Skip to main content
No Access

Fusion of biometric systems using Boolean combination: an application to iris-based authentication

Published Online:pp 291-315https://doi.org/10.1504/IJBM.2012.047645

To improve accuracy and reliability, Boolean combination (BC) can efficiently integrate the responses of multiple biometric systems in the ROC space. However, BC techniques assume that recognition systems are conditionally-independent and that their ROC curves are convex. These assumptions are rarely valid in practice, where systems face complex environments, and are designed using limited enrollment data. In recent research, the authors have introduced an Iterative BC (IBC) technique that applies all Boolean functions iteratively, without prior assumptions. In this paper, IBC is considered for fusion of different commercial biometric systems at the decision level. Performance of IBC is assessed for biometric authentication applications in which the operational response of unimodal iris-base systems are combined. Experiments performed with four different commercial systems using anonymised data collected by the Canada Border Services Agency indicate that IBC fusion with interpolation can significantly outperform related BC techniques and individual systems.

Keywords

biometrics, classification, information fusion, ROC, receiver operating characteristics, BC, Boolean combination, iris modality

References

  • 1. Banfield, R. , Hall, L. , Bowyer, K. , Kegelmeyer, W. (2003). ‘A new ensemble diversity measure applied to thinning ensembles’. Multiple Classifier Systems. 2709, 159 Google Scholar
  • 2. Barreno, M. , Cardenas, A. , Tygar, D. ‘Optimal ROC for a combination of classifiers’. Advances in Neural Information Processing Systems (NIPS). 2008, 01, 20 Google Scholar
  • 3. Bengio, S. , Mariéthoz, S. (2007). ‘Biometric person authentication is a multiple classifier problem’. Int’l Workshop on Multiple Classifier Systems, Prague, Czech Republic Google Scholar
  • 4. Bergamini, C. , Oliveira, L. , Koerich, A. , Sabourin, R. (2009). ‘Combining different biometric traits with one-class classification’. Signal Processing. 89, 2117-2127 Google Scholar
  • 5. Black, M.A. , Craig, B.A. (2002). ‘Estimating disease prevalence in the absence of a gold standard’. Statistics in Medicine. 21, 18, 2653-2669 Google Scholar
  • 6. Bouchaffra, D. , Amira, A. (2008). ‘Structural hidden markov models for biometrics: fusion of face and fingerprint’. Pattern Recognition. 41, 5, 852-867 Google Scholar
  • 7. Bowyer, K.W. , Hollingsworth, K. , Flynn, P.J. (2008). ‘Image understanding for iris biometrics: a survey’. Computer Vision and Image Understanding. 110, 2, 281-307 Google Scholar
  • 8. Breiman, L. ‘Bagging predictors’. Machine Learning. 1996, 08, 24, 2, 123-140 Google Scholar
  • 9. Brown, G. , Wyatt, J. , Harris, R. , Yao, X. (2005). ‘Diversity creation methods: a survey and categorisation’. Journal of Information Fusion. 6, 1, 5-20 Google Scholar
  • 10. Daugman, J. (2000). Biometric Decision Landscapes. UK:Universtity of Cambridge , Tech. Rep. UCAM-CL-TR-482 Google Scholar
  • 11. Fawcett, T. (2004). ROC Graphs: Notes and Practical Considerations for Researchers. Palo Alto, CA, USA:HP Laboratories , Tech. Rep. HPL-2003-4 Google Scholar
  • 12. Fawcett, T. (2006). ‘An introduction to ROC analysis’. Pattern Recognition Lett.. 27, 8, 861-874 Google Scholar
  • 13. Fierrez-Aguilar, J. , Garcia-Romero, D. , Ortega-Garcia, J. , Gonzalez-Rodriguez, J. (2005). ‘Adapted user-dependent multimodal biometric authentication exploiting general information’. Pattern Recognition Letters. 26, 16, 2628-2638 Google Scholar
