Abstract
Recent research on vascular biometrics shows that the bone structure is also contributing in the identification process. However, it is not yet documented whether bone structure can be used for identification by itself. In the NIR images of the fingerveins, the veins are dark shadow-like textures. The joints in these images are bright, where the bone itself appears darker. This research proposes a method to analyse intensity differences using two sliding windows. Brighter pixels around the joints, and darker pixels around the bones give that the difference of the sum of the pixels inside the windows give a robust representation of the rough shape of the bones. By dividing the two windows into three parts, creating six in total, the shape of the joint is taken into account more accurately. A small verification experiment resulted in an EER of 0.115 when all 6 windows have a width of 2 pixels and a gap of 10 pixels.
Original language | English |
---|---|
Title of host publication | Proceedings of the 2021 Symposium on Information Theory and Signal Processing in the Benelux |
Editors | Ruud van Sloun, Boris Skoric |
Place of Publication | Eindhoven, Netherlands |
Publisher | Werkgemeenschap voor Informatie- en Communicatietheorie (WIC) |
Pages | 56-63 |
ISBN (Electronic) | 978-90-386-5318-1 |
Publication status | Published - 2021 |
Event | 41st Symposium on Information Theory and Signal Processing in the Benelux 2021 - Online Symposium Duration: 20 May 2021 → 21 May 2021 Conference number: 41 |
Conference
Conference | 41st Symposium on Information Theory and Signal Processing in the Benelux 2021 |
---|---|
City | Online Symposium |
Period | 20/05/21 → 21/05/21 |