A Fingerprint Matching Algorithm Using Phase-Only Correlation

Koichi Ito, Hiroshi Nakajima, Koji Kobayashi, Takafumi Aoki, Tatsuo Higuchi

Research output: Contribution to journalArticlepeer-review

222 Citations (Scopus)

Abstract

This paper presents an algorithm for fingerprint matching using the Phase-Only Correlation (POC) function. One of the most difficult problems in human identification by fingerprints has been that the matching performance is significantly influenced by fingertip surface condition, which may vary depending on environmental or personal causes. This paper proposes a new fingerprint matching algorithm using phase spectra of fingerprint images. The proposed algorithm is highly robust against fingerprint image degradation due to inadequate fingertip conditions. A set of experiments is carried out using fingerprint images captured by a pressure sensitive fingerprint sensor. The proposed algorithm exhibits efficient identification performance even for difficult fingerprint images that could not be identified by the conventional matching algorithms.

Original languageEnglish
Pages (from-to)682-691
Number of pages10
JournalIEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
VolumeE87-A
Issue number3
Publication statusPublished - 2004 Mar

Keywords

  • Biometrics
  • Fingerprint identification
  • Fingerprint verification
  • Phase correlation
  • Phase-only correlation
  • Phase-only matched filtering

Fingerprint

Dive into the research topics of 'A Fingerprint Matching Algorithm Using Phase-Only Correlation'. Together they form a unique fingerprint.

Cite this