Fang, Meiling ; Damer, Naser ; Boutros, Fadi ; Kirchbuchner, Florian ; Kuijper, Arjan (2024)
The overlapping effect and fusion protocols of data augmentation techniques in iris PAD.
In: Machine Vision and Applications, 2022, 33 (1)
doi: 10.26083/tuprints-00023431
Artikel, Zweitveröffentlichung, Verlagsversion
 | Es ist eine neuere Version dieses Eintrags verfügbar. |
Kurzbeschreibung (Abstract)
Iris Presentation Attack Detection (PAD) algorithms address the vulnerability of iris recognition systems to presentation attacks. With the great success of deep learning methods in various computer vision fields, neural network-based iris PAD algorithms emerged. However, most PAD networks suffer from overfitting due to insufficient iris data variability. Therefore, we explore the impact of various data augmentation techniques on performance and the generalizability of iris PAD. We apply several data augmentation methods to generate variability, such as shift, rotation, and brightness. We provide in-depth analyses of the overlapping effect of these methods on performance. In addition to these widely used augmentation techniques, we also propose an augmentation selection protocol based on the assumption that various augmentation techniques contribute differently to the PAD performance. Moreover, two fusion methods are performed for more comparisons: the strategy-level and the score-level combination. We demonstrate experiments on two fine-tuned models and one trained from the scratch network and perform on the datasets in the Iris-LivDet-2017 competition designed for generalizability evaluation. Our experimental results show that augmentation methods improve iris PAD performance in many cases. Our least overlap-based augmentation selection protocol achieves the lower error rates for two networks. Besides, the shift augmentation strategy also exceeds state-of-the-art (SoTA) algorithms on the Clarkson and IIITD-WVU datasets.
| Typ des Eintrags: | Artikel |
|---|---|
| Erschienen: | 2024 |
| Autor(en): | Fang, Meiling ; Damer, Naser ; Boutros, Fadi ; Kirchbuchner, Florian ; Kuijper, Arjan |
| Art des Eintrags: | Zweitveröffentlichung |
| Titel: | The overlapping effect and fusion protocols of data augmentation techniques in iris PAD |
| Sprache: | Englisch |
| Publikationsjahr: | 12 März 2024 |
| Ort: | Darmstadt |
| Publikationsdatum der Erstveröffentlichung: | Januar 2022 |
| Ort der Erstveröffentlichung: | Berlin; Heidelberg |
| Verlag: | Springer |
| Titel der Zeitschrift, Zeitung oder Schriftenreihe: | Machine Vision and Applications |
| Jahrgang/Volume einer Zeitschrift: | 33 |
| (Heft-)Nummer: | 1 |
| Kollation: | 21 Seiten |
| DOI: | 10.26083/tuprints-00023431 |
| URL / URN: | https://tuprints.ulb.tu-darmstadt.de/23431 |
| Zugehörige Links: | |
| Herkunft: | Zweitveröffentlichung DeepGreen |
| Kurzbeschreibung (Abstract): | Iris Presentation Attack Detection (PAD) algorithms address the vulnerability of iris recognition systems to presentation attacks. With the great success of deep learning methods in various computer vision fields, neural network-based iris PAD algorithms emerged. However, most PAD networks suffer from overfitting due to insufficient iris data variability. Therefore, we explore the impact of various data augmentation techniques on performance and the generalizability of iris PAD. We apply several data augmentation methods to generate variability, such as shift, rotation, and brightness. We provide in-depth analyses of the overlapping effect of these methods on performance. In addition to these widely used augmentation techniques, we also propose an augmentation selection protocol based on the assumption that various augmentation techniques contribute differently to the PAD performance. Moreover, two fusion methods are performed for more comparisons: the strategy-level and the score-level combination. We demonstrate experiments on two fine-tuned models and one trained from the scratch network and perform on the datasets in the Iris-LivDet-2017 competition designed for generalizability evaluation. Our experimental results show that augmentation methods improve iris PAD performance in many cases. Our least overlap-based augmentation selection protocol achieves the lower error rates for two networks. Besides, the shift augmentation strategy also exceeds state-of-the-art (SoTA) algorithms on the Clarkson and IIITD-WVU datasets. |
| Freie Schlagworte: | Iris presentation attack detection, Data augmentation, Deep learning |
| ID-Nummer: | Artikel-ID: 8 |
| Status: | Verlagsversion |
| URN: | urn:nbn:de:tuda-tuprints-234310 |
| Zusätzliche Informationen: | Special Issue on 25th ICPR - Computer Vision, Robotics and Intelligent Systems |
| Sachgruppe der Dewey Dezimalklassifikatin (DDC): | 000 Allgemeines, Informatik, Informationswissenschaft > 004 Informatik 500 Naturwissenschaften und Mathematik > 510 Mathematik |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Fraunhofer IGD 20 Fachbereich Informatik > Mathematisches und angewandtes Visual Computing |
| Hinterlegungsdatum: | 12 Mär 2024 13:26 |
| Letzte Änderung: | 14 Mär 2024 14:02 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
Verfügbare Versionen dieses Eintrags
- The overlapping effect and fusion protocols of data augmentation techniques in iris PAD. (deposited 12 Mär 2024 13:26) [Gegenwärtig angezeigt]
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum