TY - GEN
T1 - On Recognizing Occluded Faces in the Wild
AU - Erakin, Mustafa Ekrem
AU - Demir, Ugur
AU - Ekenel, Hazim Kemal
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/9
Y1 - 2021/9
N2 - Facial appearance variations due to occlusion has been one of the main challenges for face recognition systems. To facilitate further research in this area, it is necessary and important to have occluded face datasets collected from real-world, as synthetically generated occluded faces cannot represent the nature of the problem. In this paper, we present the Real World Occluded Faces (ROF) dataset, that contains faces with both upper face occlusion, due to sunglasses, and lower face occlusion, due to masks. We propose two evaluation protocols for this dataset. Benchmark experiments on the dataset have shown that no matter how powerful the deep face representation models are, their performance degrades significantly when they are tested on real-world occluded faces. It is observed that the performance drop is far less when the models are tested on synthetically generated occluded faces. The ROF dataset and the associated evaluation protocols are publicly available at the following link https://github.com/ekremerakin/RealWorldOccludedFaces.
AB - Facial appearance variations due to occlusion has been one of the main challenges for face recognition systems. To facilitate further research in this area, it is necessary and important to have occluded face datasets collected from real-world, as synthetically generated occluded faces cannot represent the nature of the problem. In this paper, we present the Real World Occluded Faces (ROF) dataset, that contains faces with both upper face occlusion, due to sunglasses, and lower face occlusion, due to masks. We propose two evaluation protocols for this dataset. Benchmark experiments on the dataset have shown that no matter how powerful the deep face representation models are, their performance degrades significantly when they are tested on real-world occluded faces. It is observed that the performance drop is far less when the models are tested on synthetically generated occluded faces. The ROF dataset and the associated evaluation protocols are publicly available at the following link https://github.com/ekremerakin/RealWorldOccludedFaces.
KW - deep learning
KW - face occlusion
KW - Face recognition
KW - real-world occluded faces
UR - http://www.scopus.com/inward/record.url?scp=85116686968&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85116686968&partnerID=8YFLogxK
U2 - 10.1109/BIOSIG52210.2021.9548293
DO - 10.1109/BIOSIG52210.2021.9548293
M3 - Conference contribution
AN - SCOPUS:85116686968
T3 - BIOSIG 2021 - Proceedings of the 20th International Conference of the Biometrics Special Interest Group
BT - BIOSIG 2021 - Proceedings of the 20th International Conference of the Biometrics Special Interest Group
A2 - Bromme, Arslan
A2 - Busch, Christoph
A2 - Damer, Naser
A2 - Dantcheva, Antitza
A2 - Gomez-Barrero, Marta
A2 - Raja, Kiran
A2 - Rathgeb, Christian
A2 - Sequeira, Ana F.
A2 - Uhl, Andreas
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 20th International Conference of the Biometrics Special Interest Group, BIOSIG 2021
Y2 - 15 September 2021 through 17 September 2021
ER -