BHarwood-Thesis_for_submission (1)_Redacted.pdf (13.88 MB)
Download file

Understanding High Dimensional Visual Data

Download (13.88 MB)
posted on 05.03.2019, 03:47 by BENJAMIN JOHN HARWOOD
Researchers are increasingly using digital images to teach machines how to see and understand our physical world. While conventional wisdom states that a picture is worth a thousand words and seeing is believing, it is now important to ask what a picture is really worth and how much trust we can place in vision alone. This thesis has focused on the advancement of these computer vision systems. The algorithms produced by this research have established new levels of efficiency for retrieving and comparing visual data, as well as defining new machine learning techniques that extend our current capacity for automating complex visual tasks.


Campus location


Principal supervisor

Thomas William Drummond

Year of Award


Department, School or Centre

Electrical and Computer Systems Engineering


Doctor of Philosophy

Degree Type



Faculty of Engineering