Abstract
We present a holistic statistical model for the automatic analysis of complex scenes. Here, holistic refers to an integrated approach that does not take local decisions about segmentation or object transformations. Starting from Bayes’ decision rule, we develop an appearance-based approach explaining all pixels in the given scene using an explicit background model. This allows the training of object references from unsegmented data and recognition of complex scenes. We present empirical results on different databases obtaining state-of-the-art results on two databases where a comparison to other methods is possible. To obtain quantifiable results for object-based recognition, we introduce a new database with subsets of different difficulties.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Frey, B.J., Jojic, N.: Transformation-invariant clustering using the EM algorithm. IEEE Trans. Pattern Analysis and Machine Intelligence 25(1), 1–17 (2003)
Keysers, D., Dahmen, J., Ney, H., Güld, M.O.: A Statistical Framework for Multi- Object Recognition. In: Informatiktage 2001 der Gesellschaft für Informatik, pp. 73–76. Konradin Verlag, Bad Schussenried (2001)
Keysers, D., Dahmen, J., Ney, H., Wein, B., Lehmann, T.: Statistical Framework for Model-based Image Retrieval in Medical Applications. J. Electronic Imaging 12(1), 59–68 (2003)
Motter, M.: Statistische Modellierung von Bildobjekten für die Bilderkennung. Diploma thesis, Chair of Computer Science VI, RWTH Aachen University of Technology, Aachen, Germany (December 2001)
Murase, H., Nayar, S.: Visual Learning and Recognition of 3-D Objects from Appearance. Int. J. Computer Vision 14(1), 5–24 (1995)
Reinhold, M., Paulus, D., Niemann, H.: Appearance-Based Statistical Object Recognition by Heterogeneous Background and Occlusions. In: Radig, B., Florczyk, S. (eds.) DAGM 2001. LNCS, vol. 2191, pp. 254–261. Springer, Heidelberg (2001)
Smeulders, A.W.M., Worring, M., Santint, S., Gupta, A., Jain, R.: Content-Based Image Retrieval at the End of the Early Years. IEEE Trans. Pattern Analysis and Machine Intelligence 22, 1349–1380 (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Keysers, D., Motter, M., Deselaers, T., Ney, H. (2003). Training and Recognition of Complex Scenes Using a Holistic Statistical Model. In: Michaelis, B., Krell, G. (eds) Pattern Recognition. DAGM 2003. Lecture Notes in Computer Science, vol 2781. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-45243-0_8
Download citation
DOI: https://doi.org/10.1007/978-3-540-45243-0_8
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40861-1
Online ISBN: 978-3-540-45243-0
eBook Packages: Springer Book Archive