Article

Performance evaluation of fingerprint verification systems.

Biometric System Laboratory-DEIS, University of Bologna, via Sacchi 3, 47023 Cesena, Italy.
IEEE Transactions on Pattern Analysis and Machine Intelligence (Impact Factor: 5.69). 02/2006; 28(1):3-18. DOI: 10.1109/TPAMI.2006.20
Source: PubMed

ABSTRACT This paper is concerned with the performance evaluation of fingerprint verification systems. After an initial classification of biometric testing initiatives, we explore both the theoretical and practical issues related to performance evaluation by presenting the outcome of the recent Fingerprint Verification Competition (FVC2004). FVC2004 was organized by the authors of this work for the purpose of assessing the state-of-the-art in this challenging pattern recognition application and making available a new common benchmark for an unambiguous comparison of fingerprint-based biometric systems. FVC2004 is an independent, strongly supervised evaluation performed at the evaluators' site on evaluators' hardware. This allowed the test to be completely controlled and the computation times of different algorithms to be fairly compared. The experience and feedback received from previous, similar competitions (FVC2000 and FVC2002) allowed us to improve the organization and methodology of FVC2004 and to capture the attention of a significantly higher number of academic and commercial organizations (67 algorithms were submitted for FVC2004). A new, "Light" competition category was included to estimate the loss of matching performance caused by imposing computational constraints. This paper discusses data collection and testing protocols, and includes a detailed analysis of the results. We introduce a simple but effective method for comparing algorithms at the score level, allowing us to isolate difficult cases (images) and to study error correlations and algorithm "fusion." The huge amount of information obtained, including a structured classification of the submitted algorithms on the basis of their features, makes it possible to better understand how current fingerprint recognition systems work and to delineate useful research directions for the future.

4 Followers
 · 
376 Views
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper argues that biometric verification evaluations can obscure vulnerabilities that increase the chances that an attacker could be falsely accepted. This can occur because existing evaluations implicitly assume that an imposter claiming a false identity would claim a random identity rather than consciously selecting a target to impersonate. This paper shows how an attacker can select a target with a similar biometric signature in order to increase their chances of false acceptance. It demonstrates this effect using a publicly available iris recognition algorithm. The evaluation shows that the system can be vulnerable to attackers targeting subjects who are enrolled with a smaller section of iris due to occlusion. The evaluation shows how the traditional DET curve analysis conceals this vulnerability. As a result, traditional analysis underestimates the importance of an existing score normalisation method for addressing occlusion. The paper concludes by evaluating how the targeted false acceptance rate increases with the number of available targets. Consistent with a previous investigation of targeted face verification performance, the experiment shows that the false acceptance rate can be modelled using the traditional FAR measure with an additional term that is proportional to the logarithm of the number of available targets.
    2013 IEEE 6th International Conference on Biometrics: Theory, Applications and Systems (BTAS); 09/2013
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, the use of relevance feedback with fingerprint identification systems is investigated. Two key limitations in current systems are addressed. Firstly, performance in current systems is highly dependent upon the fingerprint features selected for identification and the accuracy of the underlying pattern matching algorithm. Secondly, there is no effective mechanism to improve future queries through knowledge captured from the users, who are often experienced fingerprint examiners. Relevance feedback, a human computer interaction technique to capture and re-use knowledge of a user, has been studied extensively in text-based document retrieval systems and content-based image retrieval systems, but to date examples of its application to fingerprint identification systems are rare. By exploiting relevance feedback, this paper presents a user-centric and adaptive framework that allows tacit knowledge of fingerprint examiners to be captured and re-used to enhance their future decisions. The outcome is a knowledge-based Decision Support System (DSS) that provides the examiner with both intuitive visualization displays to analyze the relationships between images in the fingerprint database and relevance feedback facility to produce a persistent and personalized semantic space overlay. This serves a long term memory that can be updated to reflect the knowledge captured from the user. Empirical experiments confirmed the ability of this approach to improve the accuracy of fingerprint identification queries when compared to the static data processing architecture of current systems.
    Knowledge-Based Systems 10/2014; 73. DOI:10.1016/j.knosys.2014.10.005 · 3.06 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we propose a novel robust and efficient minutia-based fingerprint matching algorithm. There are two key contributions. First, we apply a set of global level minutia dependent features, i.e., the qualities that measure the reliabilities of the extracted minutiae and the area of overlapping regions between the query and template images of fingerprints. The implementation of these easy-to-get minutia dependent features presents coherence to the well-accepted fingerprint template standards. Besides, the reasonable combination of them results in the robustness to poor quality fingerprint images. Second, we implement a hierarchical recognition strategy, which applies a procedure of global matching that refines the local matching decision towards a genuine result over the entire images. Other than the much improved accuracy, our algorithm also promotes the efficiency, because compared with other state-of-the-art matching approaches, it does not make use of any time-consuming operations or any complex feature structures. The experimental results demonstrate the proposed method exhibits an excellent accuracy that exceeds the performances of well-known minutia based matchers. Meanwhile, the proposed algorithm presents potentials to serve a real-time fingerprint recognition system.
    2013 2nd IAPR Asian Conference on Pattern Recognition (ACPR); 11/2013

Preview

Download
19 Downloads
Available from