Distributed incremental fingerprint identification with reduced database penetration rate using a hierarchical classification based on feature fusion and selection

Fingerprint recognition has been a hot research topic along the last few decades, with many applications and ever growing populations to identify. The need of flexible, fast identification systems is therefore patent in such situations. In this context, fingerprint classification is commonly used to...

Full description

Bibliographic Details
Main Authors: Peralta, Daniel, Triguero, Isaac, García, Salvador, Saeys, Yvan, Benitez, Jose M., Herrera, Francisco
Format: Article
Published: Elsevier 2017
Subjects:
Online Access:https://eprints.nottingham.ac.uk/41561/
_version_ 1848796303067185152
author Peralta, Daniel
Triguero, Isaac
García, Salvador
Saeys, Yvan
Benitez, Jose M.
Herrera, Francisco
author_facet Peralta, Daniel
Triguero, Isaac
García, Salvador
Saeys, Yvan
Benitez, Jose M.
Herrera, Francisco
author_sort Peralta, Daniel
building Nottingham Research Data Repository
collection Online Access
description Fingerprint recognition has been a hot research topic along the last few decades, with many applications and ever growing populations to identify. The need of flexible, fast identification systems is therefore patent in such situations. In this context, fingerprint classification is commonly used to improve the speed of the identification. This paper proposes a complete identification system with a hierarchical classification framework that fuses the information of multiple feature extractors. A feature selection is applied to improve the classification accuracy. Finally, the distributed identification is carried out with an incremental search, exploring the classes according to the probability order given by the classifier. A single parameter tunes the trade-off between identification time and accuracy. The proposal is evaluated over two NIST databases and a large synthetic database, yielding penetration rates close to the optimal values that can be reached with classification, leading to low identification times with small or no accuracy loss.
first_indexed 2025-11-14T19:45:50Z
format Article
id nottingham-41561
institution University of Nottingham Malaysia Campus
institution_category Local University
last_indexed 2025-11-14T19:45:50Z
publishDate 2017
publisher Elsevier
recordtype eprints
repository_type Digital Repository
spelling nottingham-415612020-05-04T18:50:06Z https://eprints.nottingham.ac.uk/41561/ Distributed incremental fingerprint identification with reduced database penetration rate using a hierarchical classification based on feature fusion and selection Peralta, Daniel Triguero, Isaac García, Salvador Saeys, Yvan Benitez, Jose M. Herrera, Francisco Fingerprint recognition has been a hot research topic along the last few decades, with many applications and ever growing populations to identify. The need of flexible, fast identification systems is therefore patent in such situations. In this context, fingerprint classification is commonly used to improve the speed of the identification. This paper proposes a complete identification system with a hierarchical classification framework that fuses the information of multiple feature extractors. A feature selection is applied to improve the classification accuracy. Finally, the distributed identification is carried out with an incremental search, exploring the classes according to the probability order given by the classifier. A single parameter tunes the trade-off between identification time and accuracy. The proposal is evaluated over two NIST databases and a large synthetic database, yielding penetration rates close to the optimal values that can be reached with classification, leading to low identification times with small or no accuracy loss. Elsevier 2017-06-15 Article PeerReviewed Peralta, Daniel, Triguero, Isaac, García, Salvador, Saeys, Yvan, Benitez, Jose M. and Herrera, Francisco (2017) Distributed incremental fingerprint identification with reduced database penetration rate using a hierarchical classification based on feature fusion and selection. Knowledge-Based Systems, 126 . pp. 91-103. ISSN 1872-7409 Fingerprint recognition; Fingerprint identification; Fingerprint classification; Large databases; Feature selection; Hierarchical classification http://www.sciencedirect.com/science/article/pii/S095070511730134X doi:/10.1016/j.knosys.2017.03.014 doi:/10.1016/j.knosys.2017.03.014
spellingShingle Fingerprint recognition; Fingerprint identification; Fingerprint classification; Large databases; Feature selection; Hierarchical classification
Peralta, Daniel
Triguero, Isaac
García, Salvador
Saeys, Yvan
Benitez, Jose M.
Herrera, Francisco
Distributed incremental fingerprint identification with reduced database penetration rate using a hierarchical classification based on feature fusion and selection
title Distributed incremental fingerprint identification with reduced database penetration rate using a hierarchical classification based on feature fusion and selection
title_full Distributed incremental fingerprint identification with reduced database penetration rate using a hierarchical classification based on feature fusion and selection
title_fullStr Distributed incremental fingerprint identification with reduced database penetration rate using a hierarchical classification based on feature fusion and selection
title_full_unstemmed Distributed incremental fingerprint identification with reduced database penetration rate using a hierarchical classification based on feature fusion and selection
title_short Distributed incremental fingerprint identification with reduced database penetration rate using a hierarchical classification based on feature fusion and selection
title_sort distributed incremental fingerprint identification with reduced database penetration rate using a hierarchical classification based on feature fusion and selection
topic Fingerprint recognition; Fingerprint identification; Fingerprint classification; Large databases; Feature selection; Hierarchical classification
url https://eprints.nottingham.ac.uk/41561/
https://eprints.nottingham.ac.uk/41561/
https://eprints.nottingham.ac.uk/41561/