Abstract
Affine invariant scale space analyses have been introduced in the 1990s and largely used in shape recognition applications. Nowadays they are also used for the determination of points of interests. Nevertheless, a projective analysis is necessary if information is to be gathered from images taken of the same scene but under different points of view. In previous work, we replaced the projective analysis due to the heat equation by a flow of second order equations. The registration group allows to model the deformations of an image due to camera motion by a 6 parameter group. We will show that it allows also to view in a new light the projective analysis and the Affine Morphological Scale Space of Alvarez, Lions, Guichard and Morel (Arch. Ration. Mechan. 16:200–257 (1993)). Moreover, the registration group gives directly a first approach for a Projective Scale Invariant Feature Tracking 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
Alvarez, L., Guichard, F., Lions, P.-L., Morel, J.-M.: Axioms and fundamental equations of image processing. Arch. Ration. Mechan. 16, 200–257 (1993)
Bruckstein, A., Shaked, D.: On projective invariant smoothing and evolutions of planar curves and polygons. J. Math. Imaging Vis. 7(3), 181–192 (1998)
Cohignac, T., Lopez, C., More, J.-M.: Integral and local affine invariant parameter and application to shape recognition, ICPR, pp. 164–168. (1994)
Dibos, F.: Du groupe projectif au groupe des recalages: une nouvelle modélisation. C.R. Acad. Sci. Paris Série I 332(9) (2001)
Dibos, F.: Projective analysis of 2D images. IEEE Trans. Image Process. 7(3), 274–279 (1998)
Dibos, F., Frosini, P., Pasquignon, D.: The use of size functions for comparison of shapes through differential invariants. J. Math. Imaging Vis. 21, 107–118 (2004)
Dibos, F., Jonchery, C., Koepfler, G.: Iterative camera motion and depth estimation in a video sequence. In: Lecture Notes in Computer Science, vol. 5702, pp. 1028–1035. Proceedings of the 13th International Conference on Computer Analysis of Images and Patterns. Springer, Berlin (2009)
Dibos, F., Koepfler, G., Monasse, P.: Image alignment. In: Geometric Level Set Methods in Imaging. Springer, Heidelberg (2003)
Faugeras, O.: Sur l’évolution de courbes simples du plan projectif réel. C.R. Acad. Sci. Paris Série I 317, 565–570 (1993)
Faugeras, O., Keriven, R.: Some recent results on the projective evolution of 2D curves. In: Proceedings ICIP, vol. 3, pp. 13–16. Washington (1995)
Jonchery, C., Dibos, F., Koepfler, G.: Camera motion estimation through planar deformation determination. J. Math. Imaging Vis. 32(1) (2008)
Koepfler, G., Moisan, L.: Geometric Multiscale representation of numerical images. In: Proceedings of the second International Conference on Scale Space Theories in Computer Vision, Springer Lectures Notes in Computer Science, vol. 1682, pp. 339–350 (1999)
Lowe, D.: Distinctive image features from scale-invariant key points. Int. J. Comput. Vis. 60, 91–110 (2004)
Mikolajczyk, K., Schmid, C.: Scale and affine invariant interest point detectors. Int. J. Comput. Vis. 60(1),63–86 (2004)
Morel, J.-M., Yu, G.: ASIFT: A new framework for fully affine invariant image comparison. SIAM J. Imaging Sci. 2(2), 438–469 (2009)
Muse, P., Sur, F., Cao, F., Gousseau, Y., Morel, J.-M.: An a contrario decision method for shape element recognition. Int. J. Comput. Vis. 69, 295–315 (2006)
Sapiro, G., Tannenbaum, A.: Affine invariant scale space. Int. J. Comput. Vis. 11, 25–44 (1993)
Sur, F.: Invariant image descriptors and affine morphological scale-space. Rapport de Recherche, no 6250, INRIA Lorraine, 2007
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Dibos, F. (2011). Projective Invariant Features Detection and the Registration Group. In: Bergounioux, M. (eds) Mathematical Image Processing. Springer Proceedings in Mathematics, vol 5. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-19604-1_5
Download citation
DOI: https://doi.org/10.1007/978-3-642-19604-1_5
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-19603-4
Online ISBN: 978-3-642-19604-1
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)