Abstract
Fingerprints are the most widely used characteristics in systems that recognize a person’s identity, for their proven uniqueness and stability over time. Although automatic fingerprint recognition was one of the first pattern recognition application, it is not a solved problem. In this talk, the main automatic fingerprint recognition approaches will be reviewed, concentrating on feature extraction and matching techniques (minutiae-based, correlation-based texture-based), and discussing some of the most important challenges in this field. Furthermore, the fingerprint evaluation campaigns organized in the recent years will be described, focusing on the three editions of the Fingerprint Verification Competition (FVC). Independent and reliable evaluation of the advances in fingerprint recognition is extremely important for several reasons: 1) to give governments, organizations and to every potential user a clear panorama of the potentiality and current limits of this technology; 2) to compare and rank different solutions (academic and commercial); 3) to provide unambiguous benchmarks/protocols to researchers to track their advances. Finally, a method for generating synthetic fingerprints with the aim of creating large test databases at zero cost will be introduced. The synthetic images are randomly generated according to few given parameters; the method captures the variability which characterizes the acquisition of fingerprints through on-line sensors and uses a sequence of steps to derive a series of “impressions” of the same “artificial finger”
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Cappelli, R. (2004). Fingerprints: Recognition, Performance Evaluation and Synthetic Generation. In: Li, S.Z., Lai, J., Tan, T., Feng, G., Wang, Y. (eds) Advances in Biometric Person Authentication. SINOBIOMETRICS 2004. Lecture Notes in Computer Science, vol 3338. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30548-4_3
Download citation
DOI: https://doi.org/10.1007/978-3-540-30548-4_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-24029-7
Online ISBN: 978-3-540-30548-4
eBook Packages: Computer ScienceComputer Science (R0)