Supervisor

Muhammad Iqbal

Programme

BSc (Hons) in Computing in IT

Subject

Computer Science

Department

Computer Science

Abstract

This Capstone Project focused on developing an accurate Facial Expression Recognition (FER) model by leveraging deep learning techniques, specifically Convolutional Neural Networks (CNNs). The objective was to explore, design, and implement custom architectures and evaluate their performance against existing work. The process involved several stages, such as data preprocessing, data augmentation, architecture design, hyperparameter tuning, and performance assessment using metrics like accuracy and F1-score while utilizing the FER-2013 dataset for training. The resulting FER model exhibited competitive accuracy levels and generalization capabilities, opening up opportunities for real-time implementation and application across various domains.

Date of Award

Spring 5-2024

Full Publication Date

5-2024

Access Rights

open access

Document Type

Undergraduate Project

Resource Type

bachelor thesis

Share

COinS