Fingerprint identification using graph matching

https://doi.org/10.1016/0031-3203(86)90017-8Get rights and content

Abstract

A new algorithm for automated fingerprint encoding and matching is presented. The algorithm is intended to be insensitive to imperfections introduced during fingerprint registration, such as noise, distortion and displacement. A fingerprint is represented in the form of a graph whose nodes correspond to ridges in the print. Edges of the graph connect nodes that represent neighboring or intersecting ridges. Hence the graph structure captures the topological relationships within the fingerprint. The algorithm has been implemented and tested using a library of real-life fingerprint images.

References (28)

  • T.Ch. Malleswara Rao

    Feature extraction for fingerprint classification

    Pattern Recognition

    (1976)
  • Fingerprints. Royal Canadian Mounted Police, Ottawa,...
  • J.L. Muerle et al.

    EDP security through positive identification

  • C.H. Bean et al.

    Personal Access Control

  • Lt.J. Woodard et al.

    Automated entry control: RADC technology development results and future plans

  • R.G. Bradley

    Performance estimates for personnel access control systems

  • M. Eleccion

    Automatic fingerprint identification

    Spectrum

    (1973)
  • D.H. McMahon et al.

    A hybrid optical computer processing technique for fingerprint identification

    IEEE Trans. Comp.

    (1975)
  • K. Millard

    An approach to the automatic retrieval of latent fingerprints

  • P.K. Shizume et al.

    A computer technical fingerprint search system

  • T.K. Lindh et al.

    An automated fingerprint retrieval system

  • R.P. Chiralo et al.

    Adaptive digital enhancement of latent fingerprints

  • C.B. Shelman et al.

    A decimal Henry system

  • C.B. Shelman

    Fingerprint classification—theory and application

  • Cited by (136)

    • EEG-based user identification system using 1D-convolutional long short-term memory neural networks

      2019, Expert Systems with Applications
      Citation Excerpt :

      A biometric system is often designed to extract features by applying signal processing, machine learning and pattern recognition techniques on the user’s physiological signals, and compare the features with the users’ profiles/templates stored in the database. Physiological and behavioral biometric traits, such as fingerprint (Isenor & Zaky, 1986), face (Samaria & Harter, 1994), gait (Sun & Lo, 2018), and electrocardiography (ECG) (Zhao, Yang, Chen, & Luo, 2013) have been widely accepted and applied in user identification systems. Despite the popularity of such biometric systems, there are weaknesses in using fingerprint, iris or voice for user identification.

    • A fast projected fixed-point algorithm for large graph matching

      2016, Pattern Recognition
      Citation Excerpt :

      Graph matching, aiming to find the optimal correspondences between the nodes of two graphs, is an important and active topic of research in computer vision and pattern recognition [1,2]. It has been extensively applied in various fields including optical character recognition [3,4], object recognition [5,6], shape matching [6–8], face recognition [9], feature correspondence [10], point matching [11], image retrieval [12], video indexing [13], document processing [14], protein classification [15] and fingerprint identification [16]. Graph matching is in general a NP-hard discrete optimization problem.

    • Handbook of fingerprint recognition: Third edition

      2022, Handbook of Fingerprint Recognition: Third Edition
    View all citing articles on Scopus

    This work was partially supported by the Natural Sciences and Engineering Research Council of Canada, under grant No. A8994.

    View full text