A New Similarity Measure Based on Intraclass Statistics for Biometric Systems

ETRI Journal

关键词: similarity measure;    statistical test theory;    Chi-square distribution;    statistical verification;    Biometrics;   

Others  :  1184773
DOI  :  10.4218/etrij.03.0102.0017

【 摘 要 】

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.

   

【 参考文献 】

• [1]M. Bartlett and T. Sejnowsky, "Viewpoint Invariant Face Recognition using Independent Component Analysis and Attractor Networks," Neural Information Proc. Systems-Natural and Synthetic, vol. 9, 1997, pp. 817-823.
• [2]P. Belhumeur, J. Hespanha, and D. Kriegman, "Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection," IEEE trans. on Pattern Recognition and Machine Intelligence, vol. 19, no. 7, 1997, pp. 711-720.
• [3]W.W. Boles, B. Boashash, "A Human Identification Technique Using Images of the Iris and Wavelet Transform," IEEE Trans. on Signal Proc., vol. 46, no. 4, 1998, pp. 1185-1188.
• [4]W. Campbell, "A Sequence Kernel and its Applications to Speaker Recognition," Advances in Neural Information Proc. Systems, 2001.
• [5]J.G. Daugman, "High Confidence Visual Recognition of Persons by a Test of Statistical Independence," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 15, no. 11, 1993, pp. 1148-1161.
• [6]G. Kee, Y. Byun, K. Lee, and Y. Lee, "Improved Techniques for an Iris Recognition System with High Performance," AI 2001: Advances in Artificial Intelligence, LNAI 2256, 2001, pp. 177-188.
• [7]O. Lee, H. Park, and S. Choi, "PCA vs. ICA for Face Recognition," The 2000 Int’l Technical Conf. on Circuits/Systems, Computers, and Commun., 2000, pp. 873-876.
• [8]S. Lim, K. Lee, O. Byeon, and T. Kim, "Efficient Iris Recognition through Improvement Feature Vector and Classifier," ETRI J., vol. 23, no. 2, 2001, pp. 61-70.
• [9]R.P. Wildes, "Iris Recognition: An Emerging Biometric Technology," Proc. of the IEEE, vol. 85, no. 9, 1997, pp. 1348-1363.
• [10]K. Fukunaga, Introduction to Statistical Pattern Recognition, 2ed, Academic Press, INC. 1990.
• [11]A. Stuart and K. Ord, Kendall’s Advanced Theory of Statistics, 1, 6ed., Edward Arnold, 1994.
• [12]D. Ioammou, W. Huda, A.F. Laine, "Circle recognition through a 2D Hough Transform and radius histogramming," Image and Vision Computing, vol. 17, 1999, pp. 15-26.
• [13]C. Bishop, Neural Networks for Pattern Recognition, Oxford University Press, 1995.
• [14]R.M. Bolle, S. Pankanti, and N.K. Ratha, "Evaluation Techniques for Biometrics-based Authentication System (FRR)," Proc. of the Fifteens International Conf. on Pattern Recognition, vol. 2, 2000, pp. 831-837.
• [15]W. Shen, M. Surette, and R. Khanna, "Evaluation of Automated Biometrics-based Identification and Verification," Proc. of the IEEE, vol. 85, 1997, pp. 1464-1478.