A study on multi-unit fingerprint verification

Kangrok Lee, Kang Ryoung Park, Jain Jang, Sanghoon Lee, Jaihie Kim

Research output: Contribution to journalConference articlepeer-review

4 Citations (Scopus)


Previous fingerprint verification systems have achieved good results, but these have been affected by the quality of input data. Fingerprint verification systems that use many fingers or multiple impressions of the same finger are more efficient and reliable than systems that use a single finger. However, multiple impressions give inconvenience to the user and increase the overall verification time. Therefore, we use only two fingers (multi-unit fusion) to improve performance of the fingerprint verification system. We show that performance can be improved by selecting a better quality fingerprint image of two fingerprints. Also, we propose a new quality checking algorithm composed of three stages. Our experimental results show that when the quality checking algorithm is performed by selecting a better quality fingerprint image of two fingerprints, there is a significance improvement in performance of the fingerprint verification system.

Original languageEnglish
Pages (from-to)141-150
Number of pages10
JournalLecture Notes in Computer Science
Publication statusPublished - 2005
Event5th International Conference on Audio - and Video-Based Biometric Person Authentication, AVBPA 2005 - Hilton Rye Town, NY, United States
Duration: 2005 Jul 202005 Jul 22

All Science Journal Classification (ASJC) codes

  • Theoretical Computer Science
  • Computer Science(all)


Dive into the research topics of 'A study on multi-unit fingerprint verification'. Together they form a unique fingerprint.

Cite this