Akanuma, Asei. 2020. Colour for the Advancement of Deep Learning in Computer Vision. Doctoral thesis, Goldsmiths, University of London [Thesis]

Preview

Text COM_thesis_AkanumaA_2020.pdf - Accepted Version Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (5MB) | Preview

Abstract or Description

This thesis explores several research areas for Deep Learning related to computer vision concerning colours. First, this thesis considers one of the most long standing challenges that has remained for Deep Learning which is, how can Deep Learning algorithms learn successfully without using human annotated data? To that end, this thesis examines using colours in images to learn meaningful representations of vision as a substitute for learning from hand-annotated data. Second, is another related topic to the previous, which is the application of Deep Learning to automate the complex graphics task of image colourisation, which is the process of adding colours to black and white images. Third, this thesis explores colour spaces and how the representations of colours in images affect the performance in Deep Learning models.

Item Type:	Thesis (Doctoral)
Identification Number (DOI):	https://doi.org/10.25602/GOLD.00030181
Keywords:	Deep Learning, Vision, Self-supervised Learning, Image Colourisation, Colour Spaces
Departments, Centres and Research Units:	Computing
Date:	31 December 2020
Item ID:	30181
Date Deposited:	16 Jun 2021 08:40
Last Modified:	08 Sep 2022 13:08
URI:	https://research.gold.ac.uk/id/eprint/30181

View statistics for this item...

Edit Record (login required)