eprintid: 3361
rev_number: 4
eprint_status: archive
userid: 286
dir: disk0/00/00/33/61
datestamp: 2018-12-21 01:05:13
lastmod: 2018-12-21 01:05:13
status_changed: 2018-12-21 01:05:13
type: article
succeeds: 2695
metadata_visibility: show
creators_name: Le, Hong Hai
creators_name: Nguyen, Ngoc Hoa
creators_name: Nguyen, Tri Thanh
creators_id: hoa.nguyen@vnu.edu.vn
creators_id: ntthanh@vnu.edu.vn
title: Speeding up and enhancing a large-scale fingerprint identification system on GPU
ispublished: pub
subjects: IT
divisions: fac_fit
abstract: Fingerprint identification is one of the most common biometric feature problems which is used in many applications. Although state-of-the-art algorithms are very accurate, the need for fast processing a big database of millions of fingerprints is highly demanding. In this paper, we propose to adapt the fingerprint matching algorithm based on minutia cylinder-code (MCC) on Graphics Processing Units (GPUs) to speed up the matching. Another contribution of this paper is to add a consolidation stage after matching to enhance the precision. The experimental results on a GTX-680 and a K40 tesla devices with standard datasets prove the proposed algorithm can be comparable with the state-of-the-art approach, and suitable for a real time identification application.
date: 2018-05-26
date_type: published
publisher: Taylor & Francis
official_url: https://doi.org/10.1080/24751839.2017.1404712
full_text_status: public
publication: Journal of Information and Telecommunication
pagerange: 1-16
refereed: TRUE
issn: 2475-1839
citation:   Le, Hong Hai and Nguyen, Ngoc Hoa and Nguyen, Tri Thanh  (2018) Speeding up and enhancing a large-scale fingerprint identification system on GPU.  Journal of Information and Telecommunication .   pp. 1-16.  ISSN 2475-1839     
document_url: https://eprints.uet.vnu.edu.vn/eprints/id/eprint/3361/1/Speeding%20up%20and%20enhancing%20a%20large%20scale%20fingerprint%20identification%20system%20on%20GPU.pdf