Abstract
This paper presents a general solution for the problem of affine point pattern matching (APPM). Formally, given two sets of two-dimensional points (x,y) which are related by a general affine transformation (up to small deviations of the point coordinates and maybe some additional outliers). Then we can determine the six parameters aik of the transformation using new Hu point-invariants which are invariant with respect to affine transformations. With these invariants we compute a weighted point reference list. The affine parameters can be calculated using the method of the least absolute differences (LAD method) and using linear programming. In comparison to the least squares method, our approach is very robust against noise and outliers. The algorithm works in O(n) average time and can be used for translation and/or rotations, isotropic and non-isotropic scalings, shear transformations and reflections.
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
S. Abraham, K. Voss, H. Suesse: Affines matching planarer Punktmengen mittels Normalisierung über diskrete Momente. Proc. 18. DAGM-Symposium, Heidelberg 1996, Springer-Verlag, pp. 315–322
Y.S. Abu-Mostafa and D. Psaltis, Image Normalization by Complex Moments, PAMI 7 (1985) 46–55.
M. Ben-Ezra, S. Peleg, and M. Werman: Real-time motion analysis with linear programming. CVIU 78(1999) 32–52
M. Carcassoni, E.R. Hancock: Point pattern matching with robust spectral correspondence. Proceedings CVPR(2000) 649–655
Chang, S.H., Cheng, F.H., Hsu, W.H., Wu, G.Z.: Fast algorithm for point pattern-matching: Invariant to translations, rotations and scale changes. PR 30(1997) 311–320
G.S. Cox, G.De Jager: A survey of point pattern matching techniques and a new approach to point pattern recognition. Proc. of South African Symposium on Communications and Signal Processing 1993, pp. 243–248 Fig. 3. Real-time performance of the system
Flusser J., T. Suk: Pattern recognition by affine moment invariants. PR 26(1993) 167–174
S. Gold, A. Rangarajan, C.-P. Lu, S. Pappu, E. Mjolsness: New algorithms for 2D and 3D point matching: Pose estimation and correspondence. PR 31(1998) 1019–1031
M. Hagedoorn, and R.C. Veltkamp: Reliable and efficient pattern matching using an affine invariant metric. IJCV 31 (1999) 203–225
J. Hong, X. Tan: A new approach to point pattern matching. Proc. of 9th International Conference on Pattern Recognition 1988, Vol.1, pp.82.84
M.K. Hu: Visual pattern recognition by moment invariants.IT 8 (1962) 179–187
H. Karloff: Linear Programming. Birkhauser Verlag,Basel 1991.
I. Rothe, H. Suesse, K. Voss: The method of normalization to determine invariants. IEEE Trans. PAMI 18 (1996) 366–377
J. Sprinzak, M. Werman: Affine point matching. PRL 15 (1994) 337–339
K. Voss, H. Suesse: A new one-parametric fitting method for planar objects. IEEE Trans. PAMI 21(1999) 646–651
K. Voss, H. Suesse: Adaptive Modelle und Invarianten für zweidimensionale Bilder. Shaker-Verlag,Aachen 1995
K. Voss, H. Suesse: Invariant fitting of planar objects by primitives. IEEE Trans. PAMI 19 (1997) 80–84
P.B. van Wamelen, Z. Li, S.S. Iyengar: A fast algorithm for point pattern matching problem. appear in PAMI
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Voss, K., Suesse, H. (2001). Affine Point Pattern Matching. In: Radig, B., Florczyk, S. (eds) Pattern Recognition. DAGM 2001. Lecture Notes in Computer Science, vol 2191. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45404-7_21
Download citation
DOI: https://doi.org/10.1007/3-540-45404-7_21
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42596-0
Online ISBN: 978-3-540-45404-5
eBook Packages: Springer Book Archive