Generalized Presentation Attack Detection: a face anti-spoofing evaluation proposal
| Autor: | José Luis Alba-Castro, Esteban Vazquez-Fernandez, David Jimenez-Cabello, Artur Costa-Pazo, Roberto J. López-Sastre |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
021110 strategic defence & security studies Computer science business.industry Generalization media_common.quotation_subject Computer Vision and Pattern Recognition (cs.CV) 0211 other engineering and technologies Computer Science - Computer Vision and Pattern Recognition 02 engineering and technology Resolution (logic) Machine learning computer.software_genre Facial recognition system Adversarial system Presentation Anti spoofing Face (geometry) 0202 electrical engineering electronic engineering information engineering Benchmark (computing) 020201 artificial intelligence & image processing Artificial intelligence business computer media_common |
| Zdroj: | ICB |
| Popis: | Over the past few years, Presentation Attack Detection (PAD) has become a fundamental part of facial recognition systems. Although much effort has been devoted to anti-spoofing research, generalization in real scenarios remains a challenge. In this paper we present a new open-source evaluation framework to study the generalization capacity of face PAD methods, coined here as face-GPAD. This framework facilitates the creation of new protocols focused on the generalization problem establishing fair procedures of evaluation and comparison between PAD solutions. We also introduce a large aggregated and categorized dataset to address the problem of incompatibility between publicly available datasets. Finally, we propose a benchmark adding two novel evaluation protocols: one for measuring the effect introduced by the variations in face resolution, and the second for evaluating the influence of adversarial operating conditions. 8 pages, to appear at International Conference on Biometrics (ICB19) |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|