Deep Convolutional Neural Network for Robust Facial Emotion Recognition

CNN-based facial emotion recognition evaluated on multiple datasets with strong accuracy benchmarks.

Published

June 6, 2019

Doi

10.1109/INISTA.2019.8778282

Keywords

Machine Learning Engineer, Python, PyTorch, LLM, MLOps, Applied ML, Model Evaluation, Probability Calibration, Affective Computing, NLP

Published in: INISTA 2019 : International Symposium on INnovations in Intelligent SysTems and Applications. - Institute of Electrical and Electronics Engineers s. 1-7
DOI: 10.1109/INISTA.2019.8778282
ISBN: 978-1-7281-1861-1
Link: https://ieeexplore.ieee.org/document/8778282

Emotion and the ability to understand them are considered a channel of non-verbal communication. It is an important factor to achieve a smooth and yet robust interaction between machines and humans. In this paper, we review CNN-based methods for facial emotion recognition and we propose a new cutting edge deep learning approach to classify facial expressions from pictures. To guarantee the efficacy of the method, we used multiple datasets: FER2013, AffectNet, RaFD, and KDEF. We obtained results respectively 82.3%, 76.79%, 78.58 %, and 77.08 %. Those results surpassed the current state of the art. We also compared our achieved measurements to available APIs for facial emotion recognition.