Verification and Validation of a Fingerprint Image Registration Software
- PDF / 1,029,564 Bytes
- 9 Pages / 600.03 x 792 pts Page_size
- 14 Downloads / 312 Views
Verification and Validation of a Fingerprint Image Registration Software Dejan Desovski,1 Vijai Gandikota,1 Yan Liu,2 Yue Jiang,1 and Bojan Cukic1 1 Lane
Department of Computer Science and Electrical Engineering, West Virginia University, Morgantown, WV 26506-6109, USA Labs, Motorola Inc., Schaumburg, IL 60196, USA
2 Motorola
Received 28 February 2005; Revised 14 September 2005; Accepted 21 October 2005 The need for reliable identification and authentication is driving the increased use of biometric devices and systems. Verification and validation techniques applicable to these systems are rather immature and ad hoc, yet the consequences of the wide deployment of biometric systems could be significant. In this paper we discuss an approach towards validation and reliability estimation of a fingerprint registration software. Our validation approach includes the following three steps: (a) the validation of the source code with respect to the system requirements specification; (b) the validation of the optimization algorithm, which is in the core of the registration system; and (c) the automation of testing. Since the optimization algorithm is heuristic in nature, mathematical analysis and test results are used to estimate the reliability and perform failure analysis of the image registration module. Copyright © 2006 Hindawi Publishing Corporation. All rights reserved.
1.
INTRODUCTION
The application of biometric devices and systems is experiencing significant growth, primarily due to the increasing need for reliable authentication and identification [1]. For example, fingerprint identification is used at airports for securing border crossing, but also in our offices as a password replacement. Typical biometric system classifies users as genuine or imposters depending on a selected threshold. For example, if 50 is selected as a threshold for the device whose performance characteristics are depicted in Figure 1, all users with scores higher than 50 will be classified as imposters, while those with scores less than 50 will be classified as genuine. Consequently, the failures of biometric systems include false positives (an imposter classified as a genuine) and false negatives (a genuine user classified as an imposter). Different algorithms [2, 3] in biometric systems have the goal of increasing the rate of success and at the same time decreasing the rate of failure. Depending on the actual application environment, the cost impact of failures might be different. In an office setup, a rejected fingerprint (false negative) causes the user to repeat the authentication procedure. However, if a fingerprint recognition device makes a false match (false positive) in matters of national security or criminal court cases, the potential of grave consequences is obvious. Most biometric applications (e.g., fingerprint, face, hand geometry, iris scans) work with images. An image of a biometric feature is easy to acquire. Unfortunately, studies
of image processing systems in the software reliability engineering arena are rare. One of the
Data Loading...
