Innovative Study on Popular Approaches used in Gaze Prediction

Sohail, Sammam (2024) Innovative Study on Popular Approaches used in Gaze Prediction. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (2MB) | Preview

Abstract

The rapid advancement in technology today has given significant importance to gaze prediction. Ranging from virtual reality to monitoring humans in a specific environment, gaze prediction plays a vital contributor in these fields. This paper focuses on implementing a system that can monitor human gaze direction using the traditional techniques of computer vision and the more advanced convolutional neural networks. The traditional technique implemented in this paper relies on the famous HOG classifier for extracting human eyes from face images and a modular approach for facial feature extraction using convolutional neural networks for gaze prediction. We use the Columbia Gaze dataset, which is a popular dataset in the field of gaze prediction, for training and evaluating the systems developed for this paper. The aim of this study is to develop and exploit the limitations of each technique that predicts the human gaze. The paper, at the end, discusses various analysis techniques, comprising visualisations and evaluation metrics such as precision, recall, f1-score and accuracy. To contribute further, a recommendation is made by evaluating the metrics between the employed techniques for their use in different gaze prediction environments.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Sahni, Anu UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence > Computer vision Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence > Computer vision
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	05 Sep 2025 10:55
Last Modified:	05 Sep 2025 10:55
URI:	https://norma.ncirl.ie/id/eprint/8817

Actions (login required)

View Item