Fingerprint verification using computational geometry

Manuel Ramírez-Flores, Gualberto Aguilar-Torres, Gina Gallegos-García

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

© The author; licensee Universidad Nacional de Colombia. This paper presents a robust minutiae based method for fingerprint verification. The proposed method uses Delaunay Triangulation to represent minutiae as nodes of a connected graph composed of triangles. The minimum angle over all triangulations is maximized, which gives local stability to the constructed structures against rotation and translation variations. Geometric thresholds and minutiae data were used to characterize the triangulations created from input and template fingerprint images. The effectiveness of the proposed method is confirmed through calculations of false acceptance rate (FAR), false rejected rate (FRR) and equal error rate (EER) over FVC2002 databases compared to the results of other approaches.
Original languageAmerican English
Pages (from-to)128-137
Number of pages10
JournalDYNA (Colombia)
DOIs
StatePublished - 1 Feb 2016

Fingerprint

Computational geometry
Triangulation

Cite this

Ramírez-Flores, Manuel ; Aguilar-Torres, Gualberto ; Gallegos-García, Gina. / Fingerprint verification using computational geometry. In: DYNA (Colombia). 2016 ; pp. 128-137.
@article{3714f60c4ea74f67bc2d039c1ea7a2ef,
title = "Fingerprint verification using computational geometry",
abstract = "{\circledC} The author; licensee Universidad Nacional de Colombia. This paper presents a robust minutiae based method for fingerprint verification. The proposed method uses Delaunay Triangulation to represent minutiae as nodes of a connected graph composed of triangles. The minimum angle over all triangulations is maximized, which gives local stability to the constructed structures against rotation and translation variations. Geometric thresholds and minutiae data were used to characterize the triangulations created from input and template fingerprint images. The effectiveness of the proposed method is confirmed through calculations of false acceptance rate (FAR), false rejected rate (FRR) and equal error rate (EER) over FVC2002 databases compared to the results of other approaches.",
author = "Manuel Ram{\'i}rez-Flores and Gualberto Aguilar-Torres and Gina Gallegos-Garc{\'i}a",
year = "2016",
month = "2",
day = "1",
doi = "10.15446/dyna.v83n195.46323",
language = "American English",
pages = "128--137",
journal = "DYNA (Colombia)",
issn = "0012-7353",
publisher = "Universidad Nacional de Colombia",

}

Fingerprint verification using computational geometry. / Ramírez-Flores, Manuel; Aguilar-Torres, Gualberto; Gallegos-García, Gina.

In: DYNA (Colombia), 01.02.2016, p. 128-137.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Fingerprint verification using computational geometry

AU - Ramírez-Flores, Manuel

AU - Aguilar-Torres, Gualberto

AU - Gallegos-García, Gina

PY - 2016/2/1

Y1 - 2016/2/1

N2 - © The author; licensee Universidad Nacional de Colombia. This paper presents a robust minutiae based method for fingerprint verification. The proposed method uses Delaunay Triangulation to represent minutiae as nodes of a connected graph composed of triangles. The minimum angle over all triangulations is maximized, which gives local stability to the constructed structures against rotation and translation variations. Geometric thresholds and minutiae data were used to characterize the triangulations created from input and template fingerprint images. The effectiveness of the proposed method is confirmed through calculations of false acceptance rate (FAR), false rejected rate (FRR) and equal error rate (EER) over FVC2002 databases compared to the results of other approaches.

AB - © The author; licensee Universidad Nacional de Colombia. This paper presents a robust minutiae based method for fingerprint verification. The proposed method uses Delaunay Triangulation to represent minutiae as nodes of a connected graph composed of triangles. The minimum angle over all triangulations is maximized, which gives local stability to the constructed structures against rotation and translation variations. Geometric thresholds and minutiae data were used to characterize the triangulations created from input and template fingerprint images. The effectiveness of the proposed method is confirmed through calculations of false acceptance rate (FAR), false rejected rate (FRR) and equal error rate (EER) over FVC2002 databases compared to the results of other approaches.

U2 - 10.15446/dyna.v83n195.46323

DO - 10.15446/dyna.v83n195.46323

M3 - Article

SP - 128

EP - 137

JO - DYNA (Colombia)

JF - DYNA (Colombia)

SN - 0012-7353

ER -