Abstract
Invariant representations are frequently used in computer vision algorithms to eliminate the effect of an unknown transformation of the data. These representations, however, depend on the order in which the features are considered in the computations. We introduce the class of projective/permutation p2-invariants which are insensitive to the labeling of the feature set. A general method to compute the p2-invariant of a point set (or of its dual) in the n-dimensional projective space is given. The one-to-one mapping between n + 3 points and the components of their p2-invariant representation makes it possible to design correspondence algorithms with superior tolerance to positional errors. An algorithm for coplanar points in projective correspondence is described as an application, and its performance is investigated. The use of p2-invariants as an indexing tool in object recognition systems may also be of interest.
Similar content being viewed by others
References
Alefeld, G. and Herzberger, J. 1983. Introduction to Interval Computations. Academic Press: New York.
Åström, K.E. and Morin, L. 1995. Random cross ratios. In Proc. 9th Scand. Conf. on Image Anal., Uppsala, Sweden, pp. 1053-1061.
Biglieri, E. and Yao, K. 1989. Some properties of singular value decomposition and their applications to digital signal processing. Signal Processing, 18:277-289.
Brill, M.H. and Barrett, E.A. 1983. Closed-form extension of the anharmonic ratio to n-space. Computer Vision, Graphics, and Image Processing, 23:92-98.
Carlsson, S. 1994. The double algebra: An effective tool for computing invariants in computer vision. In Applications of Invariance in Computer Vision, J.L. Mundy et al. (Eds.), Springer Verlag, pp. 145-164.
Carlsson, S. 1995. Duality of reconstruction and positioning from projective views. In Proc. of IEEE Workshop on Representation of Visual Scenes, Boston, pp. 85-92.
Chellappa, R., Zheng, Q., Davis, L.S., DeMenthon, D., and Rosenfeld, A. 1993. Site-model-based change detection and image registration. In Proc.DARPA Image Understanding Workshop, Washington, DC, pp. 205-216.
Efron, B. and Tibshirani, R.J. 1993. An Introduction to the Bootstrap.Chapman & Hall: London.
Faugeras, O. 1993. Three Dimensional Computer Vision. MIT Press: Cambridge, MA.
Faugeras, O. 1995. Stratification of three-dimensional vision: Projective, affine, and metric representations. J. Opt. Soc. Am. A, 12:465-484.
Golub, G.H. and van Loan, C.F. 1989. Matrix Computations. Second edition. Johns Hopkins University Press: Baltimore.
Grimson, W.E.L., Huttenlocher, D.P., and Jacobs, D.W. 1994. A study of affine matching with bounded sensor error. Intl. J. of Computer Vision, 13:7-32.
Haralick, R.M. and Shapiro, L.G. 1993. Computer and Robot Vision. Addison-Wesley: Reading, MA, Vols. I-II.
Hartley, R. 1993. Cheirality invariants. In Proc. of DARPA Image Understanding Workshop, Washington, D.C., pp. 745-753.
Huttenlocher, D.P. and Ullman, S. 1990. Recognizing solid objects by alignment with an image. Intl. J. of Computer Vision,5:195- 212.
Jacobs, D.W. 1996. Robust and efficient detection of salient convex groups. IEEE Trans. on PAMI, 18:23-38.
Kanatani, K. 1991. Computational projective geometry. CVGIP: Image Understanding, 54:333-348.
Lamdan, Y., Schwartz, J.T., and Wolfson, H.J. 1990. Affine invariant model-based object recognition. IEEE Trans. Robot. Autom., 6:578-589.
Lamdan, Y. and Wolfson, H.J. 1991. On the error analysis of 'Geometric Hashing'. In Proc. of the 1991 IEEE Comp. Soc. Conf. on Computer Vision and Pattern Recog., Lahaina, Maui, Hawaii, pp. 22-27.
Lenz, R. and Meer, P. 1994. Point configuration invariants under simultaneous projective and permutation transformations. Pattern Recog., 27:1523-1532.
Maybank, S.J. 1994. Classification based on the cross ratio. In Applications of Invariance in Computer Vision, J.L. Mundy et al. (Eds.), Springer Verlag, pp. 453-472.
Maybank, S.J. 1995. Probabilistic analysis of the application of the cross ratio to model based vision: Misclassification. Intl. J. of Computer Vision, 14:199-210.
Meer, P., Ramakrishna, S., and Lenz, R. 1994. Correspondence of coplanar features through p2-invariant representations. In Applications of Invariance in Computer Vision, J.L. Mundy et al. (Eds.), Springer Verlag, pp. 473-492.
Morin, L. 1993. Quelques Contributions des Invariants Projectifs a la Vision par Ordinateur, Ph.D. Thesis, Institut National Polytechnique de Grenoble.
Morin, L., Brand, P., and Mohr, R. 1994. Indexing with projective invariants. Presented at the Syntactical and Structural Pattern Recog. Workshop, Nahariya, Israel.
Mundy, J.L. and Zisserman, A. (Eds.) 1992. Geometric Invariance in Machine Vision. MIT Press: Cambridge, MA.
Mundy, J.L., Zisserman, A., and Forsyth, D.A. (Eds.) 1994a. Applications of Invariance in Computer Vision. Lecture Notes in Computer Science, 825. Springer-Verlag: Heilderberg.
Mundy, J.L., Huang, C., Liu, J., Hoffman, W., Forsyth, D.A., Rothwell, C.A., Zisserman, A., Utcke, S., and Bournez, O. 1994b. MORSE: A 3D object recognition system based on geometric invariants. In Proc. DARPA Image Understanding Workshop, Monterey, CA, pp. 1393-1402.
Quan, L. 1995. Invariants of six points and projective reconstruction from three uncalibrated cameras. IEEE Trans. on PAMI, 17:34-46.
Ramakrishna, S. 1994. Invariance Based Robust Matching. M.S. Thesis. Tech. Rep. CE-105. Dep. of Electrical and Comp. Engn., Rutgers University.
Rothwell, C.A. 1994. Hierarchical object description using invariants. In Applications of Invariance in Computer Vision, J. L. Mundy et al. (Eds.), Springer Verlag, pp. 397-414.
Rothwell, C.A., Csurka, G., and Faugeras, O. 1995. A comparison of projective reconstruction methods for pair of views. INRIA Tech. Rep., No. 2538. Appeared in Computer Vision and Understanding, 68:37-58, 1997.
Springer, C.E. 1965. Geometry and Analysis of Projective Spaces. Freeman: San Francisco.
Zhang, S., Deriche, R., Faugeras, O., and Luong, Q.-T. 1994. A robust technique for matching two uncalibrated images through the recovery of unknown epipolar geometry. INRIA Tech. Rep., No. 2273. Artificial Intelligence, 78:87-119, 1996.
Zheng, Q. and Chellappa, R. 1992. A computational vision approach to image registration. In Proc. 11th IAPR Intl. Conf. on Pattern Recog., The Hague, The Netherlands, Vol. 1, pp. 193-197.
Zisserman, A., Mundy, J., Forsyth, D.A., Liu, J., Pillow, N., Rothwell, C.A., and Utcke, S. 1995. Class-based grouping in perspective images. In Proc. 5th Intl. Conf. in Computer Vision, Boston, pp. 183-188.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Meer, P., Lenz, R. & Ramakrishna, S. Efficient Invariant Representations. International Journal of Computer Vision 26, 137–152 (1998). https://doi.org/10.1023/A:1007944826230
Issue Date:
DOI: https://doi.org/10.1023/A:1007944826230