ETRI Journal

Electronics and Telecommunications Research Institute (한국전자통신연구원)
권호 표지

A New Similarity Measure Based on Intraclass Statistics for Biometric Systems

  • Lee, Kwan-Yong (Department of Computer, Information, and Communication, Korea Cyber University) ;
  • Park, Hye-Young (Laboratory for Mathematical Neuroscience, RIKEN Brain Science Institute)
  • Received : 2002.06.04
  • Published : 2003.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

A biometric system determines the identity of a person by measuring physical features that can distinguish that person from others. Since biometric features have many variations and can be easily corrupted by noises and deformations, it is necessary to apply machine learning techniques to treat the data. When applying the conventional machine learning methods in designing a specific biometric system, however, one first runs into the difficulty of collecting sufficient data for each person to be registered to the system. In addition, there can be an almost infinite number of variations of non-registered data. Therefore, it is difficult to analyze and predict the distributional properties of real data that are essential for the system to deal with in practical applications. These difficulties require a new framework of identification and verification that is appropriate and efficient for the specific situations of biometric systems. As a preliminary solution, this paper proposes a simple but theoretically well-defined method based on a statistical test theory. Our computational experiments on real-world data show that the proposed method has potential for coping with the actual difficulties in biometrics.

Keywords

References

  1. Neural Information Proc. Systems-Natural and Synthetic v.9 Viewpoint Invariant Face Recognition Using Independent Component Analysis and Attractor Networks Bartlett, M.;Sejnowsky, T.
  2. IEEE TRans. on Pattern Recognition and Machine Intelligence v.19 no.7 Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection Belhumeur, P.;Hespanha, J.;Kriegman, D.
  3. IEEE Trans. on Signal Proc. v.46 no.4 A Human Identification Technique Using Images of the Iris and Wavelet Transform Boles, W.W.;Boashash, B.
  4. Advances in Neural Information Proc. Systems A Sequence Kernel and Its Applications to Speaker Recognition Campbell, W.
  5. IEEE Trans. on Pattern Analysis and Machine Intelligence v.15 no.11 High Confidence Visual Recognition of Persons by a Test of Statistical Independence Daugman, J.G.
  6. AI 2001: Advances in Artificial Intelligence v.LNAI2256 Improved Techniques for an Iris Recognition System with High Performance Kee, G.;Byun, Y.;Lee, K.;Lee, Y.
  7. The 2000 Int'l Technical Conf. on Circuits/Systems, Computers, and Commun. PCA vs. ICA for Face Recognition Lee, O.;Park, H.;Choi, S.
  8. ETRI J. v.23 no.2 Efficient Iris Recognition through Improvement Feature Vector and Classifier Lim, S.;Lee, K.;Byeon, O.;Kim, T.
  9. Proc. of the IEEE v.85 no.9 Iris Recognition: An Emerging Biometric Technology Wildes, R.P.
  10. Introduction to Statistical Pattern Recognition Fukunaga, K.
  11. Kendall's Advanced Theory of Statistics, 1 Stuart, A.;Ord, K.
  12. Image and Vision Computing v.17 Circle Recognition through a 2D Hough Transform and Radius Histogramming Ioammou, D.;Huda, W.;Laine, A.F.
  13. Neural Networks for Pattern Recognition Bishop, C.
  14. Proc. of the Fifteens International Conf. of Pattern Recognition v.2 Evaluation Techniques for Biometrics-based Authentication System (FRR) Bolle, R.M.;Pankanti, S.;Ratha, N.K.
  15. Proc. of the IEEE v.85 Evaluation of Automated Biometrics-based Identification and Verification Shen, W.;Surette, M.;Khanna, R.