OCFER-Net: Recognizing Facial Expression in Online Learning System

TL;DR

OCFER-Net introduces an orthogonality-enforcing convolutional approach for facial expression recognition in online learning, improving accuracy by promoting diverse feature extraction, validated on FER-2013 dataset.

Contribution

It proposes a novel orthogonality regularizer for convolutional kernels to enhance feature diversity in FER models, specifically tailored for online learning systems.

Findings

Achieved 1.087% higher accuracy than baselines on FER-2013.

Demonstrated the effectiveness of orthogonality regularization in FER.

Provided publicly available code for reproducibility.

Abstract

Recently, online learning is very popular, especially under the global epidemic of COVID-19. Besides knowledge distribution, emotion interaction is also very important. It can be obtained by employing Facial Expression Recognition (FER). Since the FER accuracy is substantial in assisting teachers to acquire the emotional situation, the project explores a series of FER methods and finds that few works engage in exploiting the orthogonality of convolutional matrix. Therefore, it enforces orthogonality on kernels by a regularizer, which extracts features with more diversity and expressiveness, and delivers OCFER-Net. Experiments are carried out on FER-2013, which is a challenging dataset. Results show superior performance over baselines by 1.087. The code of the research project is publicly available on https://github.com/YeeHoran/OCFERNet.