Abstract
This paper proposes an unsupervised learning technique for object recognition from an unlabelled and unordered set of training images. It enables the robust recognition of complex 3D objects in cluttered scenes, under scale changes and partial occlusion. The technique uses a matching based on the consistency of two different descriptors characterising the appearance and shape of local features. The variation of each local feature with viewing direction is modeled by a multi-view feature model. These multi-view feature models can be matched directly to the features found in a test image. This avoids a matching to all training views as necessary for approaches based on canonical views.
The proposed approach is tested with real world objects and compared to a supervised approach using features characterised by SIFT descriptors (Scale Invariant Feature Transform). These experiments show that the performance of our unsupervised technique is equal to that of a supervised SIFT object recognition approach.
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
Weber, M., Welling, M., Perona, P.: Unsupervised learning of models for recognition. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1842, pp. 18–32. Springer, Heidelberg (2000)
Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 264–271. IEEE Computer Society Press, Los Alamitos (2003)
Lowe, D.G.: Object recognition from local scale-invariant features. In: Proc. of the International Conference on Computer Vision ICCV, Corfu., pp. 1150–1157 (1999)
Lowe, D.: Local feature view clustering for 3d object recognition. In: IEEE CVPR (Conference on Computer Vision and Pattern Recognition), Kauai, Hawai, pp. 682–688 (2001)
Rothganger, F., Lazebnik, S., Schmid, C., Ponce, J.: 3d object modeling and recognition using affine-invariant patches and multi-view spatial constraints. In: CVPR (2003)
Ferrari, V., Tuytelaars, T., van Gool, L.: Integrating multiple model views for object recognition. In: CVPR, vol. II, pp. 105–112 (2004)
Leitner, R., Bischof, H.: Recognition of 3d objects by learning from correspondences in a sequence of unlabeled training images. In: DAGM (2005)
Thomas, A., Ferrari, V., Leibe, B., Tuytelaars, T., Schiele, B., van Gool, L.: Towards multi-view object class detection. In: IEEE Computer Vision and Pattern Recognition (CVPR), New York, IEEE Computer Society Press, Los Alamitos (2006)
Bülthoff, H.H., Wallraven, C., Graf, A.B.A.: View-based dynamic object recognition based on human perception. In: International Conference on Pattern Recognition, vol. 3, pp. 768–776 (2002)
Matas, J., Chum, O., Urban, M., Pajdla T.: Robust wide baseline stereo from maximally stable extremal regions. In: Proc. BMVC, pp. 384–393 (2002)
Rui, Y., She, A.C., Huang, T.S.: Modified fourier descriptors for shpae representation - a practical approach. In: First International Workshop on Image Databases and Multi Media Search (1996)
Kuhn, H.W.: The Hungarian method for the assignment problem. In: Naval Research Logistics Quarterly, vol. 2, pp. 83–97 (1955)
Munkres, J.R.: Algorithms for the assignment and transportation problems. SIAM 5, 32–38 (1957)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Leitner, R. (2007). Learning 3D Object Recognition from an Unlabelled and Unordered Training Set. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2007. Lecture Notes in Computer Science, vol 4841. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-76858-6_62
Download citation
DOI: https://doi.org/10.1007/978-3-540-76858-6_62
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-76857-9
Online ISBN: 978-3-540-76858-6
eBook Packages: Computer ScienceComputer Science (R0)