Abstract
In this paper we extend a method that uses image patch histograms and discriminative training to recognize objects in cluttered scenes. The method generalizes and performs well for different tasks, e.g. for radiograph recognition and recognition of objects in cluttered scenes. Here, we further investigate this approach and propose several extensions. Most importantly, the method is substantially improved by adding multi-scale features so that it better accounts for objects of different sizes. Other extensions tested include the use of Sobel features, the generalization of histograms, a method to account for varying image brightness in the PCA domain, and SVMs for classification. The results are improved significantly, i.e. on average we have a 59% relative reduction of the error rate and we are able to obtain a new best error rate of 1.1% on the Caltech motorbikes task.
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
Darroch, J.N., Ratcliff, D.: Generalized Iterative Scaling for Log-Linear Models. Annals of Mathematical Statistics 43(5), 1470–1480 (1972)
Deselaers, T., Keysers, D., Ney, H.: Features for Image Retrieval – A Quantitative Comparison. In: Rasmussen, C.E., Bülthoff, H.H., Schölkopf, B., Giese, M.A. (eds.) DAGM 2004. LNCS, vol. 3175, pp. 228–236. Springer, Heidelberg (2004)
Deselaers, T., Keysers, D., Ney, H.: Discriminative Training for Object Recognition using Image Patches. In: CVPR, San Diego, CA (June 2005) (in press)
Dorko, G., Schmid, C.: Selection of Scale-Invariant Parts for Object Class Recognition. In: ICCV, Nice, France, October 2003, vol. 1, pp. 634–640 (2003)
Fergus, R., Perona, P., Zissermann, A.: Object Class Recognition by Unsupervised Scale-Invariant Learning. In: CVPR, Blacksburg, VG, June 2003, pp. 264–271 (2003)
Fussenegger, M., Opelt, A., Pinz, A., Auer, P.: Object Recognition Using Segmentation for Feature Detection. In: ICPR, Cambridge, UK, August 2004, vol. 3, pp. 41–48 (2004)
Keysers, D., Och, F.-J., Ney, H.: Maximum Entropy and Gaussian Models for Image Object Recognition. In: Van Gool, L. (ed.) DAGM 2002. LNCS, vol. 2449, pp. 498–506. Springer, Heidelberg (2002)
Keysers, D., Gollan, C., Ney, H.: Local Context in Non-linear Deformation Models for Handwritten Character Recognition. In: ICPR, Cambridge, UK, August 2004, vol. 4, pp. 511–514 (2004)
Kölsch, T., Keysers, D., Ney, H., Paredes, R.: Enhancements for Local Feature Based Image Classification. In: ICPR, August 2004, vol. 1, pp. 248–251 (2004)
Leibe, B., Schiele, B.: Scale Invariant Object Categorization Using a Scale-Adaptive Mean-Shift Search. In: Rasmussen, C.E., Bülthoff, H.H., Schölkopf, B., Giese, M.A. (eds.) DAGM 2004. LNCS, vol. 3175, pp. 145–153. Springer, Heidelberg (2004)
Loupias, E., Sebe, N., Bres, S., Jolion, J.: Wavelet-based Salient Points for Image Retrieval. In: ICIP, Vancouver, Canada, September 2000, vol. 2, pp. 518–521 (2000)
Martinez, A., Kak, A.: PCA versus LDA. IEEE TPAMI 23(2), 228–233 (2001)
Mohan, A., Papageorgiou, C., Poggio, T.: Example-based Object Detection in Images by Components. IEEE TPAMI 23(4), 349–361 (2001)
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)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Deselaers, T., Keysers, D., Ney, H. (2005). Improving a Discriminative Approach to Object Recognition Using Image Patches. In: Kropatsch, W.G., Sablatnig, R., Hanbury, A. (eds) Pattern Recognition. DAGM 2005. Lecture Notes in Computer Science, vol 3663. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11550518_41
Download citation
DOI: https://doi.org/10.1007/11550518_41
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28703-2
Online ISBN: 978-3-540-31942-9
eBook Packages: Computer ScienceComputer Science (R0)