Figure - available from: Evolutionary Intelligence
This content is subject to copyright. Terms and conditions apply.
A qualitative comparison with other algorithms in fingerprint enhancement. From left to right: degraded fingerprints, corresponding ground-truth, results of our method, MU-GAN, Cycle-GAN and DU-GAN

A qualitative comparison with other algorithms in fingerprint enhancement. From left to right: degraded fingerprints, corresponding ground-truth, results of our method, MU-GAN, Cycle-GAN and DU-GAN

Source publication
Article
Full-text available
Fingerprint is a suitable biometric for identity verification. However, the fingerprint details are significantly affected by the impression conditions and the non-uniform contact with fingerprint capture device, making the fingerprint recognition a challenging task. The objective of this work is to present an approach to improve the quality of fin...

Similar publications

Article
Full-text available
Double-identity biometrics, that is the combination of two subjects features into a single template, was demonstrated to be a serious threat against existing biometric systems. In fact, well-synthetized samples can fool state-of-the-art biometric verification systems, leading them to falsely accept both the contributing subjects. This work proposes...