Facial Emotion Recognition: State of the Art Performance on FER2013

TL;DR

This paper presents a deep learning approach using VGGNet architecture to achieve the highest single-network accuracy on the FER2013 facial emotion recognition dataset, demonstrating significant progress in the field.

Contribution

The study fine-tunes VGGNet hyperparameters and optimization methods to attain state-of-the-art accuracy on FER2013 without additional training data.

Findings

Achieved 73.28% accuracy on FER2013

Optimized VGGNet hyperparameters for FER

Demonstrated effectiveness of CNNs in FER

Abstract

Facial emotion recognition (FER) is significant for human-computer interaction such as clinical practice and behavioral description. Accurate and robust FER by computer models remains challenging due to the heterogeneity of human faces and variations in images such as different facial pose and lighting. Among all techniques for FER, deep learning models, especially Convolutional Neural Networks (CNNs) have shown great potential due to their powerful automatic feature extraction and computational efficiency. In this work, we achieve the highest single-network classification accuracy on the FER2013 dataset. We adopt the VGGNet architecture, rigorously fine-tune its hyperparameters, and experiment with various optimization methods. To our best knowledge, our model achieves state-of-the-art single-network accuracy of 73.28 % on FER2013 without using extra training data.