Non-reference Image Quality Assessment for Fingervein Presentation Attack Detection
| Autor: | Dominik Sollinger, Jutta Hammerle-Uhl, Amrit Pal Singh Bhogal, Pauline Trung, Andreas Uhl |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
021110 strategic
defence & security studies Measure (data warehouse) Spoofing attack Local binary patterns Computer science business.industry Image quality media_common.quotation_subject 0211 other engineering and technologies 02 engineering and technology Machine learning computer.software_genre Set (abstract data type) Attack model ComputingMethodologies_PATTERNRECOGNITION 0202 electrical engineering electronic engineering information engineering Discrete cosine transform 020201 artificial intelligence & image processing Quality (business) Artificial intelligence business computer media_common |
| Zdroj: | Image Analysis ISBN: 9783319591254 SCIA (1) |
| DOI: | 10.1007/978-3-319-59126-1_16 |
| Popis: | Non-reference image quality measures are used to distinguish real biometric data from data as used in presentation/sensor spoofing attacks. An experimental study shows that based on a set of 6 such measures, classification of real vs. fake fingervein data is feasible with an accuracy of 99% on one of our datasets. However, we have found that the best quality measure (combination) and classification setting highly depends on the target dataset. Thus, we are unable to provide any other recommendation than to optimise the choice of quality measure and classification setting for each specific application setting. Results also imply, that generalisation to unseen attack types might be difficult due to dataset dependence of the results. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|