Abstract
The problem of recognizing classes of objects as opposed to special instances requires methods of comparing images that capture the variation within the class while they discriminate against objects outside the class. We present a simple method for image description based on histograms of qualitative shape indexes computed from the combination of triplets of sampled locations and gradient directions in the image. We demonstrate that this method indeed is able to capture variation within classes of objects and we apply it to the problem of recognizing four different categories from a large database. Using our descriptor on the whole image, containing varying degrees of background clutter, we obtain results for two of the objects that are superior to the best results published so far for this database. By cropping images manually we demonstrate that our method has a potential to handle also the other objects when supplied with an algorithm for searching the image. We argue that our method, based on qualitative image properties, capture the large range of variation that is typically encountered within an object class. This means that our method can be used on substantially larger patches of images than existing methods based on simpler criteria for evaluating image similarity.
Keywords
Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
References
Belongie, S., Malik, J.: Matching with Shape Contexts. In: Proc. 8th International Conference on Computer Vision, ICCV 2001 (2001)
Borenstein, E., Ullman, S.: Class-Specific, Top-Down Segmentation. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2351, pp. 109–122. Springer, Heidelberg (2002)
Burl, M.C., Weber, M., Perona, P.: A probabilistic approach to object recognition. In: Burkhardt, H., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1407, pp. 628–641. Springer, Heidelberg (1998)
Carlsson, S.: Order Structure, Correspondence and Shape Based Categories. In: Forsyth, D., Mundy, J.L., Di Gesú, V., Cipolla, R. (eds.) Shape, Contour, and Grouping 1999. LNCS, vol. 1681, p. 58. Springer, Heidelberg (1999)
Carlsson S. and Sullivan J. Action Recognition by Shape Matching to Key Frames Workshop on Models versus Exemplars in Computer Vision, Kauai, Hawaii, USA December 14th, 2001
Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning, CVPR03(II: 264-271). IEEE Abstract. IEEE Top Reference. 0307 BibRef
Schiele, B., Crowley, J.: Recognition without Correspondence using Multidimensional Receptive Field Histograms. IJCV 36(1), 31–50 (2000)
Schneiderman, H.: A Statistical Approach to 3D Object Detection Applied to Faces and Cars. In: Proc. CVPR 2000 (2000)
Sung, K.K., Poggio, T.: Example-Based Learning for View-Based Human Face Detection. PAMI 20(1), 39–51 (1998)
Thompson, W.D.: On growth and form. Dover, Mineola (1917)
Thureson, J., Carlsson, S.: Finding Object Categories in Cluttered Images Using Minimal Shape Prototypes. In: Proc. Scandinavian Conference on Image Analysis, pp. 1122–1129 (2003)
Weber, M.: Unsupervised Learning of Models for Visual Object Class Recognition, PhD thesis, California Institute of Technology, Pasadena,CA (2000)
Weber, M., Welling, M., Perona, P.: Unsupervised Learning of Models for Visual Object Class Recognition. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1842, pp. 18–32. Springer, Heidelberg (2000)
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
Thureson, J., Carlsson, S. (2004). Appearance Based Qualitative Image Description for Object Class Recognition. In: Pajdla, T., Matas, J. (eds) Computer Vision - ECCV 2004. ECCV 2004. Lecture Notes in Computer Science, vol 3022. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24671-8_41
Download citation
DOI: https://doi.org/10.1007/978-3-540-24671-8_41
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-21983-5
Online ISBN: 978-3-540-24671-8
eBook Packages: Springer Book Archive