Conference Paper

Fingerprint biometric authentication based on local global graphs

Coll. of Eng., Wright State Univ., Dayton, OH, USA
DOI: 10.1109/NAECON.2009.5426628 Conference: Aerospace & Electronics Conference (NAECON), Proceedings of the IEEE 2009 National
Source: IEEE Xplore


In this work, we present a method for fingerprint based biometric authentication using the Local Global (LG) Graph methodology. Local graphs of the pre-processed fingerprint image are first calculated and combined to form a Global graph that is stored in a database for the purpose of authentication. The distance between the Global graphs of the presented and the stored fingerprint images is calculated and based on a threshold, subject authenticity is established.

7 Reads
  • [Show abstract] [Hide abstract]
    ABSTRACT: Fingerprint verification is used for person authentication. This has wide application from low risk to safety critical authentication systems. Research in this field has a long history. A number of approaches have been implemented for effective and efficient fingerprint verification. This article reports the results of quantitative comparison of different fingerprint verification approaches. We conducted an experiment of fingerprint verification using three approaches- biometric technique, Genetic algorithm and Back propagation neural network. The performance of the three approaches was assessed in terms of False Acceptance Rate (FAR), False Rejection Rate (FRR) and execution time. Our comparative analysis reveals that for small number of images there is no significant difference in performance among the chosen approaches.
    No preview · Conference Paper · Jan 2011