Abstract
In this paper, we show that there exist quasi-invariant pa- rameterisations which are not exactly invariant but approximately invari- ant under group transformations and do not require high order deriva- tives. The affine quasi-invariant parameterisation is investigated in more detail and exploited for defining general affine semi-local invariants from second order derivatives only. The new invariants are implemented and used for matching curve segments under general affine motions and ex- tracting symmetry axes of objects with 3D bilateral symmetry.
The authors acknowledge the support of the EPSRC, grant GR/K84202
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
E.B. Barrett and P.M. Payton. General methods for determining projective in-variants in imagery. Computer Vision, Graphics and Image Processing, Vol. 53, No. 1, pp. 46–65, 1991.
T.O. Binford and T.S. Levitt. Quasi-invariant: Theory and exploitation. In Proc. DARPA Image Understanding Workshop, pp. 819–829, 1993.
A. Blake. A symmetry theory of planar grasp. International Journal of Robotics Research, Vol. 14, No. 5, pp. 425–444, 1995.
A.M. Bruckstein, R.J. Holt, A.N. Netravali, and T.J. Richardson. Invariant signatures for planar shape recognition under partial occlusion. Computer Vision, Graphics and Image Processing, Vol. 58, No. 1, pp. 49–65, 1993.
T.J. Cham and R. Cipolla. Automated B-spline curve representation with MDL-based active contours. In Proc. 7th British Machine Vision Conference, Vol. 2, pp. 363–372, Edinburgh, September 1996.
R. Cipolla and A. Blake. Surface orientation and time to contact from image divergence and deformation. In G. Sandini, editor, Proc. 2nd European Conference on Computer Vision, pp. 187–202, Santa Margherita, Italy, 1992. Springer-Verlag.
D. Cyganski, J.A. Orr, T.A. Cott, and R.J. Dodson. An a_ne transformation invariant curvature function. In Proc. 1st International Conference on Computer Vision, pp. 496–500, London, 1987.
D. Forsyth, J.L. Mundy, A. Zisserman, and C.A. Rothwell. Recognising rota-tionally symmetric surfaces from their outlines. In G. Sandini, editor, Proc. 2nd European Conference on Computer Vision, Santa Margherita, Italy, 1992. Springer-Verlag.
S.A. Friedberg. Finding axes of skewed symmetry. Computer Vision, Graphics and Image Processing, Vol. 34, pp. 138–155, 1986.
A.D. Gross and T.E. Boult. Analyzing skewed symmetries. International Journal of Computer Vision, Vol. 13, No. 1, pp. 91–111, 1994.
M. Hu. Visual pattern recognition by moment invariants. IRE Transaction on Information Theory, Vol. IT-8, pp. 179–187, February 1962.
T. Kanade and J.R. Kender. Mapping image properties into shape constraints: Skewed symmetry, a_ne-transformable patterns, and the shape-from-texture paradigm. In J. Beck et al, editor, Human and Machine Vision, pp. 237–257. Academic Press, NY, 1983.
J.J. Koenderink and A.J. van Doorn. Geometry of binocular vision and a model for stereopsis. Biological Cybernetics, Vol. 21, pp. 29–35, 1976.
S. Lie. Gesammelte Abhandlungen, Vol. 6. Teubner, Leipzig, 1927.
R. Mohan and R. Nevatia. Perceptual organization for scene segmentation and description. IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 14, No. 6, pp. 616–635, 1992.
T. Moons, E.J. Pauwels, L.J. Van Gool, and A. Oosterlinck. Foundations of semi-di_erential invariants. International Journal of Computer Vision, Vol. 14, pp. 25–47, 1995.
J.L. Mundy and A. Zisserman. Geometric Invariance in Computer Vision. MIT Press, Cambridge, USA, 1992.
P.J. Olver. Applications of Lie Groups to Di_erential Equations. Springer-Verlag, 1986.
P.J. Olver, G. Sapiro, and A. Tannenbaum. Di_erential invariant signatures and flows in computer vision. In B.M. ter Haar Romeny, editor, Geometry-Driven Di_usion in Computer Vision, pp. 255–306. Kluwer Academic Publishers, 1994.
E.J. Pauwels, T. Moons, L.J. Van Gool, P. Kempenaers, and A. Oosterlinck. Recognition of planar shapes under a_ne distortion. International Journal of Computer Vision, Vol. 14, pp. 49–65, 1995.
D. Reisfeld, H. Wolfson, and Y. Yeshurun. Contex-free attention operators: The generalized symmetry transform. International Journal of Computer Vision, Vol. 14, No. 2, pp. 119–130, 1995.
C.A. Rothwell, A. Zisserman, D.A. Forsyth, and J.L. Mundy. Planar object recog-nition using projective shape representation. International Journal of Computer Vision, Vol. 16, pp. 57–99, 1995.
J. Sato and R. Cipolla. A_ne integral invariants for extracting symmetry axes. In Proc. 7th British Machine Vision Conference, Vol. 1, pp. 63–72, Edinburgh, September 1996.
J. Sato and R. Cipolla. Quasi-invariant parameterisations and matching of curves in images. International Journal of Computer Vision, Vol. 28, No. 2, pp. 117–136, 1998.
D.H. Sattinger and O.L. Weaver. Lie groups and algebras with applications to physics, geometry and mechanics. Springer-Verlag, New York, 1986.
G. Taubin and D.B. Cooper. Object recognition based on moment (or algebraic) invariants. In J.L. Mundy and A. Zisserman, editors, Geometric Invariance in Computer Vision, pp. 375–397. MIT Press, 1992.
L.J. Van Gool, T. Moons, E. Pauwels, and A. Oosterlinck. Semi-differential invariants. In J.L. Mundy and A. Zisserman, editors, Geometric Invariance in Computer Vision, pp. 157–192. MIT Press, 1992.
L.J. Van Gool, T. Moons, D. Ungureanu, and A. Oosterlinck. The characterization and detection of skewed symmetry. Computer Vision and Image Understanding, Vol. 61, No. 1, pp. 138–150, 1995.
L.J. Van Gool, T. Moons, D. Ungureanu, and E. Pauwels. Symmetry from shape and shape from symmetry. International Journal of Robotics Research, Vol. 14, No. 5, pp. 407–424, 1995.
I. Weiss. Projective invariants of shapes. In Proc. Image Understanding workshop, Vol. 2, pp. 1125–1134, 1988.
M. Zerroug and R. Nevatia. Three-dimensional descriptions based on the analysis of the invariant and quasi-invariant properties of come curved-axis generalized cylinders. IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 18, No. 3, pp. 237–253, 1996.
A. Zisserman, D.A. Forsyth, J.L. Mundy, and C.A. Rothwell. Recognizing general curved objects efficiently. In J.L. Mundy and A. Zisserman, editors, Geometric Invariance in Computer Vision, pp. 228–251. MIT Press, 1992.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Sato, J., Cipolla, R. (1999). Quasi-Invariant Parameterisations and Their Applications in Computer Vision. In: Shape, Contour and Grouping in Computer Vision. Lecture Notes in Computer Science, vol 1681. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-46805-6_6
Download citation
DOI: https://doi.org/10.1007/3-540-46805-6_6
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66722-3
Online ISBN: 978-3-540-46805-9
eBook Packages: Springer Book Archive