutionary Algorithms ( John Wiley & Sons , Chichester, UK , 2001 ) . Google Scholar
H. A. Abbass, Neural Comput. 15(11), 2705 (2003), DOI: 10.1162/089976603322385126. Crossref, Google Scholar
Y. Jin, T. Okabe and B. Sendhoff, Neural network regularization and ensembling using multi-objective evolutionary algorithms, Proceedings of Congress on Evolutionary Computation (CEC'04) (IEEE Press, 2004) pp. 1–8. Google Scholar
K. Debet al., IEEE Trans. Evol. Comput. 6(2), 182 (2002), DOI: 10.1109/4235.996017. Crossref, Google Scholar
G. P. Zhang, IEEE Trans. Syst. Man Cybernet. — Part C 30(4), (2000). Google Scholar
M.-H. Yang, D. J. Kriegman and N. Ahuja, IEEE Trans. Pattern Anal. Much. Intell. 24(1), 34 (2002). Crossref, Google Scholar
E. Hjelmas and B. K. Low, Gomput. Vision Image Understanding 83, 236 (2001), DOI: 10.1006/cviu.2001.0921. Crossref, Google Scholar
P. L. Bartlett, IEEE Trans. Inf. Theory 44(2), 525 (1998), DOI: 10.1109/18.661502. Crossref, Google Scholar
R. Caruana, S. Lawrence and C. L. Giles, Advances in Neural Information Processing Systems 13 (MIT Press, Denver, Colorado, 2001) pp. 402–408. Google Scholar
S. Nolfi, The Handbook of Brain Theory and Neural Networks, 2nd edn., ed. M. A. Arbib (MIT Press, 2002) pp. 415–418. Google Scholar
X. Yao, Proc. IEEE 87(9), 1423 (1999). Google Scholar
R. D. Reed and J. Marks II , Neural Smithing ( MIT Press , 1999 ) . Crossref, Google Scholar
A. Stahlberger and M. Riedmiller, Advances in Neural Information Processing Systems 9, eds. M. C. Mozer, M. I. Jordan and T. Petsche (The MIT Press, 1997) pp. 655–661. Google Scholar
H. A. Rowley, S. Baluja and T. Kanade, IEEE Trans. Pattern Anal. Much. Intell. 20(1), 23 (1998), DOI: 10.1109/34.655647. Crossref, Google Scholar
H. Braun , Neurale Netze: Optimierung durch Lernen und Evolution ( Springer-Verlag , 1997 ) . Crossref, Google Scholar
L. D. Whitley, The GENITOR algorithm and selection pressure: Why rank-based allocation of reproductive trials is best, Proceedings of the Third International Conference on Genetic Algorithms, ICGA 1989, ed. J. D. Schaffer (Morgan Kaufmann, Fairfax, VA, USA, 1989) pp. 116–121. Google Scholar
C. Igel and M. Hüsken, Neurocomputing 50(C), 105 (2003), DOI: 10.1016/S0925-2312(01)00700-7. Crossref, Google Scholar
M. Riedmiller, Comput. Standards Interfaces 16(5), 265 (1994), DOI: 10.1016/0920-5489(94)90017-5. Crossref, Google Scholar
L. Prechelt, Neural Networks: Tricks of the Trade, Lecture Notes in Computer Science 1524, eds. G. B. Orr and K.-R. Müller (Springer-Verlag, 1999) pp. 57–69. Google Scholar
D. B. Fogel , Evolutionary Computation: Toward a New Philosophy of Machine Intelligence ( IEEE Press , Piscataway, NJ, USA , 1995 ) . Google Scholar
E. Zitzler , Evolutionary Algorithms for Multiobjective Optimization: Methods and Applications ( Shaker Verlag , Aachen, Germany , 1999 ) . Google Scholar
A. E. Eiben, R. Hinterding and Z. Michalewicz, IEEE Trans. Evol. Comput. 3(2), 124 (1999), DOI: 10.1109/4235.771166. Crossref, Google Scholar
C. Igel and M. Kreutz, Neurocomputing 55(1–2), 347 (2003), DOI: 10.1016/S0925-2312(02)00628-8. Crossref, Google Scholar
J. E. Smith and T. C. Fogarty, Soft Comput. 1(2), 81 (1997). Crossref, Google Scholar
L. Davis, Adapting operator probabilities in genetic algorithms, Proceedings of the Third International Conference on Genetic Algorithms, ICGA'89, ed. J. D. Schaffer (Morgan Kaufmann, Fairfax, VA, USA, 1989) pp. 61–69. Google Scholar
T. Okabe, Y. Jin and B. Sendhoff, A critical survey of performance indices for multi-objective optimisation, Proceedings of the 2003 Congress on Evolutionary Computation (CEC'03) (IEEE Press, 2003) pp. 1053–1060. Google Scholar
E. Zitzleret al., IEEE Trans. Evol. Comput. 7(2), 117 (2003), DOI: 10.1109/TEVC.2003.810758. Crossref, Google Scholar