Skip to main navigation Skip to search Skip to main content

Improved local correlation method for fingerprint matching

  • Quincy University
  • SUNY Buffalo

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations

Abstract

In our previous study, we presented the idea of verifying minutiae based fingerprint match by local correlation methods, where both the global minutiae distribution structure and the local matching similarity between the two fingerprints are considered. In this paper, we conduct two algorithms to enhance the evaluation of local correlation score, thus improve our previous local correlation fingerprint matching method. The local image enhancement algorithm is used to improve the quality of the fingerprint image, based upon local ridge information, when the correlation score is calculated. The gradient decent algorithm is used to boost the speed of local fingerprint image registration around the potential matching areas. FVC2002 DB1 database is used to test the proposed approaches. Experimental result shows the improvement on both time and precision.

Original languageEnglish
Title of host publicationProceedings - 2014 2nd International Symposium on Computing and Networking, CANDAR 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages560-562
Number of pages3
ISBN (Electronic)9781479941520
DOIs
StatePublished - 2014
Event2nd International Symposium on Computing and Networking, CANDAR 2014 - Shizuoka, Japan
Duration: Dec 10 2014Dec 12 2014

Publication series

NameProceedings - 2014 2nd International Symposium on Computing and Networking, CANDAR 2014

Conference

Conference2nd International Symposium on Computing and Networking, CANDAR 2014
Country/TerritoryJapan
CityShizuoka
Period12/10/1412/12/14

Keywords

  • Fingerprint matching
  • Gradient decent
  • Image enhancement
  • Image registration
  • Local correlation

Fingerprint

Dive into the research topics of 'Improved local correlation method for fingerprint matching'. Together they form a unique fingerprint.

Cite this