Introduction

I am a Computer Science major at Earlham College with a strong interest in Artificial Intelligence and ethical applications of machine learning. My capstone project focuses on developing a Facial Emotion Recognition (FER) system with bias mitigation techniques to ensure fairness across demographic groups.

Abstract

Facial Emotion Recognition (FER) systems are increasingly used in human-computer interaction, yet they often suffer from biases related to ethnicity, gender, and age due to imbalanced datasets and model architectures. My project addresses this challenge by building a deep learning-based FER system while integrating fairness-aware training strategies. The project leverages popular datasets like FER-2013 and RAF-DB, and explores transfer learning, re-weighting, adversarial debiasing, and data augmentation. The end goal is to deploy a real-time FER model that performs equitably across diverse users, contributing to the development of inclusive AI systems.

Technical Report