  • 14. Freund, Y. , Schapire, R.E. (1996). ‘Experiments with a new boosting algorithm’. ICML 96, 148-156 Google Scholar
  • 15. Gorodnichy, D.O. (2011). ‘Multi-order biometric score analysis framework and its application to designing and evaluating biometric systems for access and border control’. IEEE Workshop on Computational Intelligence in Biometrics and Identity Management, 11–25 April, Paris, France, 44-53 Google Scholar
  • 16. Gorodnichy, D.O. , Dubrofsky, E. , Hoshino, R. , Khreich, W. , Granger, E. , Sabourin, R (2011). ‘Exploring the upper bound performance limit of iris biometrics using score fusion and score calibration’. IEEE Workshop on Computational Intelligence in Biometrics and Identity Management, 11–25 April, Paris, France Google Scholar
  • 17. Haker, S. , Wells, W.M. , Warfield, S.K. , Talos, I-F. , Bhagwat, J.G. , Goldberg-Zimring, D. , Mian, A. , Ohno-Machado, L. , Zou, K.H. (2005). ‘Combining classifiers using their receiver operating characteristics and maximum likelihood estimation’. Medical Image Computing and Computer-Assisted Intervention (MICCAI). 3749, 506-514 Google Scholar
  • 18. Ho, T.K. (1998). ‘The random subspace method for constructing decision forests’. IEEE Transactions on Pattern Analysis and Machine Intelligence. 20, 8, 832-844 Google Scholar
  • 19. Ho, T.K. , Hull, J. , Srihari, S. (1994). ‘Decision combination in multiple classifier systems’. IEEE Transactions on Pattern Analysis and Machine Intelligence. 16, 1, 66-75 Google Scholar
  • 20. Jain, A. , Nandakumar, K. , Ross, A. (2005). ‘Score normalization in multimodal biometric systems’. Pattern Recognition. 38, 2270-2285 Google Scholar
  • 21. Jain, A. , Ross, A. , Pankanti, S. (2006). ‘Biometrics: a tool for information security’. IEEE Trans. on Information Forensics and Security. 1, 2, 125-143 Google Scholar
  • 22. Khreich, W. , Granger, E. , Miri, A. , Sabourin, R. (2010). ‘Iterative boolean combination of classifiers in the roc space: an application to anomaly detection with hmms’. Pattern Recognition. 43, 8, 2732-2752 Google Scholar
  • 23. Khreich, W. , Granger, E. , Sabourin, R. , Miri, A. (2009). ‘Combining hidden Markov models for anomaly detection’. International Conference on Communications (ICC), Dresden, Germany, 1-6 Google Scholar
  • 24. Kittler, J. , Hatef, M. , Duin, R. , Matas, L. (1998). ‘On combining classifiers’. IEEE Trans. on Pattern Analysis and Machine Intellignece. 20, 3, 226-239 Google Scholar
  • 25. Kittler, J. , Poh, N. , Fatukasi, O. , Messer, K. , Kryszczuk, K. , Richiardi, J. , Drygajlo, A. (2006). ‘Quality dependent fusion of intramodal and multimodal biometric experts’. Proc. of SPIE Vol. 6539, Biometric Technology for Human Identification IV. 1-14 Google Scholar
  • 26. Kuncheva, L.I. (2004). Combining Pattern Classifiers: Methods and Algorithms. New Jersey, USA:Wiley- Interscience Publication Google Scholar
  • 27. Kuncheva, L.I. , Whitaker, C.J. (2003). ‘Measures of diversity in classifier ensembles and their relationship with the ensemble accuracy’. Machine Learning. 51, 2, 181-207 Google Scholar
  • 28. Kung, S. , Mak, M. , Lin, S. (2004). Biometric Authentication: A Machine Learning Approach. New Jersey, USA:Prentice Hall Google Scholar
  • 29. Nandakumar, K. , Chen, Y. , Dass, S. , Jain, A. (2008). ‘Likelihood ratio-based biometric score fusion’. IEEE Trans. on Pattern Analysis and Machine Intellignece. 30, 2, 342-347 Google Scholar
