Abstract
In this paper the problem of recognizing textureless objects in unconstrained illumination and material conditions is investigated. We evaluate the discriminative power of various low-level image features for a pixelwise representation of the underlying surface characteristics of the object. For this purpose, a new dataset with rendered images of 3D models is used which allows to directly compare the influences of texture and material properties in an object recognition scenario. The results are further validated on a dataset of real object images and finally reveal that jets of single- and multi-scale even Gabor filter responses outperform other proposed features in scenarios with textureless objects and strong variations of illumination.
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
Adini, Y., Moses, Y., Ullman, S.: Face recognition: The problem of compensating for changes in illumination direction. PAMI 19(7), 721–732 (1997)
Barrow, H., Tenenbaum, J.: Recovering intrinsic scene characteristics from images. Computer Vision Systems, 3–26 (1978)
Basri, R., Jacobs, D.: Lambertian reflectance and linear subspaces. PAMI 25(2), 218–233 (2003)
Brown, M., Hua, G., Winder, S.: Discriminative learning of local image descriptors. PAMI 33(1), 43–57 (2011)
Chen, H., Belhumeur, P., Jacobs, D.: In search of illumination invariants. In: CVPR, pp. 254–261 (2000)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR, pp. 886–893
Freeman, W., Adelson, E.: The design and use of steerable filters. PAMI 13(9), 891–906 (1991)
Gabor, D.: Theory of communication. Journal of the Institute of Electrical Engineers 93, 429–457 (1946)
Georghiades, A., Belhumeur, P., Kriegman, D.: From few to many: Illumination cone models for face recognition under variable lighting and pose. PAMI 23(6), 643–660 (2001)
Geusebroek, J., Burghouts, G., Smeulders, A.: The amsterdam library of object images. IJCV 61(1), 103–112 (2005)
Gopalan, R., Jacobs, D.: Comparing and combining lighting insensitive approaches for face recognition. CVIU 114(1), 135–145 (2010)
Kamarainen, J., Kyrki, V., Kalviainen, H.: Invariance properties of gabor filter-based features-overview and applications. TIP 15(5), 1088–1099 (2006)
Lowe, D.: Distinctive image features from scale-invariant keypoints. IJCV 60(2), 91–110 (2004)
Moreels, P., Perona, P.: Evaluation of features detectors and descriptors based on 3d objects. IJCV 73(3), 263–284 (2007)
Osadchy, M., Jacobs, D., Lindenbaum, M.: Surface dependent representations for illumination insensitive image comparison. PAMI 29(1), 98–111 (2007)
Van De Sande, K., Gevers, T., Snoek, C.: Evaluating color descriptors for object and scene recognition. PAMI 32(9), 1582–1596 (2010)
Wang, H., Li, S., Wang, Y.: Face recognition under varying lighting conditions using self quotient image. In: FG, pp. 819–824 (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zambanini, S., Kampel, M. (2013). Evaluation of Low-Level Image Representations for Illumination-Insensitive Recognition of Textureless Objects. In: Petrosino, A. (eds) Image Analysis and Processing – ICIAP 2013. ICIAP 2013. Lecture Notes in Computer Science, vol 8156. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-41181-6_8
Download citation
DOI: https://doi.org/10.1007/978-3-642-41181-6_8
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-41180-9
Online ISBN: 978-3-642-41181-6
eBook Packages: Computer ScienceComputer Science (R0)