The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Les points singuliers des empreintes digitales, à savoir. core et delta, sont des points de référence importants pour la classification des empreintes digitales. Plusieurs approches conventionnelles telles que la méthode de l'indice de Poincaré ont été proposées ; cependant, ces approches ne sont pas fiables avec des empreintes digitales de mauvaise qualité. Cet article propose une nouvelle détection de base et delta utilisant une analyse de candidats singuliers et un graphe relationnel étendu. L'analyse de candidats singuliers permet d'utiliser à la fois les caractéristiques locales et globales des modèles de direction de crête et permet d'obtenir une tolérance élevée au bruit d'image local ; cela implique l'extraction d'emplacements où il existe une forte probabilité d'existence d'un point singulier. Les résultats expérimentaux utilisant les bases de données d'images d'empreintes digitales FVC2000 et FVC2002, qui incluent plusieurs images de mauvaise qualité, montrent que le taux de réussite de l'approche proposée est 10 % supérieur à celui de la méthode de l'indice de Poincaré pour la détection de singularité, bien que le temps de calcul moyen soit de 15 %. %-30% de plus.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Tomohiko OHTSUKA, Daisuke WATANABE, "Singular Candidate Method: Improvement of Extended Relational Graph Method for Reliable Detection of Fingerprint Singularity" in IEICE TRANSACTIONS on Information,
vol. E93-D, no. 7, pp. 1788-1797, July 2010, doi: 10.1587/transinf.E93.D.1788.
Abstract: The singular points of fingerprints, viz. core and delta, are important referential points for the classification of fingerprints. Several conventional approaches such as the Poincare index method have been proposed; however, these approaches are not reliable with poor-quality fingerprints. This paper proposes a new core and delta detection employing singular candidate analysis and an extended relational graph. Singular candidate analysis allows the use both the local and global features of ridge direction patterns and realizes high tolerance to local image noise; this involves the extraction of locations where there is high probability of the existence of a singular point. Experimental results using the fingerprint image databases FVC2000 and FVC2002, which include several poor-quality images, show that the success rate of the proposed approach is 10% higher than that of the Poincare index method for singularity detection, although the average computation time is 15%-30% greater.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E93.D.1788/_p
Copier
@ARTICLE{e93-d_7_1788,
author={Tomohiko OHTSUKA, Daisuke WATANABE, },
journal={IEICE TRANSACTIONS on Information},
title={Singular Candidate Method: Improvement of Extended Relational Graph Method for Reliable Detection of Fingerprint Singularity},
year={2010},
volume={E93-D},
number={7},
pages={1788-1797},
abstract={The singular points of fingerprints, viz. core and delta, are important referential points for the classification of fingerprints. Several conventional approaches such as the Poincare index method have been proposed; however, these approaches are not reliable with poor-quality fingerprints. This paper proposes a new core and delta detection employing singular candidate analysis and an extended relational graph. Singular candidate analysis allows the use both the local and global features of ridge direction patterns and realizes high tolerance to local image noise; this involves the extraction of locations where there is high probability of the existence of a singular point. Experimental results using the fingerprint image databases FVC2000 and FVC2002, which include several poor-quality images, show that the success rate of the proposed approach is 10% higher than that of the Poincare index method for singularity detection, although the average computation time is 15%-30% greater.},
keywords={},
doi={10.1587/transinf.E93.D.1788},
ISSN={1745-1361},
month={July},}
Copier
TY - JOUR
TI - Singular Candidate Method: Improvement of Extended Relational Graph Method for Reliable Detection of Fingerprint Singularity
T2 - IEICE TRANSACTIONS on Information
SP - 1788
EP - 1797
AU - Tomohiko OHTSUKA
AU - Daisuke WATANABE
PY - 2010
DO - 10.1587/transinf.E93.D.1788
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E93-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2010
AB - The singular points of fingerprints, viz. core and delta, are important referential points for the classification of fingerprints. Several conventional approaches such as the Poincare index method have been proposed; however, these approaches are not reliable with poor-quality fingerprints. This paper proposes a new core and delta detection employing singular candidate analysis and an extended relational graph. Singular candidate analysis allows the use both the local and global features of ridge direction patterns and realizes high tolerance to local image noise; this involves the extraction of locations where there is high probability of the existence of a singular point. Experimental results using the fingerprint image databases FVC2000 and FVC2002, which include several poor-quality images, show that the success rate of the proposed approach is 10% higher than that of the Poincare index method for singularity detection, although the average computation time is 15%-30% greater.
ER -