Abstract
This paper proposes a preprocessing filter fusion for efficient face recognition.Since no priori knowledge of system working environment can be assumed. The proposed method can decide an optimal configuration of filter by exploring the filter fusion to unknown illumination conditions. In this paper, we propose to investigate how to preprocess an input face image for the task of robust face recognition, especially in changing illumination environment (bad illumination). We found that the performance of each preprocessing method for compensating illumination is highly affected by working illumination environment. Changing illumination poses a most challenging problem in face recognition. A previous research for illumination compensation has been investigated. The illumination filter includes Retinex filter, end-in contrast stretching and histogram equalization filter. The proposed method has been tested to robust face recognition in varying illumination conditions (our lab, FERET DB). We made in illumination cluster using combined FART and RBF, K-means algorithm. Extensive experiment shows that the proposed system can achieve very encouraging performance in varying illumination environments. We furthermore show how this algorithm can be extended towards face recognition across illumination.
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.
References
Lee, S.Y.: Illumination Direction and Scale Robust Face Recognition using Logpolar and Background Illumination Modeling, Thesis, Inha University, Korea (2002)
Liu, H., et al.: Illumination Compensation and Feedback of Illumination Feature in Face Detection. In: Proc. International Conferences on Information-technology and Information-net, Beijing, vol. 3, pp. 444–449 (2001)
Gonzalez, R.C., Woods, R.E.: Digital Image Processing. Addison-Wesley, Reading (1992)
Moore, A.: Real-time Neural System for color Constancy. IEEE Transactions on Neural Networks 2(2) (1991)
Funt, B.V., Ciurea, F., McCann, J.: Retinex in Matlab. In: Proc. of IS&T/SID Eighth Color Imaging Conference, pp. 112–121 (2000)
Jobson, D.J., Rahman, Z.-u., Woodell, G.A.: The Spatial Aspect of Color and Scientific Implications of Retinex Image Processing
Funt, B., Barnard, K.: Luminance-Based Multi-Scale Retinex. In: rmalize proceedings AIC Colour 1997 8th Congress of the International Colour Association (1997)
Bossmaier, T.R.J.: Efficient image representation by Gabor functions. In: Kulikowsji, J.J., Dicknson, C.M., Murray, I.J. (eds.) An information theory approach, pp. 698–704. Pergamon Press, Oxford
Savvides, M., Vijaya Kumar, B.V.K., Khosla, P.K.: Robust, Shift-Invariance Biometric Identification from Partial Face Images. Presented at Proc of SPIE, Biometric Technologies for Human Identifications (OR51), Orlando, FL (2004)
Savvides, M., Vijaya Kumar, B.V.K.: Quad Phase Minimum Average Correlation Energy Filters for Reduced Memory Illumination Tolerant Face Authentication. In: Kittler, J., Nixon, M.S. (eds.) AVBPA 2003. LNCS, vol. 2688, pp. 19–26. Springer, Heidelberg (2003)
Georghiades, S., Belhumeur, P.N., Kriegman, D.J.: From Few to Many: Illumination One Models for face recognition under Variable Lighting and Pose. IEEE Trans. on PAMI 23(6), 643–660 (2001)
Phillips, P.: The FERET database and evaluation procedure for face recognition algorithms. Image and Vision Computing 16(5), 295–306 (1999)
FRVT 2000 Evaluation Report, by Blackburn, D.M., Bone, J.M., Phillips, P.J. (February 2001)
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
Nam, M.Y., Rhee, P.K. (2005). Hybrid Filter Fusion for Robust Visual Information Processing. In: Khosla, R., Howlett, R.J., Jain, L.C. (eds) Knowledge-Based Intelligent Information and Engineering Systems. KES 2005. Lecture Notes in Computer Science(), vol 3684. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11554028_27
Download citation
DOI: https://doi.org/10.1007/11554028_27
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28897-8
Online ISBN: 978-3-540-31997-9
eBook Packages: Computer ScienceComputer Science (R0)