Deep learning-based artificial recognition: a study on facial expression analysis and emotion detection.

Author

Mukombwe, Abel T.

Title

Deep learning-based artificial recognition: a study on facial expression analysis and emotion detection.

Abstract

This dissertation investigates the application of deep learning techniques in facial expression analysis and emotion detection. It aims to assess the effectiveness of various deep learning architectures, including Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Long Short-Term Memory (LSTM) networks, in recognizing facial expressions and detecting emotions. A comprehensive literature review highlights the current advancements and challenges in the field. The proposed deep learning-based approach demonstrates significant improvements in accuracy, with LSTM outperforming both CNN and RNN models across multiple emotional categories. The findings underscore the potential of deep learning in enhancing human-computer interaction and provide insights for future research directions in affective computing.

Date

December 2024

Publisher

BUSE

Keywords

Facial Expression Analysis

Emotion Detection

Deep Learning-based Artificial Recognition

Supervisor

Mr. Musariwa