Abstract
We consider the problem of image comparison in order to match smooth surfaces under varying illumination. In a smooth surface nearby surface normals are highly correlated. We model such surfaces as Gaussian processes and derive the resulting statistical characterization of the corresponding images. Supported by this model, we treat the difference between two images, associated with the same surface and different lighting, as colored Gaussian noise, and use the whitening tool from signal detection theory to construct a measure of difference between such images. This also improves comparisons by accentuating the differences between images of different surfaces. At the same time, we prove that no linear filter, including ours, can produce lighting insensitive image comparisons. While our Gaussian assumption is a simplification, the resulting measure functions well for both synthetic and real smooth objects. Thus we improve upon methods for matching images of smooth objects, while providing insight into the performance of such methods. Much prior work has focused on image comparison methods appropriate for highly curved surfaces. We combine our method with one of these, and demonstrate high performance on rough and smooth objects.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Belhumeur, P.N., Hespanha, J.P., Kriegman, D.J.: Eigenfaces vs. fisherfaces: Recognition using class-specific linear projection. PAMI 19(7), 711–720 (1997)
Bichsel, M.: Strategies of Robust Object Recognition for the Identification of Human Faces. ETH, Zurich (1991)
Brunelli, R., Pggio, T.: Face recognition: Features versus templates. PAMI 15(10), 1042–1062 (1993)
Bundschuh, B.: A linear predictor as a regularization function in adaptive image restoration and reconstruction. In: Chetverikov, D., Kropatsch, W.G. (eds.) CAIP 1993. LNCS, vol. 719. Springer, Heidelberg (1993)
Bundschuh, H., Schulz, B., Schneider, D.: Adaptive least squares image restoration using whitening filters of short length. In: Second HST Image Restoration Workshop (1993)
Chen, H.F., Belhumeur, P.N., Jacobs, D.W.: In search of illumination invariants. In: CVPR 2000, pp. I:254–261 (2000)
Cox, M.L., Miller, I.J., Bloom, J.A.: Digital Watermarking. Morgan Kaufmann, San Francisco (2002)
Depovere, T., Kalker, G., Linnartz, J.P.: Improved watermark detection using filtering before correlation. In: IEEE Int. Conf. on Image Processing, pp. I:430– 434 (1998)
Faugeras, O.D., Pratt, W.K.: Decorrelation methods of texture feature extraction. PAMI 2(4), 323–332 (1980)
Haralick, R.M., Shapiro, L.G.: Computer and robot vision. Addison-Wesley, Reading (1992)
Jacobs, D.W., Belhumeur, P.N., Basri, R.: Comparing images under variable illumination. In: CVPR 1998, pp. 610–617 (1998)
Jain, A.K.: Fundamentals of digital image processing. Prentice Hall, Englewood Cliffs (1989)
Lades, M., Vorbruggen, J.C., Buhmann, J., Lange, J., von der Malsburg, C., Wurtz, R.P., Konen, W.: Distortion invariant object recognition in the dynamic link architecture. TC 42(3), 300–311 (1993)
Lin, Z., Attikiouzel, Y.: Two-dimensional linear prediction model-based decorrelation method. PAMI 11(6), 661–665 (1989)
Osadchy, M., Lindenbaum, M., Jacobs, D.W.: Whitening for photometric comparison of smooth surfaces under varying illumination. In: IEEE workshop on Statistical and Computational Theories of Vision (October 2003)
Papoulis, A.: Probability, Random Variables, and Stochastic Processes, 3rd edn. McGraw Hill, New York (1991)
Pratt, W.K.: Digital Image Processing, 1st edn. Wiley, Chichester (1978)
Ravela, S., Luo, C.: Appearance-based global similarity retrieval of images. In: Bruce Croft, W. (ed.). Kluwer Academic Publisher, Dordrecht (2000)
Van Trees, H.L.: Detection, Estimation, and Modulation Theory Part I. Wiley, New-York (1965)
Yaroslavsky, L.P.: Digital Picture Processing. An Introduction. Springer, Heidelberg (1985)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Osadchy, M., Lindenbaum, M., Jacobs, D. (2004). Whitening for Photometric Comparison of Smooth Surfaces under Varying Illumination. In: Pajdla, T., Matas, J. (eds) Computer Vision - ECCV 2004. ECCV 2004. Lecture Notes in Computer Science, vol 3024. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24673-2_18
Download citation
DOI: https://doi.org/10.1007/978-3-540-24673-2_18
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-21981-1
Online ISBN: 978-3-540-24673-2
eBook Packages: Springer Book Archive