Face Image Quality Improves Morphing Attack Detection
Original title: When Morphs Look Better: Face Image Quality as a Training-Free Signal for Morphing Attack Detection
DifFIQA(R) achieves 11.42% mean D-EER on FRLL morphing attacks using fixed quality scores.
The study evaluates 17 FIQA methods as training-free signals for morphing attack detection on 20 attack sets from FRLL and FEI datasets. On FRLL, DifFIQA(R) with CLIB-FIQA and eDifFIQA(L) outperforms others with 11.42% mean D-EER. Performance depends on attack type and some methods assign higher quality to morphs than bona fide samples.
- Evaluated 17 FIQA methods on 20 morphing attack sets
- DifFIQA(R) mean D-EER of 11.42% on FRLL
- Threshold on bona fide data of one dataset fails to transfer
- GraFIQs(L) performs poorly on landmark-based and GAN attacks
From the original article
1 min read at huggingface.co
Face image quality assessment (FIQA) estimates the utility of a face image for automated face recognition and has been proposed as a morphing attack detection (MAD) signal that requires no morph-specific training. We evaluate 17 FIQA methods from all current FIQA categories on 20 morphing attack sets from two datasets, FRLL and FEI, including five diffusion-based attack sets.
By Hao Peng, Fu Bo, Mahmoud Elshirbeny · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.