Evaluating OpenDBM for Emotion Intensity Prediction: A Comparative Study Using Facial and Physiological Data
Sadeghi M, Rahimi F, Kumar A, Richer R, Rupp LH, Schindler-Gmelch L, Keinert M, Hager M, Capito K, Berking M, Eskofier B (2025)
Publication Language: English
Publication Type: Conference contribution, Abstract of a poster
Publication year: 2025
Conference Proceedings Title: EAI PervasiveHealth
Event location: Eindhoven
Abstract
Accurate emotion recognition is crucial for applications in mental health and affective computing. While commercial tools such as FaceReader are common for video analysis, their proprietary nature limits accessibility and integration. This study evaluates the open-source toolkit OpenDBM for predicting continuous emotion intensities, comparing a video-only approach to a multimodal model that fuses visual features with electrocardiogram (ECG) and respiration (RSP) signals. Using FaceReader-annotated video and biosignal data from 113 participants, we trained Random Forest (RF) and Gated Recurrent Unit (GRU) models. The video-only RF model achieved the best performance (MAE = 0.040), outperforming the multimodal model (MAE = 0.070). These results demonstrate the value of OpenDBM as an accessible alternative to commercial tools and suggest that visually derived labels may not fully capture emotion-related patterns present in physiological signals.
Authors with CRIS profile
Misha Sadeghi
Sonderforschungsbereich 1483/1 - Empathokinästhetische Sensorik - Sensortechniken und Datenanalyseverfahren zur empathokinästhetischen Modellbildung und Zustandsbestimmung (SFB EmpkinS)
Farnaz Rahimi
Department Artificial Intelligence in Biomedical Engineering (AIBE)
Lydia Rupp
Lena Marie Gmelch Lehrstuhl für Klinische Psychologie und Psychotherapie (KliPs) Eva Marie Keinert Sonderforschungsbereich 1483/1 - Empathokinästhetische Sensorik - Sensortechniken und Datenanalyseverfahren zur empathokinästhetischen Modellbildung und Zustandsbestimmung (SFB EmpkinS) Malin Hager Graduiertenzentrum der FAU Klara Capito Lehrstuhl für Klinische Psychologie und Psychotherapie (KliPs) Matthias Berking Lehrstuhl für Klinische Psychologie und Psychotherapie (KliPs) Björn Eskofier Department Artificial Intelligence in Biomedical Engineering (AIBE)
Lena Marie Gmelch Lehrstuhl für Klinische Psychologie und Psychotherapie (KliPs) Eva Marie Keinert Sonderforschungsbereich 1483/1 - Empathokinästhetische Sensorik - Sensortechniken und Datenanalyseverfahren zur empathokinästhetischen Modellbildung und Zustandsbestimmung (SFB EmpkinS) Malin Hager Graduiertenzentrum der FAU Klara Capito Lehrstuhl für Klinische Psychologie und Psychotherapie (KliPs) Matthias Berking Lehrstuhl für Klinische Psychologie und Psychotherapie (KliPs) Björn Eskofier Department Artificial Intelligence in Biomedical Engineering (AIBE)
Related research project(s)
Involved external institutions
Germany (DE)How to cite
APA:
Sadeghi, M., Rahimi, F., Kumar, A., Richer, R., Rupp, L.H., Schindler-Gmelch, L.,... Eskofier, B. (2025). Evaluating OpenDBM for Emotion Intensity Prediction: A Comparative Study Using Facial and Physiological Data. Poster presentation at 19th EAI International Conference on Pervasive Computing Technologies for Healthcare, Eindhoven, NL.
MLA:
Sadeghi, Misha, et al. "Evaluating OpenDBM for Emotion Intensity Prediction: A Comparative Study Using Facial and Physiological Data." Presented at 19th EAI International Conference on Pervasive Computing Technologies for Healthcare, Eindhoven 2025.
BibTeX: Download