An Integrated Prediction Model for Biometrics

This paper addresses the problem of predicting recognition performance on a large population from a small gallery. Unlike the current approaches based on a binomial model that use match and non-match scores, this paper presents a generalized two-dimensional model that integrates a hypergeometric probability distribution model explicitly with a binomial model. The distortion caused by sensor noise, feature uncertainty, feature occlusion and feature clutter in the gallery data is modeled. The prediction model provides performance measures as a function of rank, population size and the number of distorted images. Results are shown on NIST-4 fingerprint database and 3D ear database for various sizes of gallery and the population.

[1]  P J. Phillips,et al.  Face Recognition Vendor Test 2000: Evaluation Report , 2001 .

[2]  Bir Bhanu,et al.  Robust fingerprint identification , 2002, Proceedings. International Conference on Image Processing.

[3]  P. J. Phillips,et al.  Models of large population recognition performance , 2004, CVPR 2004.

[4]  Aaron F. Bobick,et al.  Using similarity scores from a small gallery to estimate recognition performance for larger galleries , 2003, 2003 IEEE International SOI Conference. Proceedings (Cat. No.03CH37443).

[5]  Aaron F. Bobick,et al.  Predicting Large Population Data Cumulative Match Characteristic Performance from Small Population Data , 2003, AVBPA.

[6]  John Daugman,et al.  The importance of being random: statistical principles of iris recognition , 2003, Pattern Recognit..

[7]  James L. Wayman,et al.  Error rate equations for the general biometric system , 1999, IEEE Robotics Autom. Mag..

[8]  Bir Bhanu,et al.  On the fundamental performance for fingerprint matching , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[9]  Anil K. Jain,et al.  Handbook of Fingerprint Recognition , 2005, Springer Professional Computing.

[10]  P. Jonathon Phillips,et al.  Face recognition vendor test 2002 , 2003, 2003 IEEE International SOI Conference. Proceedings (Cat. No.03CH37443).

[11]  Bir Bhanu,et al.  Performance modeling of vote-based object recognition , 2003, SPIE Defense + Commercial Sensing.