Deep Learning for Facial Expression and Human Activity Recognition Using Smart Glasses
IEEE Access · 2025 · 13 · 48257-48270
DOI: 10.1109/access.2025.3551610 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2025. Verfasst von Matea Marinova und 8 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Swiss National Science Foundation (SNSF) through Project Towards Explainable and Private Affective Computing.
Abstract (Originalsprache)
Facial Expression Recognition (FER) and Human Activity Recognition (HAR) are key areas in wearable computing, with applications in healthcare, fitness, and human-computer interaction. This study explores the use of Emteq’s OCOsense smart glasses for FER and HAR, which incorporate optomyographic sensors and a 9-axis inertial measurement unit (IMU). Using deep learning (DL) models, including CNNs, ConvLSTM, and STResNet variants, the study compares the performance of FER for six expression classes and HAR for seven different activities. We investigate the impact of the ConvBoost framework on model performance, extending its use beyond HAR with IMU data and introducing end-to-end learning for FER using OCOsense smart glasses. Our findings confirm that ConvBoost effectively improves performance of complex overfitting-prone models. Furthermore, the results also reveal that using ConvBoost in simpler models, such as the 1-dimensional convolutional neural network (CNN 1D), leads to a decrease in F1-score. The best performing models, Attention ConvLSTM for FER and ConvLSTM for HAR (in combination with ConvBoost), achieved a macro F1-score of 0.78 and 0.88, respectively. These results highlight the potential of smart glasses for FER and HAR, establishing benchmark results for future advancements in glasses-based wearable computing.
Förderung
- Swiss National Science Foundation (SNSF) through Project Towards Explainable and Private Affective Computing
Zitieren
APA
Marinova, M., Chona, E., Kotevski, A., Sazdov, B., Kiprijanovska, I., Stankoski, S., Gjoreski, M., Nduka, C., & Gjoreski, H. (2025). Deep Learning for Facial Expression and Human Activity Recognition Using Smart Glasses. IEEE Access, 13, 48257-48270. https://doi.org/10.1109/access.2025.3551610
Vancouver
Marinova M, Chona E, Kotevski A, Sazdov B, Kiprijanovska I, Stankoski S, et al. Deep Learning for Facial Expression and Human Activity Recognition Using Smart Glasses. IEEE Access. 2025;13:48257-48270. doi:10.1109/access.2025.3551610
BibTeX
@article{Marinova2025,
author = {Marinova, Matea and Chona, Emilija and Kotevski, Andrej and Sazdov, Borjan and Kiprijanovska, Ivana and Stankoski, Simon and Gjoreski, Martin and Nduka, Charles and Gjoreski, Hristijan},
title = {Deep Learning for Facial Expression and Human Activity Recognition Using Smart Glasses},
journal = {IEEE Access},
year = {2025},
volume = {13},
pages = {48257--48270},
doi = {10.1109/access.2025.3551610}
}
EUVIMED