Finger-knuckle-print for identity verification based on difference images

Jooyoung Kim, Kangrok Oh, Beng Jin Teoh, Kar Ann Toh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

In this paper, we propose to extract global directional features of finger-knuckle-print based on difference image for identity verification. In order to simplify the formulation for computational complexity reduction, the proposed horizontal and vertical difference images are generated based on matrix projection operation. Subsequently, a Heaviside step function is adopted for image ternarization. Next, we extract Fourier features from these ternary images by means of two-dimensional discrete Fourier transform. Finally, matching between extracted features is performed based on an Euclidean distance comparison. Our experiments on IIT Delhi Finger-Knuckle-Image Version 1.0 database show encouraging results in terms of verification accuracy and computing efficiency.

Original languageEnglish
Title of host publicationProceedings of the 2016 IEEE 11th Conference on Industrial Electronics and Applications, ICIEA 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1073-1077
Number of pages5
ISBN (Electronic)9781509026050
DOIs
Publication statusPublished - 2016 Oct 19
Event11th IEEE Conference on Industrial Electronics and Applications, ICIEA 2016 - Hefei, China
Duration: 2016 Jun 52016 Jun 7

Publication series

NameProceedings of the 2016 IEEE 11th Conference on Industrial Electronics and Applications, ICIEA 2016

Other

Other11th IEEE Conference on Industrial Electronics and Applications, ICIEA 2016
CountryChina
CityHefei
Period16/6/516/6/7

Fingerprint

Fingerprint
Discrete Fourier transforms
Computational complexity
Heaviside step function
Projection Matrix
Discrete Fourier transform
Euclidean Distance
Ternary
Experiments
Simplify
Computational Complexity
Horizontal
Vertical
Formulation
Computing
Experiment

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering
  • Industrial and Manufacturing Engineering
  • Control and Optimization

Cite this

Kim, J., Oh, K., Teoh, B. J., & Toh, K. A. (2016). Finger-knuckle-print for identity verification based on difference images. In Proceedings of the 2016 IEEE 11th Conference on Industrial Electronics and Applications, ICIEA 2016 (pp. 1073-1077). [7603741] (Proceedings of the 2016 IEEE 11th Conference on Industrial Electronics and Applications, ICIEA 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICIEA.2016.7603741
Kim, Jooyoung ; Oh, Kangrok ; Teoh, Beng Jin ; Toh, Kar Ann. / Finger-knuckle-print for identity verification based on difference images. Proceedings of the 2016 IEEE 11th Conference on Industrial Electronics and Applications, ICIEA 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 1073-1077 (Proceedings of the 2016 IEEE 11th Conference on Industrial Electronics and Applications, ICIEA 2016).
@inproceedings{9b1c1ea45ddb43628067f8b674ac42b5,
title = "Finger-knuckle-print for identity verification based on difference images",
abstract = "In this paper, we propose to extract global directional features of finger-knuckle-print based on difference image for identity verification. In order to simplify the formulation for computational complexity reduction, the proposed horizontal and vertical difference images are generated based on matrix projection operation. Subsequently, a Heaviside step function is adopted for image ternarization. Next, we extract Fourier features from these ternary images by means of two-dimensional discrete Fourier transform. Finally, matching between extracted features is performed based on an Euclidean distance comparison. Our experiments on IIT Delhi Finger-Knuckle-Image Version 1.0 database show encouraging results in terms of verification accuracy and computing efficiency.",
author = "Jooyoung Kim and Kangrok Oh and Teoh, {Beng Jin} and Toh, {Kar Ann}",
year = "2016",
month = "10",
day = "19",
doi = "10.1109/ICIEA.2016.7603741",
language = "English",
series = "Proceedings of the 2016 IEEE 11th Conference on Industrial Electronics and Applications, ICIEA 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1073--1077",
booktitle = "Proceedings of the 2016 IEEE 11th Conference on Industrial Electronics and Applications, ICIEA 2016",
address = "United States",

}

Kim, J, Oh, K, Teoh, BJ & Toh, KA 2016, Finger-knuckle-print for identity verification based on difference images. in Proceedings of the 2016 IEEE 11th Conference on Industrial Electronics and Applications, ICIEA 2016., 7603741, Proceedings of the 2016 IEEE 11th Conference on Industrial Electronics and Applications, ICIEA 2016, Institute of Electrical and Electronics Engineers Inc., pp. 1073-1077, 11th IEEE Conference on Industrial Electronics and Applications, ICIEA 2016, Hefei, China, 16/6/5. https://doi.org/10.1109/ICIEA.2016.7603741

Finger-knuckle-print for identity verification based on difference images. / Kim, Jooyoung; Oh, Kangrok; Teoh, Beng Jin; Toh, Kar Ann.

Proceedings of the 2016 IEEE 11th Conference on Industrial Electronics and Applications, ICIEA 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 1073-1077 7603741 (Proceedings of the 2016 IEEE 11th Conference on Industrial Electronics and Applications, ICIEA 2016).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Finger-knuckle-print for identity verification based on difference images

AU - Kim, Jooyoung

AU - Oh, Kangrok

AU - Teoh, Beng Jin

AU - Toh, Kar Ann

PY - 2016/10/19

Y1 - 2016/10/19

N2 - In this paper, we propose to extract global directional features of finger-knuckle-print based on difference image for identity verification. In order to simplify the formulation for computational complexity reduction, the proposed horizontal and vertical difference images are generated based on matrix projection operation. Subsequently, a Heaviside step function is adopted for image ternarization. Next, we extract Fourier features from these ternary images by means of two-dimensional discrete Fourier transform. Finally, matching between extracted features is performed based on an Euclidean distance comparison. Our experiments on IIT Delhi Finger-Knuckle-Image Version 1.0 database show encouraging results in terms of verification accuracy and computing efficiency.

AB - In this paper, we propose to extract global directional features of finger-knuckle-print based on difference image for identity verification. In order to simplify the formulation for computational complexity reduction, the proposed horizontal and vertical difference images are generated based on matrix projection operation. Subsequently, a Heaviside step function is adopted for image ternarization. Next, we extract Fourier features from these ternary images by means of two-dimensional discrete Fourier transform. Finally, matching between extracted features is performed based on an Euclidean distance comparison. Our experiments on IIT Delhi Finger-Knuckle-Image Version 1.0 database show encouraging results in terms of verification accuracy and computing efficiency.

UR - http://www.scopus.com/inward/record.url?scp=84997471090&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84997471090&partnerID=8YFLogxK

U2 - 10.1109/ICIEA.2016.7603741

DO - 10.1109/ICIEA.2016.7603741

M3 - Conference contribution

AN - SCOPUS:84997471090

T3 - Proceedings of the 2016 IEEE 11th Conference on Industrial Electronics and Applications, ICIEA 2016

SP - 1073

EP - 1077

BT - Proceedings of the 2016 IEEE 11th Conference on Industrial Electronics and Applications, ICIEA 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Kim J, Oh K, Teoh BJ, Toh KA. Finger-knuckle-print for identity verification based on difference images. In Proceedings of the 2016 IEEE 11th Conference on Industrial Electronics and Applications, ICIEA 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 1073-1077. 7603741. (Proceedings of the 2016 IEEE 11th Conference on Industrial Electronics and Applications, ICIEA 2016). https://doi.org/10.1109/ICIEA.2016.7603741