Abstract
We propose a novel classifier that both classifies surface texture and simultaneously estimates the unknown illumination conditions. A new formal model of the dependency of texture features on lighting direction is developed which shows that their mean vectors are trigonometric functions of the illuminations’ tilt and slant angles. This is used to develop a probabilistic description of feature behaviour which forms the basis of the new classifier. Given a feature set from an image of an unknown texture captured under unknown illumination conditions the algorithm first estimates the most likely illumination direction for each possible texture class. These estimates are used to calculate the class likelihoods and the classification is made accordingly.
The ability of the classifier to estimate illuminant direction, and to assign the correct class, was tested on 55 real texture samples in two stages. The classifier was able to accurately estimate both the tilt and the slant angles of the light source for the majority of textures and gave a 98% classification rate.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Chantler, M.J. 1995. Why illuminant direction is fundamental to texture analysis. IEE Proc. Vision, Image and Signal Processing, 142(4):199–206.
Chantler, M.J. and McGunnigle, G. 1995. Compensation of illuminant tilt variation for texture classification. In Proceedings of 5th International Conference on Image Processing and its Applications, pp. 767–761.
Chantler, M.J., Schmidt, M., Petrou, M., and McGunnigle, G. 2002. The effect of illuminant rotation on texture filters: Lissajous’s ellipses. In ECCV2002, European Conference on Computer Vision, vol. III, pp. 289–303.
Cula, O.G. and Dana, K.J. 2001. Recognition methods for 3D textured surfaces. In Proceedings of SPIE, San Jose.
Dana, K.J. and Nayar, S.K. 1998. Histogram model for 3d textures. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 618–624.
Dana, K.J. and Nayar, S.K. 1999. Conrelation model for 3d texture. In Proceedings of ICCV99: IEEE International Conference on Computer Vision, pp. 1061–1067.
Dana, K.J., Nayar, S.K., van Ginneken, B., and Koenderink, J.J. 1997. Reflectance and texture of real-world surfaces. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 151–157.
Jain, A.K. and Fanokhnia, F. 1991. Unsupervised texture segmentation using Gabor filters. Pattern Recognition, 24(12):1167–1186.
Kube, P.R. and Pentland, A.P. 1988. On the imaging of fractal surfaces. IEEE Trans. on Pattern Analysis and Machine Intelligence, 10(5):704–707.
Laws, K.I. 1980. Textured image segmentation. <nt>Ph.D. thesis, Electrical Engineering, University of Southern California. </nt>
Leung, T. and Malik, J. 1999. Recognizing surfaces using three-dimensional textons. In Proceedings of ICCV99: IEEE International Conference on Computer Vision, pp. 1010–1017.
Leung, T. and Malik, J. 2001. Representing and recognizing the visual appearance of materials using three-dimensional textons. International Journal of Computer Vision, 43(1):29–44.
McGunnigle, G. and Chantler, M.J. 1997. A model-based technique for the classification of textured surfaces with illuminate direction invariance. In Proceedings of BMVC97: British Machine Vision Conference, vol. 2. pp. 470–479.
McGunnigle, G. and Chantler, M.J. 2001. Evaluating Kube and Pentland’s fiactal imaging model. IEEE 7ians. on Image Processing, 10(4):534–542.
Penirschke, A. 2002. Illumination invariant classification of 3d surface textures. Research Memorandum (RM/02/4).
Randen, T. and Husoy, J.H. 1999. Filtering for texture classification: A comparative study. IEEE Trans. on Pattern Analysis and Machine Intelligence, 21(4):291–310.
van Ginneken, B., Koenderink, J.J., and Dana, K.J. 1999. Texture histograms as a function of irradiation and viewing direction. International Journal of Computer Vision, 31(2/3): 169–184.
Varma, M. and Zisserrman, A. 2002. Classifying images of materials: Achieving viewpoint and illumination independence. In ECCV2002, European Conference on Computer Vision, pp. 255–271.
Varma, M. and Zisselman, A.P. 2002. Classifying materials from images: To cluster or not to cluster? In Texture2002: The 2nd Internanatinal Workshop on Texture Analysis and Synthesis, 1 June 2002, Copenhagen, pp. 139–144.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Chantler, M., Petrou, M., Penirsche, A. et al. Classifying Surface Texture while Simultaneously Estimating Illumination Direction. Int J Comput Vision 62, 83–96 (2005). https://doi.org/10.1023/B:VISI.0000046590.98379.19
Issue Date:
DOI: https://doi.org/10.1023/B:VISI.0000046590.98379.19