Evaluation of Biometric Identification in Open Systems
This paper concerns the generalizability of biometric identification results from small-sized closed systems to larger open systems. Many researchers have claimed high identification accuracies on closed system consisting of a few hundred or thousand members. Here, we consider what happens to these closed identification systems as they are opened to non-members. We claim that these systems do not generalize well as the non-member population increases. To support this claim, we present experimental results on writer and iris biometric databases using Support Vector Machine (SVM) and Nearest Neighbor (NN) classifiers. We find that system security (1-FAR) decreases rapidly for closed systems when they are tested in open-system mode as the number of non members tested increases. We also find that, although systems can be trained for greater closed-system security using SVM rather than NN classifiers, the NN classifiers are better for generalizing to open systems due to their superior capability of rejecting non-members.
KeywordsSupport Vector Machine Support Vector Machine Classifier Near Neighbor Radial Basis Function Kernel Equal Error Rate
Unable to display preview. Download preview PDF.
- 1.Bolle, R.M., Connell, J.H., Pankanti, S., Ratha, N.K., Senior, A.W.: Guide to Biometrics. Springer, Heidelberg (2004)Google Scholar
- 4.Cha, S.-H., Srihari, S.N.: Handwritten Document Image DatabaseConstruction and Retrieval System. In: Proceedings of SPIE Document Recognition and Retrieval VIII, San Jose, vol. 4307 (2001)Google Scholar
- 6.Gibbons, M.: On Evaluating Open Biometric Identification Systems. Master.s Thesis, CSIS Department, Pace University (2005)Google Scholar
- 7.Grother, P., Phillips, P.J.: Models of Large Population Recognition Performance. In: 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2004), Washington, D.C, vol. 2, pp. 68–77 (2004)Google Scholar
- 8.Hsu, C.-W., Chang, C.-C., Len, C.-J.: A Practical Guide to Support Vector ClassificationGoogle Scholar
- 9.Kee, G., Byun, Y., Lee, K., Lee, Y.: Improved Techniques for an Iris Recognition System with High Performance. Lecture Notes Artificial Intelligence. Springer, Heidelberg (2001)Google Scholar
- 10.Krichen, E., Mellakh, M.A., Garcia-Salicetti, S., Dorizzi, B.: Iris Identification Using Wavelet Packets. In: 17th International Conference on Pattern Recognition (ICPR 2004), pp. 335–338 (2004)Google Scholar
- 11.Kung, S.Y., Mak, M.W., Lin, S.H.: Biometric Authentication: A Machine Learning Approach. Pearson Education Company (2004)Google Scholar
- 12.Ma, Y., Pollick, F., Hewitt, W.T.: Using B-Spline Curves for Hand Recognition. In: 17th International Conference on Pattern Recognition (ICPR 2004), Cambridge UK, vol. 3, pp. 274–277 (2004)Google Scholar
- 13.Osuna, E., Freund, R., Girosi, F.: Support Vector Machines: Training and Applications. MIT Artificial Intelligence Laboratory and Center for Biological and Computational Learning Department of Brain and Cognitive Sciences. A.I. Memo No 1602, C.B.C.L. Paper No 144 (1997)Google Scholar
- 15.Schlapbach, A., Bunke, H.: Off-line Handwriting Identification Using HMM Based Recognizers. In: 17th International Conference on Pattern Recognition (ICPR 2004), Cambridge UK, vol. 2, pp. 654–658 (2004)Google Scholar
- 16.Woodford, B.J., Deng, D., Benwell, G.L.: A Wavelet-based Neuro-fuzzy System forData Mining Small Image SetsGoogle Scholar