Bologna Online Evaluation Platform (BOEP) - Morph Attack Detection Evaluation
BOEP is a fully automated web-based evaluation system hosted in the FVC-onGoing framework specifically designed to evaluate Morph Attack Detection (MAD) algorithms. It has been designed and developed in the context of the SOTAMD European project and it is supported by EU funded project iMars.
Face MAD - Benchmark Areas
BOEP contains the following benchmark areas for face morph attack detection:
|
Single-image Morph Attack Detection |
|
This benchmark area contains face morphing detection benchmarks. Morphing detection consists in analyzing a face image to determine whether it is the result of a morphing process (mixing faces of two subjects) or not. Algorithms submitted to these benchmarks are required to analyze a suspected morph image and produce a score representing the probability of the image to be morphed. Read more...
|
|
|
Differential Morph Attack Detection |
|
This benchmark area contains face morphing detection benchmarks. Morphing detection consists in analyzing a face image to determine whether it is the result of a morphing process (mixing faces of two subjects) or not. Algorithms submitted to these benchmarks are required to compare a suspected morph image to a bona fide (not morphed) one and produce a score representing the probability of the suspected morph image to be a morphed face image. Read more...
|
Fingerprint MAD
In the iMars EU project, the following experiments on fingerprint morph attack detection have been conducted:
| Fingerprint Single-image Morph Attack Detection |
| The aim of fingerprint single-image morph attack detection is to assess whether a suspected fingerprint is a morph (also called a double-identity fingerprint) or not. Read more... |
| Fingerprint Differential Morph Attack Detection |
| The aim of fingerprint differential morph attack detection is to assess whether a suspected fingerprint is a morph (also called a double-identity fingerprint) by comparing it to a bona fide fingerprint. Read more... |
Iris MAD
In the iMars EU project, the following experiments on iris morph attack detection have been conducted:
| Iris Single-image Morph Attack Detection |
| The aim of iris single-image morph attack detection is to assess whether a suspected iris image is a morph or not. Read more... |
Impact of FIQ on MAD
In the iMars EU project, the following experiments on the impact of face image quality on MAD performance have been conducted:
| Impact of Face Image Quality on Morphing Attack Detection |
| An analysis of the impact of face image quality on MAD performance.. Read more... |
|