Skip to content

Read-only version: For security reasons, the Research Information System (FIS) has been temporarily replaced by this read-only version. All public content and full texts remain available; login, editing, submission and statistics are not available. Questions: fis@uni-bamberg.de

Home › Publications › Uncovering the Bias in Facial Expressions

Publication

Uncovering the Bias in Facial Expressions

Deuschel, Jessica; Finzel, Bettina; Rieger, Ines (2021): Uncovering the Bias in Facial Expressions, in: Bamberg: Otto-Friedrich-Universität, S. 1–28, doi: 10.20378/irb-50304.

Details

Faculty/Chair
Faculty/Professorship
Author
Deuschel, Jessica
Publisher Information
Otto-Friedrich-Universität : Bamberg
Year of publication
2021
Source/Other editions
Kolloquium Forschende Frauen 2020 - Gender in Gesellschaft 4.0: Beiträge Bamberger Nachwuchswissenschaftlerinnen / hg. von Judith Rauscher, Mona Hess, Astrid Schütz und Renata Szczepaniak. - Bamberg : University of Bamberg Press, 2021, 144 S. - (Forschende Frauen in Bamberg; 12). - ISBN 978-3-86309-807-0, S. 15-42
Language
English
DOI
Licence
URL
URN
Abstract

Over the past decades the machine and deep learning community has celebrated great achievements in challenging tasks such as image classification. The deep architecture of artificial neural networks together with the plenitude of available data makes it possible to describe highly complex relations. Yet, it is still impossible to fully capture what the deep learning model has learned and to verify that it operates fairly and without creating bias, especially in critical tasks, for instance those arising in the medical field. One example for such a task is the detection of distinct facial expressions, called Action Units, in facial images. Considering this specific task, our research aims to provide transparency regarding bias, specifically in relation to gender and skin color. We train a neural network for Action Unit classification and analyze its performance quantitatively based on its accuracy and qualitatively based on heatmaps. A structured review of our results indicates that we are able to detect bias. Even though we cannot conclude from our results that lower classification performance emerged solely from gender and skin color bias, these biases must be addressed, which is why we end by giving suggestions on how the detected bias can be avoided.

GND Keywords
Gesichtserkennung
Bias
Neuronales Netz
Deep learning
Keywords
Facial Expressions, Bias, Neural Networks, Deep Learning, Facial Action Units
DDC Classification
004 Computer science
RVK Classification
ST 301
Type
Contribution to an Articlecollection
URI
Activation date
2021-10-04

Permalink: https://fis.uni-bamberg.de/handle/uniba/50304 · Data as JSON · Cite: BibTeX · RIS

Data as of: 2026-11-16

Restricted read-only access: login, editing and submission are temporarily disabled.