Welcome to BioLab 05/10/2024 05:54
 
 


Exclusive Classification

Among the fingerprint classification approaches proposed by BioLab, it is worth mentioning:

  • Fingerprint classification by means of inexact graph matching;
  • Fingerprint classification using dynamic masks to partition the directional image;
  • Fingerprint classification based on MKL.

In particular, MKL-based classification proved to be a very powerful tool to deal with the fingerprint classification problem. The underlying idea of the approach is to find, for each class, one or more KL subspaces, which are well-suited for representing the fingerprints belonging to the class. These subspaces are created according to an optimization criterion, which attempts to minimize the average mean-square reconstruction error over a representative training set.


In 2002, BioLab published the first fingerprint classification algorithm able to meet the FBI fingerprint classification requirements: the algorithm was based on the combination of multiple MKL-classifiers and achieved 99% accuracy at 17.5% rejection on NIST DB14, thus meeting the FBI requirement (99% accuracy at 20% rejection rate).


Bibliography
(Click here if you are interested in any of the publications below)

D. Maltoni, D. Maio, A.K. Jain and J. Feng, Handbook of Fingerprint Recognition (Third Edition), Springer Nature, 2022.

D. Maltoni, D. Maio, A.K. Jain and S. Prabhakar, Handbook of Fingerprint Recognition (Second Edition), Springer (London), 2009.

R. Cappelli and D. Maio, "The State of the Art in Fingerprint Classification", in N. Ratha and R. Bolle, Automatic Fingerprint Recognition Systems, Springer, 2004. Abstract

A. Lumini and L. Nanni, "FuzzyBagging: a novel ensemble of classifiers", Pattern Recognition, vol.39, no.3, pp.488-490, March 2006. Abstract

R. Cappelli, D. Maio and D. Maltoni, "A Multi-Classifier Approach to Fingerprint Classification", Pattern Analysis and Applications Special Issue on Fusion of Multiple Classifiers, vol.5, no.2, pp.136-144, May 2002. Abstract

A. Lumini, D. Maio and D. Maltoni, "Inexact Graph Matching for Fingerprint Classification", Machine GRAPHICS & VISION Special Issue on Graph Trasformations in Pattern Generation and CAD, vol.8, no.2, pp.231-248, September 1999. Abstract

R. Cappelli, A. Lumini, D. Maio and D. Maltoni, "Fingerprint Classification by Directional Image Partitioning", IEEE Transactions on Pattern Analysis Machine Intelligence, vol.21, no.5, pp.402-421, May 1999. Abstract

R. Cappelli, D. Maio, D. Maltoni and L. Nanni, "A two-stage fingerprint classification system", in proceedings ACM SIGMM Multimedia Biometrics Methods and Applications Workshop (WBMA03), Berkley, pp.95-99, November 2003. Abstract

R. Cappelli, D. Maio and D. Maltoni, "Combining Fingerprint Classifiers", in proceedings First International Workshop on Multiple Classifier Systems (MCS2000), Cagliari, pp.351-361, June 2000. Abstract

R. Cappelli, D. Maio and D. Maltoni, "Fingerprint Classification based on Multi-space KL", in proceedings Workshop on Automatic Identification Advances Technologies (AutoID'99), Summit (NJ), pp.117-120, October 1999. Abstract

D. Maio and D. Maltoni, "A Structural Approach to Fingerprint Classification", in proceedings 13th International Conference on Pattern Recognition (ICPR), Vienna, pp.578-585, August 1996. Abstract


Copyright © 2024 Biometric System Laboratory