Implementation and evaluation of NIST Biometric Image Software for fingerprint recognition

Document type: Conference Papers
Peer reviewed: Yes
Full text:
Author(s): Sainath Maddala, Sreekanth Rao Tangellapally, Josef Ström Bartunek, Mikael Nilsson
Title: Implementation and evaluation of NIST Biometric Image Software for fingerprint recognition
Conference name: ISSNIP Biosignals and Biorobotics Conference: Biosignals and Robotics for Better and Safer Living, BRC
Year: 2011
Pagination: 18-22
ISBN: 978-142448212-2
Publisher: IEEE
City: Vitoria
URI/DOI: 10.1109/BRC.2011.5740672
Organization: Blekinge Institute of Technology
Department: School of Engineering - Dept. of Electrical Engineering School of Engineering - Dept. of Signal Processing, School of Engineering - Dept. of Signal Processing (*** !Error ***)
*** Error ***
+46 455 38 50 00
*** Error ***
Language: English
Abstract: Fingerprints are rich in details which are in the form of discontinuities in ridges known as minutiae and are unique for each person. This paper describes implementation and evaluation of an existing fingerprint recognition system in MATLAB environment. The selected system is developed by National Institute of Standards and Technology (NIST) denoted as Biometric Image Software (NBIS). The NBIS source code is written in ANSI C programming language. To be able to evaluate the algorithm in MATLAB a C language MEX-files has been used. The NBIS support both minutiae extraction and minutiae matching functions that have been employed in the evaluation. The implemented system has been tested on a Fingerprint Verification Competition (FVC) database. The results are presented as Receiver Operating Characteristics (ROC) graphs.
Subject: Signal processing\Image and Video Processing
Keywords: Biometric, MEX-file, NIST Fingerprint Verification, ROC graphs
Edit