Abstract
The performance of face recognition system is greatly affected by the illumination changes. In this article, we propose a method of face illumination compensation based on neural network and wavelet. It sufficiently combines multi-resolution analysis of wavelet and the self-adaptation learning and good spread ability of BP neural network, thus this method carries out the face illumination compensation. The theory and experiments prove that this method solves the problem of illumination compensation efficiently in the face detection and recognition process. It improves the face detection and recognition under different illumination conditions. Moreover, it has good robustness and can be used in a wide range.
Supported by the National High-Tech Research and Development Plan of China under Grant No.2004AA001110(863).
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Phillips, P.J., Moon, H., et al.: The FERET Evaluation Methodology for Face- Recognition Algorithms. IEEE TPAMI 22, 1090–1104 (2000)
Phillips, P.J., Grother, P., Micheals, R.J., Blackburn, D.M., Tabassi, E., Bone, J.M.: FRVT (2002), Evaluation Report, http://www.frvt.org/DLs/FRVT_2002_Evaluation_Report.pdf
Moses, Y., Ullman, S.: Limitation of Non-Model-Based Recognition Schemes. In: Sandini, G. (ed.) ECCV 1992. LNCS, vol. 588, pp. 820–828. Springer, Heidelberg (1992)
Warrington, E., Taylor, A.: Two Categorical Stages of Object Recognition (Perception) 7, 152–164 (1978)
Sim, T., Kanade, T.: Combining Models and Exemplars for Face Recognition: An Illuminating Example. In: CVPR (2001)
Chen, H.F., Belhumeur, P.N., Jacobs, D.W. In Search of Illumination Invariants. In: CVPR (2000)
Riklin-Raviv, T., Shashua, A.: The Quotient Image: Class Based Recognition and Synthesis Under Varying Illumination Conditions. In: CVPR (1999)
Basri, R., Jacobs, D.L.: Reflectance and Linear Subspaces. In: Proc. Eighth IEEE Int’l Conf. Computer Vision, pp. 383–390 (2001)
Georghiades, A.S., Belhumeur, P.N., Kriegman, D.J.: From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose. IEEE Trans. PAMI 23, 643–660 (2001)
Murase, H., Nayar, S.: Visual Learning and Recognition of 3D Object from Appearance. IJCV 14, 5–24 (1995)
Shashua, A., Riklin-Raviv, T.: The Quotient Image: Class-Based Re-Rendering and Recognition with Varying Illuminations. IEEE Trans. on PAMI 23, 129–139 (2001)
Phillips, P.J., Vardi, Y.: Efficient Illumination Normalization of Facial Images. PRL 17, 921–927 (1996)
Zhao, W., Chellappa, R.: Illumination-insensitive Face Recognition Using Symmetric Shape-from-Shading. In: Proc. Conf. Computer Vision and Pattern. Recog., pp. 1286–1293 (2000)
Adini, Y., Moses, Y., Ullman, S.: Face Recognition: The Problem of Compensating for Changes in Illumination Direction. IEEE Transactions on Pattern Analysis and Machine Intelligence, 721–732 (1997)
Terence, S., Simon, B., Maan, B.: The CMU Pose, Illumination, and Expression (PIE) Database of Human Faces. Robotics Institute, Carnegie Mellon University, Pittsburgh, PA (2001)
Peng, Q.S., Bao, H.J., Jin, X.G.: Procedural Elements for Realistic Image Synthesis. Science Press, Peking (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zhang, Z., Ma, S., Wu, D. (2005). The Application of Neural Network and Wavelet in Human Face Illumination Compensation. In: Wang, J., Liao, XF., Yi, Z. (eds) Advances in Neural Networks – ISNN 2005. ISNN 2005. Lecture Notes in Computer Science, vol 3497. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11427445_133
Download citation
DOI: https://doi.org/10.1007/11427445_133
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-25913-8
Online ISBN: 978-3-540-32067-8
eBook Packages: Computer ScienceComputer Science (R0)