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.
Benchmarks
Currently, a benchmark is being used to evaluate the performance of iris single-image morph attack detection approaches:
- The dataset comprises 720 bona fide iris images and two sets (Random and Radius) of 1200 morphed iris images each, generated using two different morphing techniques. For more details, please contact the authors of [1].
Performance Evaluation
For each algorithm, bona fide (evaluating bona fide iris images) and morph (evaluating morphed iris images) attempts are performed to compute Bona fide Sample Classification Error Rate (BSCER) and Morphing Attack Classification Error Rate (MACER). As defined in [2] the BSCER is the percentage of bona fide samples incorrectly classified as morphed samples while the MACER is the proportion of morphing attack samples incorrectly classified as bona fide samples.
The following performance indicators are computed:
- BSCER10 (the lowest BSCER for MACER≤10%)
- BSCER100 (the lowest BSCER for MACER≤1%)
To calculate the above indicators, both bona fide and morphed iris images are provided as input to the algorithm being evaluated.
Results
The following table present the results obtained by the method proposed in [1].
Method |
BSCER10 |
BSCER100 |
Random |
1.85% |
29.85% |
Radius |
0.05% |
5.13% |
Bibliography
[1] J. E. Tapia, S. Gonzalez, D. Benalcazar, and C. Busch, “On the Feasibility of Creating Iris Periocular Morphed Images”, arXiv, 2024.
[2] ISO/IEC DIS 20059, "Methodologies to evaluate the resistance of biometric systems to morphing attacks", 2024.
|