Environmentally realistic fingerprint-image generation with evolutionary filter-bank optimization

Jin Hyuk Hong, Ung Keun Cho, Sung Bae Cho

Research output: Contribution to journalArticle

Abstract

Constructing a fingerprint database is important to evaluate the performance of an automatic fingerprint recognition system. Because of the difficulty of collecting samples, there are only few benchmark databases available. Moreover, it is hard to evaluate how robust the system is against various environments with those databases. This paper presents a novel method that generates fingerprint images automatically from only a few training samples by using the evolutionary algorithm. Fingerprints generated by the proposed method include similar characteristics of those collected from the corresponding real environment. The proposed method has been verified by comparing with real fingerprints, indicating the usefulness of the method.

Original languageEnglish
Pages (from-to)6201-6212
Number of pages12
JournalExpert Systems with Applications
Volume39
Issue number6
DOIs
Publication statusPublished - 2012 May 1

Fingerprint

Filter banks
Evolutionary algorithms

All Science Journal Classification (ASJC) codes

  • Engineering(all)
  • Computer Science Applications
  • Artificial Intelligence

Cite this

@article{35fc3c90cee74c5eb5126717479aad64,
title = "Environmentally realistic fingerprint-image generation with evolutionary filter-bank optimization",
abstract = "Constructing a fingerprint database is important to evaluate the performance of an automatic fingerprint recognition system. Because of the difficulty of collecting samples, there are only few benchmark databases available. Moreover, it is hard to evaluate how robust the system is against various environments with those databases. This paper presents a novel method that generates fingerprint images automatically from only a few training samples by using the evolutionary algorithm. Fingerprints generated by the proposed method include similar characteristics of those collected from the corresponding real environment. The proposed method has been verified by comparing with real fingerprints, indicating the usefulness of the method.",
author = "Hong, {Jin Hyuk} and Cho, {Ung Keun} and Cho, {Sung Bae}",
year = "2012",
month = "5",
day = "1",
doi = "10.1016/j.eswa.2011.12.010",
language = "English",
volume = "39",
pages = "6201--6212",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier Limited",
number = "6",

}

Environmentally realistic fingerprint-image generation with evolutionary filter-bank optimization. / Hong, Jin Hyuk; Cho, Ung Keun; Cho, Sung Bae.

In: Expert Systems with Applications, Vol. 39, No. 6, 01.05.2012, p. 6201-6212.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Environmentally realistic fingerprint-image generation with evolutionary filter-bank optimization

AU - Hong, Jin Hyuk

AU - Cho, Ung Keun

AU - Cho, Sung Bae

PY - 2012/5/1

Y1 - 2012/5/1

N2 - Constructing a fingerprint database is important to evaluate the performance of an automatic fingerprint recognition system. Because of the difficulty of collecting samples, there are only few benchmark databases available. Moreover, it is hard to evaluate how robust the system is against various environments with those databases. This paper presents a novel method that generates fingerprint images automatically from only a few training samples by using the evolutionary algorithm. Fingerprints generated by the proposed method include similar characteristics of those collected from the corresponding real environment. The proposed method has been verified by comparing with real fingerprints, indicating the usefulness of the method.

AB - Constructing a fingerprint database is important to evaluate the performance of an automatic fingerprint recognition system. Because of the difficulty of collecting samples, there are only few benchmark databases available. Moreover, it is hard to evaluate how robust the system is against various environments with those databases. This paper presents a novel method that generates fingerprint images automatically from only a few training samples by using the evolutionary algorithm. Fingerprints generated by the proposed method include similar characteristics of those collected from the corresponding real environment. The proposed method has been verified by comparing with real fingerprints, indicating the usefulness of the method.

UR - http://www.scopus.com/inward/record.url?scp=84856540636&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84856540636&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2011.12.010

DO - 10.1016/j.eswa.2011.12.010

M3 - Article

AN - SCOPUS:84856540636

VL - 39

SP - 6201

EP - 6212

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

IS - 6

ER -