Abstract
This paper describes a method to minimize the immense training time of the conventional Adaboost learning algorithm in object detection by reducing the sampling area. A new algorithm with respect to the geometric and accordingly the symmetric relations of the analyzed object is presented. Symmetry enhanced Adaboost (SEAdaboost) can limit the scanning area enormously, depending on the degree of the objects symmetry, while it maintains the detection rate. SEAdaboost allows to take advantage of the symmetric characteristics of an object by concentrating on corresponding symmetry features during the detection of weak classifiers. In our experiments we gain 39% reduced training time (in average) with slightly increasing detection rates (up to 2.4% and up to 6% depending on the object class) compared to the conventional Adaboost algorithm.
This is a preview of subscription content, log in via an institution to check access.
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
Viola, P., Jones, M.J.: Robust real-time face detection. International Journal of Computer Vision 57, 137–154 (2004)
Freund, Y., Schapire, R.E.: A short introduction to boosting. Journal of Japanese Society for Artificial Intelligence 14, 771–780 (1999)
Freund, Y., Schapire, R.E.: Experiments with a new boosting algorithm. In: Proceedings of the Thirteenth International Conference, pp. 148–156 (1996)
Loy, G., Eklundh, J.O.: Detecting symmetry and symmetric constellations of features. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3952, pp. 508–521. Springer, Heidelberg (2006)
Kearns, M.: Thoughts on hypothesis boosting. Unpublished manuscript (1988)
Kearns, M., Vazirani, U.V.: An introduction to computational learning theory. MIT Press, Cambridge (1994)
Warmuth, M.K., Glocer, K.A., Vishwanathan, S.: Entropy regularized lpboost. In: Freund, Y., Györfi, L., Turán, G., Zeugmann, T. (eds.) ALT 2008. LNCS (LNAI), vol. 5254, pp. 256–271. Springer, Heidelberg (2008)
Warmuth, M.K., Glocer, K., Raetsch, G.: Boosting algorithms for maximizing the soft margin. In: Advances in Neural Information Processing Systems, vol. 20, pp. 1585–1592. MIT Press, Cambridge (2008)
Viola, P., Platt, J.C., Zhang, C.: Multiple instance boosting for object detection. In: Advances in Neural Information Processing, vol. 18, pp. 1417–1426 (2007)
Li, S.Z., Zhang, Z., Shum, H.Y., Zhang, H.: Floatboost learning for classification. In: Advances in Neural Information Processing Systems. Microsoft Research Asia (2002)
Jiang, J.L., Loe, K.F.: S-adaboost and pattern detection in complex environment. In: Proceedings of the 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2003), pp. 413–418 (2003)
Crowther, P.S., Cox, R.J.: A method for optimal division of data sets for use in neural networks. In: Khosla, R., Howlett, R.J., Jain, L.C. (eds.) KES 2005. LNCS (LNAI), vol. 3684, pp. 1–7. Springer, Heidelberg (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Baumann, F., Ernst, K., Ehlers, A., Rosenhahn, B. (2010). Symmetry Enhanced Adaboost. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2010. Lecture Notes in Computer Science, vol 6453. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-17289-2_28
Download citation
DOI: https://doi.org/10.1007/978-3-642-17289-2_28
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-17288-5
Online ISBN: 978-3-642-17289-2
eBook Packages: Computer ScienceComputer Science (R0)