  • 30. Neyman, J. , Pearson, E.S. (1933). ‘On the problem of the most efficient tests of statistical hypotheses’. Royal Society of London Philosophical Transactions Series A. 231, 289-337 Google Scholar
  • 31. Oh, I-S. , Suen, C. (2002). ‘A class-modular feedforward neural network for handwriting recognition’. Pattern Recognition. 35, 229-244 Google Scholar
  • 32. Oliveira, L. , Justino, E. , Sabourin, R. , Bortolozzi, F. (2008). ‘Combining classifiers in the roc-space for off-line signature verification’. Journal of Universal Computer Science. 14, 2, 237-251 Google Scholar
  • 33. Oxley, M. , Thorsen, S. , Schubert, C. (2007). ‘A Boolean algebra of receiver operating characteristic curves’. 10th International Conference on Information Fusion, Québec City, Canada, 1-8 Google Scholar
  • 34. Provost, F.J. , Fawcett, T. (2001). ‘Robust classification for imprecise environments’. Machine Learning. 42, 3, 203-231 Google Scholar
  • 35. Roli, F. , Fumera, G. , Kittler, J. (2002). ‘Fixed and trained combiners for fusion of imbalanced pattern classifiers’. Information Fusion, 2002. Proceedings of the Fifth International Conference on. 1, 278-284 Google Scholar
  • 36. Ruta, D. , Gabrys, B. ‘Classifier selection for majority voting’. Information Fusion. 2005, 03, 6, 1, 63-81 Google Scholar
  • 37. Scott, M.J.J. , Niranjan, M. , Prager, R.W. , Lewis, P.H. Nixon, M.S. (1998). ‘Realisable classifiers: improving operating performance on variable cost problems’. Proceedings of the Ninth British Machine Vision Conference. 1, September, University of Southampton, UK, 304-315 Google Scholar
  • 38. Shen, C. (2008). ‘On the principles of believe the positive and believe the negative for diagnosis using two continuous tests’. Journal of Data Science. 6, 189-205 Google Scholar
  • 39. Snelick, R. (2005). ‘Large-scale evaluation of multimodal biometric authentication state-ofthe- art systems’. IEEE Trans. on Pattern Analysis and Machine Intelligence. 27, 3, 450-455 Google Scholar
  • 40. Tabassi, E. (2010). ‘Image specific error rate: a biometric performance metric’. Proc. International Conference on Pattern Recognition. 1124-1127 Google Scholar
  • 41. Tao, Q. , Veldhuis, R. (2008). ‘Threshold-optimized decision-level fusion and its application to biometrics’. Pattern Recognition. 41, 5, 852-867 Google Scholar
  • 42. Thomopoulos, S. , Viswanathan, R. , Bougoulias, D. (1989). ‘Optimal distributed decision fusion’. IEEE Transactions on Aerospace and Electronic Systems. 25, 5, 761-765 Google Scholar
  • 43. Tulyakov, S. , Jaeger, S. , Govindaraju, V. , Doermann, D. , Simone Marinai, H.F. (2008). ‘Review of classifier combination methods’. Studies in Computational Intelligence: Machine Learning in Document Analysis and Recognition. Springer, 361-386 Google Scholar
  • 44. Van Erp, M. , Schomaker, L. (2000). ‘Variants of the borda count method for combining ranked classifier hypotheses’. Seventh International Workshop on Frontiers in Handwriting Recognition, 11–13 September, Amsterdam, 443-452 Google Scholar
  • 45. Verlinde, P. , Chollet, G. , Achcrov, M. (2000). ‘Multi-modal identity verification using expert fusion’. Information Fusion. 1, 1, 17-33 Google Scholar
  • 46. Walter, S.D. (2005). ‘The partial area under the summary ROC curve’. Statistics in Medicine. 24, 13, 2025-2040 Google Scholar
  • 47. Zhang, T. , Li, X. , Tao, D. (2008). ‘Multimodal biometrics using geometry preserving projections’. Pattern Recognition. 41, 5, 805-813 Google Scholar