Abstract
The probability density function for the cross ratio is obtained under the hypothesis that the four image points have independent, identical, Gaussian distributions. The density function has six symmetries which are closely linked to the six different values of the cross ratio obtained by permuting the quadruple of points from which the cross ratio is calculated. The density function has logarithmic singularities corresponding to values of the cross ratio for which two of the four points are coincident. The cross ratio forms the basis of a simple system for recognising or classifying quadruples of collinear image points. The performance of the system depends on the choice of rule for deciding whether four image points have a given cross ratio σ. A rule is stated which is computationally straightforward and which takes into account the effects on the cross ratio of small errors in locating the image points. Two key properties of the rule are the probabilityR of rejection, and the probabilityF of a false alarm. The probabilitiesR andF depend on a thresholdt in the decision rule. There is a trade off betweenR andF obtained by varyingt. It is shown that the trade off is insensitive to the given cross ratio σ. LetF w =max o {F}. ThenR, F w are related approximately by\(\sqrt {\ln (R^{ - 1} )} = (\sqrt 2 \varepsilon r_F )^{ - 1} F_w\), provided ε−1 F w ≥4. In the equation, ε is the accuracy with which image points can be located relative to the width of the image, andr F is a constant known as the normalised false alarm rate. In the range ε−1 F w ≤4 the probabilitiesR andF w are related approximately by\(R = 1 - \sqrt {2\pi ^{ - 1} } \varepsilon ^{ - 1} r_F^{ - 1} F_w\). The value ofr F is 14.37. The consequences of these relations between R and Fw are discussed. It is conjectured that the above general form of the trade off betweenR andF w holds for a wide class of scalar invariants that could be used for model based object recognition. Invariants with the same type of trade off between the probability of rejection and the probability of false alarm are said to be nondegenerate for model based vision.
Similar content being viewed by others
References
Abramowitz, M. and Stegun, I.A. (eds.) 1965.Handbook of Mathematical Functions with Formulas, Graphs, and Mathematical Tables. Dover: New York, NY, USA.
Åström, K. and Morin, L. 1992. Random cross ratios.Rapport Technique RT88 IMAG-14, LIFIA, LIFIA, Institut Imag, Grenoble, France.
Cramér, H. 1945.Mathematical Methods of Statistics. Princeton Mathematical Series, Vol. 9. Princeton: Princeton University Press (Eighteenth Printing 1991).
Devijver, P.A. and Kittler, J. 1982.Pattern Recognition: a statistical approach. Prentice Hall: London, UK.
Forsyth, D., Mundy, J.L., Zisserman, A., Coelho, C., Heller, A., and Rothwell, C. 1991. Invariant descriptors for 3D object recognition and pose. IEEE Trans. Pattern Analysis and Machine Intelligence, 13, 971–991.
Gradshteyn, I.S. and Ryzhik, I.M. 1983.Table of Integrals, Series and Products. Corrected and enlarged edition prepared by Jeffrey, A. Academic Press, Inc.: London, UK.
Helstrom, C.W. 1960.Statistical Theory of Signal Detection. International Series of Monographs on Electronics and Instrumentation. Oxford: Pergamon Press.
Kanungo, T., Jaisimha, M.Y., Palmer, J., and Haralick, R.M. 1993. A quantitative methodology for analyzing the performance of motion detection algorithms. In4th Int. Conf. on Computer Vision, ICCV'93, Berlin, pp. 247–252.
Maybank, S.J. 1994. Classification based on the cross ratio. In J.L. Mundy, A. Zisserman, and D. Forsyth (eds.),Applications of Invariance to Computer Vision. Lecture Notes in Computer Science 825, Springer-Verlag: Berlin, Heidelberg, New York, pp. 69–88.
Maybank, S.J. 1995. Probabilistic analysis of the application of the cross ratio to model based vision: misclassification.Int. J. Computer Vision, 14, 1–12.
Maybank, S.J. and Beardsley, P.A. 1994. Applications of invariants to model based vision.Journal of Applied Statistics 21, 439–465.
Mundy, J.L. and Zisserman, A. (eds.) 1992.Geometric Invariance in Computer Vision. MIT Press: Cambridge MA, USA.
Semple, J.G. and Kneebone, G.T. 152.Algebraic Projective Geometry. Oxford University Press: Oxford, UK. Reprinted 1979.
Whittaker, E.T. and Watson, G.N. 1952.Modern Analysis. Cambridge University Press: Cambridge, UK.
Whittle, P. 1970.Probability. Library of University Mathematics, Pengium Books Ltd.: Harmondsworth, Middlesex, UK.
Wolfram, S. 1991.Mathematica: a system for doing mathematics by computer. Addison Wesley: Redwood City CA, USA (2nd ed.).
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Maybank, S.J. Probabilistic analysis of the application of the cross ratio to model based vision. Int J Comput Vision 16, 5–33 (1995). https://doi.org/10.1007/BF01428191
Issue Date:
DOI: https://doi.org/10.1007/BF01428191