TECHNOLOGY AND CODE article
Front. Neurorobot.
This article is part of the Research TopicMultimodal human action recognition in real or virtual environmentsView all 3 articles
Emotion estimation from video footage with LSTM
Provisionally accepted
- HAN University of Applied Sciences, Nijmegen, Netherlands
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Emotion estimation is a field that has been studied for a long time, and several approaches using machine learning models exist. This article, presents BlendFER-Lite an LSTM model that utilizes Blendshapes produced by the MediaPipe library to analyse facial expressions detected from a live-streamed camera feed. This model is trained on the FER2013 dataset and achieves a performance of 71% accuracy and an F1-score of 62%, which meets the accuracy benchmark of the FER2013 dataset, while significantly reducing computational cost compared to current methods. For the sake of reproducibility, the code repository, datasets, and models proposed in this paper, in addition to the pre-print, can be found on Hugging Face at: https://huggingface.co/papers/ 2501.13432
Keywords: emotion estimation, Computer Vision, social robotics, BlendFER-Lite, neural networks, Blendshapes
Received: 03 Aug 2025; Accepted: 14 Nov 2025.
Copyright: © 2025 Attrah. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Samer Attrah, samiratra95@gmail.com
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.