TU Darmstadt / ULB / TUbiblio

The relative contributions of facial parts qualities to the face image utility

Fu, Biying ; Chen, Cong ; Henniger, Olaf ; Damer, Naser (2021):
The relative contributions of facial parts qualities to the face image utility.
In: BIOSIG 2021: Proceedings of the 20th International Conference of the Biometrics Special Interest Group,
IEEE, 20th International Conference of the Biometrics Special Interest Group, virtual Conference, 15.-17.09.2021, ISBN 978-1-6654-2693-0,
DOI: 10.1109/BIOSIG52210.2021.9548297,
[Conference or Workshop Item]

Abstract

Face image quality assessment predicts the utility of a face image for automated face recognition. A high-quality face image can achieve good performance for the identification or verification task. Some recent face image quality assessment algorithms are established on deep-learning-based approaches, which rely on face embeddings of aligned face images. Such face embeddings fuse complex information into a single feature vector and are, therefore, challenging to disentangle. The semantic context however can provide better interpretable insights into neural-network decisions. We investigate the effects of face subregions (semantic contexts) and link the general image quality of face subregions with face image utility. The evaluation is performed on two difficult large-scale datasets (LFW and VGGFace2) with three face recognition solutions (FaceNet, SphereFace, and ArcFace). In total, we applied four face image quality assessment methods and one general image quality assessment method on four face subregions (eyes, mouth, nose, and tightly cropped face region) and the aligned faces. In addition, the effect of fusion of different face subregions was investigated to increase the robustness of the outcomes.

Item Type: Conference or Workshop Item
Erschienen: 2021
Creators: Fu, Biying ; Chen, Cong ; Henniger, Olaf ; Damer, Naser
Title: The relative contributions of facial parts qualities to the face image utility
Language: English
Abstract:

Face image quality assessment predicts the utility of a face image for automated face recognition. A high-quality face image can achieve good performance for the identification or verification task. Some recent face image quality assessment algorithms are established on deep-learning-based approaches, which rely on face embeddings of aligned face images. Such face embeddings fuse complex information into a single feature vector and are, therefore, challenging to disentangle. The semantic context however can provide better interpretable insights into neural-network decisions. We investigate the effects of face subregions (semantic contexts) and link the general image quality of face subregions with face image utility. The evaluation is performed on two difficult large-scale datasets (LFW and VGGFace2) with three face recognition solutions (FaceNet, SphereFace, and ArcFace). In total, we applied four face image quality assessment methods and one general image quality assessment method on four face subregions (eyes, mouth, nose, and tightly cropped face region) and the aligned faces. In addition, the effect of fusion of different face subregions was investigated to increase the robustness of the outcomes.

Title of Book: BIOSIG 2021: Proceedings of the 20th International Conference of the Biometrics Special Interest Group
Publisher: IEEE
ISBN: 978-1-6654-2693-0
Uncontrolled Keywords: Biometrics, Face recognition, Deep learning, Quality estimation
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Interactive Graphics Systems
Event Title: 20th International Conference of the Biometrics Special Interest Group
Event Location: virtual Conference
Event Dates: 15.-17.09.2021
Date Deposited: 29 Sep 2021 13:16
DOI: 10.1109/BIOSIG52210.2021.9548297
Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)
Show editorial Details Show editorial Details