Statistical Significance as an Aid to System Performance Evaluation

  • Peter Tu
  • Richard Hartley
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1843)


Using forensic fingerprint identification as a testbed, a statistical framework for analyzing system performance is presented. Each set of fingerprint features is represented by a collection of binary codes. The matching process is equated to measuring the Hamming distances between feature sets. After performing matching experiments on a small data base, the number of independent degrees of freedom intrinsic to the fingerprint population is estimated. Using this information, a set of independent Bernoulli trials is used to predict the success of the system with respect to a particular dataset.


Binary Code Matching Process Merit Function True Assignment System Performance Evaluation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Ambler A.P., Barrow H.G., Brown C.M., Burstall R.M., Popplestone R.J., ‘A versatile computer-controlled assembly system’, IJCAI, pages 298–307, 1973.Google Scholar
  2. 2.
    Ballard D.H., Brown C.M.,’ Computer Vision’, Prentice-Hall, Englewood Cliffs, NJ, 1982.Google Scholar
  3. 3.
    Daugman J.G., “High Confidence Visual Recognition for Persons by a Test of Statistical Independence”, PAMI, vol, 15, no. 11, November 1993.Google Scholar
  4. 4.
    Ostenburg J.W., “An inquiry into the nature of proof: the identity of fingerprints”, J. forensic Sciences, vol. 9, pp. 413–427, 1964.Google Scholar
  5. 5.
    Ostenburg J. W., Parthasanathy T., Raghavan T.E.S, Sclove S.L., “Development of mathematical formula for the calculation of fingerprint probabilities based on individual characteristics”, J. Am. Statistical Assoc., vol. 72, pp. 772–778, Dec., 1977.Google Scholar
  6. 6.
    Ratha N.K., Karu K., Chen S., Jain A.K, ‘A real-time matching system for large fingerprint databases’, IEEE PAMI, vol. 18, no. 8, pp. 799–813, August 1996.Google Scholar
  7. 7.
    Roddy A.R., Stosz J.D., “Fingerprint Features-Statistical Analysis and System Performance Estimates”, Proc. of the IEEE, vol. 85, no. 9, pp. 1390–1421, September 1997.CrossRefGoogle Scholar
  8. 8.
    Weber D.M.,‘A cost effective fingerprint verification algorithm for commercial applications’, Proceedings of the 1992 South African symposium on communications and signal processing COSMIG’92. pp 99–104, published by the IEE.Google Scholar
  9. 9.
    Zisserman A., Forsyth D., Mundy J., Rothwell C., Liu J., Pillow N., ‘3D Object Recognition Using Invariance’, Artificial Intelligence Journal, 78, pp. 239–288, 1995.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • Peter Tu
    • 1
  • Richard Hartley
    • 1
  1. 1.Image Understanding GroupGeneral ElectricNiskayuna

Personalised recommendations