Publication Date
Fall 2023
Degree Type
Master's Project
Degree Name
Master of Science in Computer Science (MSCS)
Department
Computer Science
First Advisor
Nada Attar
Second Advisor
Robert Chun
Third Advisor
Reem Albaghli
Keywords
Visual Search, Eye Tracking, Machine Learning, Ensemble learning, Decision Tree, K Nearest Neighbors, Logistic Regression, AdaBoost, XGBoost
Abstract
Visual scenes represent the comprehensive visual information observed in a particular environment. Whether natural landscapes, urban settings, or designed interiors, visual scenes encompass the arrangement of elements that individuals perceive through their visual senses. Visual search is perhaps one of the most typical jobs that we carry out several times a day. This is one of the main paradigms for researching visual attention. Many visual task models have been put forward in an effort to better understand visual attention. Fixations and the rapid movement of the eye - saccades, define visual exploration and visual search. When we subject viewers to highly informative visual scenes, more microsaccades (microscopic saccades) tend to get generated and viewers fixate for longer. Numerous studies have linked microsaccades to perception and attentional allocation. We aim to explore this relationship between microsaccades, pupil dilation and other key eye features and perform task classification on visual scenes by using an ensemble of Machine Learning Classifiers. This ensemble will involve employing various Machine Learning models to classify our tasks and the final outcome will be decided based on the results of the entire ensemble.
Recommended Citation
Ranganath, Rahul, "Visual Scene Classification using Ensemble of Machine Learning Classifiers" (2023). Master's Projects. 1320.
https://scholarworks.sjsu.edu/etd_projects/1320
