Abstract
In this paper we describe the first stage of a new learning system for object detection and recognition. For our system we propose Boosting [5] as the underlying learning technique. This allows the use of very diverse sets of visual features in the learning process within a common framework: Boosting — together with a weak hypotheses finder — may choose very inhomogeneous features as most relevant for combination into a final hypothesis. As another advantage the weak hypotheses finder may search the weak hypotheses space without explicit calculation of all available hypotheses, reducing computation time. This contrasts the related work of Agarwal and Roth [1] where Winnow was used as learning algorithm and all weak hypotheses were calculated explicitly. In our first empirical evaluation we use four types of local descriptors: two basic ones consisting of a set of grayvalues and intensity moments and two high level descriptors: moment invariants [8] and SIFTs [12]. The descriptors are calculated from local patches detected by an interest point operator. The weak hypotheses finder selects one of the local patches and one type of local descriptor and efficiently searches for the most discriminative similarity threshold. This differs from other work on Boosting for object recognition where simple rectangular hypotheses [22] or complex classifiers [20] have been used. In relatively simple images, where the objects are prominent, our approach yields results comparable to the state-of-the-art [3]. But we also obtain very good results on more complex images, where the objects are located in arbitrary positions, poses, and scales in the images. These results indicate that our flexible approach, which also allows the inclusion of features from segmented regions and even spatial relationships, leads us a significant step towards generic object recognition.
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
Agarwal, S., Roth, D.: Learning a sparse representation for object detection. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2353, pp. 113–130. Springer, Heidelberg (2002)
Dorko, G., Schmid, C.: Selection of scale-invariant parts for object class recognition. In: Proc. International Conference on Computer Vision (2003)
Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: Proc. CVPR 2003 (2003)
Freeman, W., Adelson, E.: The design and use of steerable filters. In: PAMI, pp. 891–906 (1991)
Freund, Y., Schapire, R.E.: A decision-theoretic generalisation of on-line learning. Computer and System Sciences 55(1) (1997)
Garg, A., Agarwal, S., Huang, T.S.: Fusion of global and local information for object detection. In: Proc. CVPR, vol. 2, pp. 723–726 (2002)
Gonzalez, R.C., Woods, R.E.: Digital Image Processing. Addison-Wesley, Reading (2001)
Van Gool, L., Moons, T., Ungureanu, D.: Affine / photometric invariants for planar intensity patterns. In: Buxton, B.F., Cipolla, R. (eds.) ECCV 1996. LNCS, vol. 1065, pp. 642–651. Springer, Heidelberg (1996)
Harris, C., Stephens, M.: A combined corner and edge detector. In: Proc. of the 4th ALVEY vision conference, pp. 147–151 (1988)
Laganiere, R.: A morphological operator for corner detection. Pattern Recognition 31(11), 1643–1652 (1998)
Lindeberg, T.: Feature detection with automatic scale selection. International Journal of Computer Vision (1996)
Lowe, D.G.: Object recognition from local scale-invariant features. In: Proc. ICCV, pp. 1150–1157 (1999)
Maass, W., Warmuth, M.: Efficient learning with virtual threshold gates. Information and Computation 141(1), 66–83 (1998)
Mahamud, S., Hebert, M., Shi, J.: Object recognition using boosted discriminants. In: Proc. CVPR, vol. 1, pp. 551–558 (2001)
Mikolajczyk, K., Schmid, C.: Indexing based on scale invariant interest points. In: Proc. ICCV, pp. 525–531 (2001)
Mikolajczyk, K., Schmid, C.: An affine invariant interest point detector. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 128–142. Springer, Heidelberg (2002)
Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. In: Proc. CVPR (2003)
Schmid, C., Mohr, R.: Local grayvalue invariants for image retrieval. In: PAMI, vol. 19, pp. 530–534 (1997)
Schmid, C., Mohr, R., Bauckhage, C.: Evaluation of interest point detectors. International Journal of Computer Vision, 151–172 (2000)
Schneiderman, H., Kanade, T.: Object detection using the statistics of parts. International Journal of Computer Vision (to appear)
Shilat, E., Werman, M., Gdalyahu, Y.: Ridge’s corner detection and correspondence. In: Computer Vision and Pattern Recognition, pp. 976–981 (1997)
Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proc. CVPR (2001)
Weber, M.: Unsupervised Learning of Models for Object Recognition. PhD thesis, California Institute of Technology, Pasadena, CA (2000)
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)
Wuertz, R.P., Lourens, T.: Corner detection in color images by multiscale combination of end-stopped cortical cells. In: International Conference on Artificial Neuronal Networks, pp. 901–906 (1997)
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
Opelt, A., Fussenegger, M., Pinz, A., Auer, P. (2004). Weak Hypotheses and Boosting for Generic Object Detection and 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_6
Download citation
DOI: https://doi.org/10.1007/978-3-540-24671-8_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-21983-5
Online ISBN: 978-3-540-24671-8
eBook Packages: Springer Book Archive