Logo des Repositoriums
 
Konferenzbeitrag

Low-resolution Iris Recognition via Knowledge Transfer

Lade...
Vorschaubild

Volltext URI

Dokumententyp

Text/Conference Paper

Zusatzinformation

Datum

2022

Zeitschriftentitel

ISSN der Zeitschrift

Bandtitel

Verlag

Gesellschaft für Informatik e.V.

Zusammenfassung

This work introduces a novel approach for extremely low-resolution iris recognition based on deep knowledge transfer. This work starts by adapting the penalty margin loss to the iris recognition problem. This included novel analyses on the appropriate penalty margin for iris recognition. Additionally, this work presents analyses toward finding the optimal deeply learned representation dimension for the identity information embedded in the iris capture. Most importantly, this work proposes a training framework that aims at producing iris deep representations from extremely lowresolution that are similar to those of high resolution. This was realized by the controllable knowledge transfer of an iris recognition model trained for high-resolution images into a model that is specifically trained for extremely low-resolution irises. The presented approach leads to the reduction of the verification errors by more than 3 folds, in comparison to the traditionally trained model for low-resolution iris recognition.

Beschreibung

Fadi Boutros, Olga Kaehm (2022): Low-resolution Iris Recognition via Knowledge Transfer. BIOSIG 2022. DOI: 10.1109/BIOSIG55365.2022.9896959. Bonn: Gesellschaft für Informatik e.V.. PISSN: 1617-5498. ISBN: 978-3-88579-723-4. pp. 293-300. Further Conference Contributions. Darmstadt. 14.-16. September 2022

Zitierform

Tags