On Recognizing Occluded Faces in the Wild

Erakin M. E., Demir U., Ekenel H. K.

20th Annual International Conference of the Biometrics-Special-Interest-Group (BIOSIG ), ELECTR NETWORK, 15 - 17 September 2021, vol.315 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume: 315
  • Doi Number: 10.1109/biosig52210.2021.9548293
  • Country: ELECTR NETWORK
  • Keywords: Face recognition, face occlusion, deep learning, real-world occluded faces
  • Istanbul Technical University Affiliated: Yes

Abstract

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 realworld, 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.