Abstract
In this paper, we mainly investigate a fast algorithm, Extreme Learning Machine (ELM), on its equivalent relationship, approximation capability and real-time face detection application. Firstly, an equivalent relationship is presented for neural networks without orthonormalization (ELM) and orthonormal neural networks. Secondly, based on the equivalent relationship and the universal approximation of orthonormal neural networks, we successfully prove that neural networks with ELM have the property of universal approximation, and adjustable parameters of hidden neurons and orthonormal transformation are not necessary. Finally, based on the fast learning characteristic of ELM, we successfully combine ELM with AdaBoost algorithm of Viola-Jones in face detection applications such that the whole system not only retains a real-time learning speed, but also possesses high face detection accuracy.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Yang, M.H., Kriegman, D.J., Member, S., Ahuja, N.: Detecting faces in images: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 24(1), 34–58 (2002)
Pan, Y., Ge, S.S., Mamun, A.A.: Weighted locally linear embedding for dimension reduction. Pattern Recognitioin 42, 798–811 (2009)
Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proceeding of IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2001), Kauai Marriott, Hawaii, US, December 9-14, pp. 511–518 (2001)
Viola, P., Jones, M.: Robust real-time face detection. International Journal of Computer Vision 57(2), 137–154 (2004)
Hornik, K.: Approximation capabilities of multilayer feedforward networks. Neural Networks 4, 251–257 (1991)
Ito, Y.: Approximation of continuous functions on R d by linear combinations of shifted rotations of a sigmoid function with and without scaling. Neural Networks 5, 105–115 (1992)
Huang, G.B., Zhu, Q.Y., Siew, C.K.: Extreme learning machine: Theory and applications. Neurocomputing 70, 489–501 (2006)
Royden, H.L.: Real Analysis, 3rd edn. Macmillan Publishing Company, New York (1988)
Kaminski, W., Strumillo, P.: Kernel orthonormalization in radial basis function neural networks. IEEE Transactions on Neural Networks 8(5), 1177–1183 (1997)
Ortega, J.M.: Matrix theory. Plenum Press, New York (1987)
Lancaster, P., Tismenetsky, M.: The theory of matrices. Academic Press, London (1984)
Stein, E.M., Shakarchi, R.: Real Analysis: Measure Theory, Integration, and Hilbert Spaces. Princeton University Press, Princeton (2005)
Serre, D.: Matrices: Theory and Applications. Springer, New York (2002)
Rao, C.R., Mitra, S.K.: Generalized Inverse of Matrices and Its applications. John Wiley & Sons, Inc., New York (1971)
Tamura, S., Tateishi, M.: Capabilities of a four-layer feedforward neural network: Four layers versus three. IEEE Transactions on Neural Networks 8(2), 251–255 (1997)
Blake, C., Merz, C.: UCI repository of machine learning databases. Department of Information and Computer Sciences, University of California, Irvine, USA (1998), http://www.ics.uci.edu/~mlearn/MLRepository.html
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ge, S.S., Pan, Y., Zhang, Q., Chen, L. (2009). Equivalent Relationship of Feedforward Neural Networks and Real-Time Face Detection System. In: Kim, JH., et al. Advances in Robotics. FIRA 2009. Lecture Notes in Computer Science, vol 5744. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-03983-6_34
Download citation
DOI: https://doi.org/10.1007/978-3-642-03983-6_34
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-03982-9
Online ISBN: 978-3-642-03983-6
eBook Packages: Computer ScienceComputer Science (R0)