In this paper, we present a fingerprint classification
approach based on a novel feature-learning algorithm.
Unlike current research for fingerprint classification
that generally uses well defined meaningful features,
our approach is based on Genetic Programming (GP),
which learns to discover composite operators and
features that are evolved from combinations of
primitive image processing operations. Our experimental
results show that our approach can find good composite
operators to effectively extract useful features. Using
a Bayesian classifier, without rejecting any
fingerprints from the NIST-4 database, the correct
rates for 4- and 5-class classification are 93.3percent
and 91.6percent, respectively, which compare favourably
with other published research and are one of the best
results published to date.
%0 Journal Article
%1 Tan:2006:tSMC
%A Tan, Xuejun
%A Bhanu, B.
%A Lin, Yingqiang
%D Aug
%J IEEE Transactions on Systems, Man and Cybernetics,
Part C: Applications and Reviews
%K (artificial Bayes Bayesian NIST-4 algorithm, algorithms, classification classification, classifier, composite database, databases discovery, extraction, feature feature-learning fingerprint genetic identification, image intelligence), learning method, methods, operations operator primitive processing programming, visual
%N 3
%P 287--300
%R 10.1109/TSMCC.2005.848167
%T Fingerprint classification based on learned features
%V 35
%X In this paper, we present a fingerprint classification
approach based on a novel feature-learning algorithm.
Unlike current research for fingerprint classification
that generally uses well defined meaningful features,
our approach is based on Genetic Programming (GP),
which learns to discover composite operators and
features that are evolved from combinations of
primitive image processing operations. Our experimental
results show that our approach can find good composite
operators to effectively extract useful features. Using
a Bayesian classifier, without rejecting any
fingerprints from the NIST-4 database, the correct
rates for 4- and 5-class classification are 93.3percent
and 91.6percent, respectively, which compare favourably
with other published research and are one of the best
results published to date.
@article{Tan:2006:tSMC,
abstract = {In this paper, we present a fingerprint classification
approach based on a novel feature-learning algorithm.
Unlike current research for fingerprint classification
that generally uses well defined meaningful features,
our approach is based on Genetic Programming (GP),
which learns to discover composite operators and
features that are evolved from combinations of
primitive image processing operations. Our experimental
results show that our approach can find good composite
operators to effectively extract useful features. Using
a Bayesian classifier, without rejecting any
fingerprints from the NIST-4 database, the correct
rates for 4- and 5-class classification are 93.3percent
and 91.6percent, respectively, which compare favourably
with other published research and are one of the best
results published to date.},
added-at = {2008-06-19T17:46:40.000+0200},
author = {Tan, Xuejun and Bhanu, B. and Lin, Yingqiang},
biburl = {https://www.bibsonomy.org/bibtex/2797af734fa2ebc20d8ad574c5a7eeddd/brazovayeye},
doi = {10.1109/TSMCC.2005.848167},
interhash = {fccb4e2cdd23d80d8db7162a74e835a4},
intrahash = {797af734fa2ebc20d8ad574c5a7eeddd},
issn = {1094-6977},
journal = {IEEE Transactions on Systems, Man and Cybernetics,
Part C: Applications and Reviews},
keywords = {(artificial Bayes Bayesian NIST-4 algorithm, algorithms, classification classification, classifier, composite database, databases discovery, extraction, feature feature-learning fingerprint genetic identification, image intelligence), learning method, methods, operations operator primitive processing programming, visual},
number = 3,
pages = {287--300},
timestamp = {2008-06-19T17:52:35.000+0200},
title = {Fingerprint classification based on learned features},
volume = 35,
year = {Aug}
}