Automatic fingerprint classification based on embedded Hidden Markov Models

Automatic fingerprint classification provides an important indexing scheme to facilitate efficient matching in large-scale fingerprint databases for any Automatic Fingerprint Identification System (AFIS). A novel method of fingerprint classification, which is based on embedded Hidden Markov Models (HMM) and the fingerprint's orientation field, is described in this paper. The accurate and robust fingerprint classification can be achieved with extracting features from a fingerprint, forming the samples of observation vectors, and training the embedded HMM. Results are presented on two fingerprint databases, Fingdb and Finger/spl I.bar/DUT, respectively.

[1]  Robert K. L. Gay,et al.  Geometric framework for fingerprint image classification , 1997, Pattern Recognit..

[2]  Dario Maio,et al.  A structural approach to fingerprint classification , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[3]  Andrew W. Senior,et al.  A Combination Fingerprint Classifier , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  A. R. Rao,et al.  A Taxonomy for Texture Description and Identification , 1990, Springer Series in Perception Engineering.

[5]  Anil K. Jain,et al.  Fingerprint classification and matching using a filterbank , 2001 .

[6]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[7]  Rama Chellappa,et al.  Evaluation of pattern classifiers for fingerprint and OCR applications , 1994, Pattern Recognit..

[8]  Pierre Baldi,et al.  Neural Networks for Fingerprint Recognition , 1993, Neural Computation.

[9]  A. Senior,et al.  A hidden Markov model fingerprint classifier , 1997, Conference Record of the Thirty-First Asilomar Conference on Signals, Systems and Computers (Cat. No.97CB36136).