NeutrEx: A 3D Quality Component Measure on Facial Expression Neutrality

Marcel Grimmer*, Christian Rathgeb, Raymond Veldhuis, Christoph Busch

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

13 Downloads (Pure)

Abstract

Accurate face recognition systems are increasingly important in sensitive applications like border control or migration management. Therefore, it becomes crucial to quantify the quality of facial images to ensure that lowquality images are not affecting recognition accuracy. In this context, the current draft of ISO/IEC 29794-5 introduces the concept of component quality to estimate how single factors of variation affect recognition outcomes. In this study, we propose a quality measure (NeutrEx) based on the accumulated distances of a 3D face reconstruction to a neutral expression anchor. Our evaluations demonstrate the superiority of our proposed method compared to baseline approaches obtained by training Support Vector Machines on face embeddings extracted from a pre-trained Convolutional Neural Network for facial expression classification. Furthermore, we highlight the explainable nature of our NeutrEx measures by computing per-vertex distances to unveil the most impactful face regions and allow operators to give actionable feedback to subjects1.

Original languageEnglish
Title of host publication2023 IEEE International Joint Conference on Biometrics, IJCB 2023
PublisherIEEE
ISBN (Electronic)9798350337266
DOIs
Publication statusPublished - 1 Mar 2023
EventIEEE International Joint Conference on Biometrics, IJCB 2023 - Ljubljana, Slovenia
Duration: 25 Dec 202328 Dec 2023

Conference

ConferenceIEEE International Joint Conference on Biometrics, IJCB 2023
Abbreviated titleIJCB
Country/TerritorySlovenia
CityLjubljana
Period25/12/2328/12/23

Keywords

  • 2024 OA procedure

Fingerprint

Dive into the research topics of 'NeutrEx: A 3D Quality Component Measure on Facial Expression Neutrality'. Together they form a unique fingerprint.

Cite this