Abstract
Object detection and localization are common tasks in image analysis.
Correlation based detection algorithms are known to work well, when dealing with objects with known geometry in Gaussianly distributed additive noise. In the Bayes’ view, correlation is linearly related to the logarithm of the probability density, and optimal object detection is obtained by the integral of the exponentiated squared correlation under appropriate normalization.
Correlation with a model is linear in the input image, and can be computed effectively for all possible positions of the model using Fourier based linear filtering techniques. It is therefore interesting to extend the application to objects with many but small degrees of freedom in their geometry. These geometric variations deteriorate the linear correlation signal, both regarding its strength and localization with multiple peaks from a single object.
Localization is typically preferred over detection, and Bayesian localization may be obtained as local integration of the probability density. In this work, Gaussian kernels of the exponentiated correlation are studied, and the use of Linear Scale-Space allows us to extend the Bayes detection with a well-posed localization, to extend the usage of correlation to a larger class of shapes, and to argue for the use of mathematical morphology with quadratic structuring elements on correlation images.
This project is supported in part by the Danish Research Agency, project “Computing Natural Shape”, no. 2051-01-0008 and in part by the DSSCV project under the IST Programme of the European Union (IST-2001-35443)
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
Robert Hoffman and Leo Gros. The modulation contrast microscope. Nature, 254:568–588, April 1975.
N.H. Olsen, J. Sporring, and M. Nielsen. Reconstruction of optical thickness. In Peter Johansen, editor, Den 11. Danske Konference om Mønstergenkendelse og Billedanalyse. Departement of Computer Science, University of Copenhagen, 2002. Technical Report no. 2002/15.
T.F. Cootes, G.J. Edwards, and C.J. Taylor. Active appearance models. PAMI, 23(6):681–684, June 2001.
C. J. Taylor, T. F. Cootes, A. Hill, and J. Haslam. Medical image segmentation using active shape models. In L. Beolchi and M. Kuhn, editors, Medical Imaging. IOS Press, 1994.
Andrew Swann and Niels Holm Olsen. Linear transformation groups and shape space. JMIV, accepted 2002. revised.
H.H. Barrett and C.K. Abbey. Bayesian detection of random signals on random backgrounds. In J. Duncan and G. Gindi, editors, Proceedings of the 15th International Conference on Information Processing in Medical Imaging, pages 155–166. Springer-Verlag, 1997.
Luc Florack, Robert Maas, and Wiro Niessen. Pseudo-linear scale-space theory. International Journal of Computer Vision, 31(2/3):247–259, 1999.
Christian P. Robert. The Bayesian Choice: a decision-theoretic motivation. Springer, 1997.
Yurij Kharin. Robustness in Statistical Pattern Recognition, volume 380 of Mathematics and Its Applications. Kluwer Academic Publishers, 1996.
Vladimir N. Vapnik. The Nature of Statistical Learning Theory. Springer, 1995.
Niels Holm Olsen, Jon Sporring, Mads Nielsen, Christina Hnida, and Søren Ziebe. Reconstructing the optical thickness from hoffman modulation contrast images. In Søren Olsen, editor, Den 11. Danske Konference i Mønstergenkendelse og Billedanalyze, volume 15 of DIKU Technical Reports, pages 11–18. DIKU, August 2002. ISSN: 0107-8283.
Eric Clarkson and Harrison Barrett. Bayesian detection with amplitude, scale, orientation and position uncertainty. In James Duncan and Gene Gindi, editors, Information Processing in Medical Imaging, 15 th Internanational Conference, IPMI’97, volume 1230 of Lecture Notes in Computer Science, pages 549–554, Poultney, Vermont, USA, June 1997. Springer.
J. Weickert, S. Ishikawa, and A. Imiya. On the history of Gaussian scale-space axiomatics. In Mads Nielsen, Luc Florack, and Peter Johansen, editors. Gaussian Scale-Space Theory. Kluwer Academic Publishers, Dordrecht, The Netherlands 1997 Sporring et al. [15], chapter 4, pages 45–59.
Rein van den Boomgaard and Leo Dorst. The morphological equivalent of gaussian scale-space. In Mads Nielsen, Luc Florack, and Peter Johansen, editors. Gaussian Scale-Space Theory. Kluwer Academic Publishers, Dordrecht, The Netherlands 1997 Sporring et al. [15], chapter 15.
Jon Sporring, Mads Nielsen, Luc Florack, and Peter Johansen, editors. Gaussian Scale-Space Theory. Kluwer Academic Publishers, Dordrecht, The Netherlands, 1997.
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
Sporring, J., Olsen, N.H., Nielsen, M. (2003). Detection and Localization of Random Signals. In: Griffin, L.D., Lillholm, M. (eds) Scale Space Methods in Computer Vision. Scale-Space 2003. Lecture Notes in Computer Science, vol 2695. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44935-3_55
Download citation
DOI: https://doi.org/10.1007/3-540-44935-3_55
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40368-5
Online ISBN: 978-3-540-44935-5
eBook Packages: Springer Book Archive