Full Text Available

Note: Clicking the button above will open the full text document at the original institutional repository in a new window.

Using the Earth Mover's Distance for perceptually meaningful visual saliency

Visual saliency is one of the mechanisms that guide our visual attention, or where we look. This topic has seen a lot of research in recent years, starting with biologicallyinspired models, followed by the information-theoretic and recently statistical-based models. This dissertation looks at a stat...

Full description

Saved in:
Bibliographic Details
Main Author: Dunbar, Logan
Other Authors: Nicolls, Fred
Format: Thesis
Language:English
Published: Department of Electrical Engineering 2017
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1867613206097166336
access_status_str Open Access
author Dunbar, Logan
author2 Nicolls, Fred
author_browse Dunbar, Logan
Nicolls, Fred
author_facet Nicolls, Fred
Dunbar, Logan
author_sort Dunbar, Logan
collection Thesis
description Visual saliency is one of the mechanisms that guide our visual attention, or where we look. This topic has seen a lot of research in recent years, starting with biologicallyinspired models, followed by the information-theoretic and recently statistical-based models. This dissertation looks at a state-of-the-art statistical model and studies what effects the histogram construction method and histogram distance measures have on detecting saliency. Equi-width histograms, which have constant bin size, equi-depth histograms, which have constant density per bin, and diagonal histograms, whose bin widths are determined from constant diagonal portions of the empirical cumulative distribution function (ecdf), are used to calculate saliency scores on a publicly available dataset. Crossbin distances are introduced and compared with the currently employed bin-to-bin distances by calculating saliency scores on the same dataset. An exhaustive experiment with combinations of all histogram construction methods and histogram distance measures is performed. It was discovered that using the equi-depth histogram is able to improve various saliency metrics. It is also shown that employing cross-bin histogram distances improves the contrast of the resulting saliency maps, making them more perceptually meaningful but lowering their saliency scores in the process. A novel improvement is made to the model which removes the implicit center bias, which also generates more perceptually meaningful saliency maps but lowers saliency scores. A new scoring method is proposed which aims to deal with the perceptual and scoring disparities.
format Thesis
id oai:open.uct.ac.za:11427/24293
institution University of Cape Town (South Africa)
language eng
last_indexed 2026-06-10T12:32:27.580Z
license_str Not specified — see source repository
provenance_str_mv Harvested via OAI-PMH from UCTD — University of Cape Town Open Access Repository
publishDate 2017
publishDateRange 2017
publishDateSort 2017
publisher Department of Electrical Engineering
publisherStr Department of Electrical Engineering
record_format dspace
source_str UCTD — University of Cape Town Open Access Repository
spelling oai:open.uct.ac.za:11427/24293 Using the Earth Mover's Distance for perceptually meaningful visual saliency Dunbar, Logan Nicolls, Fred Electrical Engineering Visual saliency is one of the mechanisms that guide our visual attention, or where we look. This topic has seen a lot of research in recent years, starting with biologicallyinspired models, followed by the information-theoretic and recently statistical-based models. This dissertation looks at a state-of-the-art statistical model and studies what effects the histogram construction method and histogram distance measures have on detecting saliency. Equi-width histograms, which have constant bin size, equi-depth histograms, which have constant density per bin, and diagonal histograms, whose bin widths are determined from constant diagonal portions of the empirical cumulative distribution function (ecdf), are used to calculate saliency scores on a publicly available dataset. Crossbin distances are introduced and compared with the currently employed bin-to-bin distances by calculating saliency scores on the same dataset. An exhaustive experiment with combinations of all histogram construction methods and histogram distance measures is performed. It was discovered that using the equi-depth histogram is able to improve various saliency metrics. It is also shown that employing cross-bin histogram distances improves the contrast of the resulting saliency maps, making them more perceptually meaningful but lowering their saliency scores in the process. A novel improvement is made to the model which removes the implicit center bias, which also generates more perceptually meaningful saliency maps but lowers saliency scores. A new scoring method is proposed which aims to deal with the perceptual and scoring disparities. 2017-05-16T07:36:49Z 2017-05-16T07:36:49Z 2015 Master Thesis Masters MSc (Eng) http://hdl.handle.net/11427/24293 eng application/pdf Department of Electrical Engineering Faculty of Engineering and the Built Environment University of Cape Town
spellingShingle Electrical Engineering
Dunbar, Logan
Using the Earth Mover's Distance for perceptually meaningful visual saliency
thesis_degree_str Master's
title Using the Earth Mover's Distance for perceptually meaningful visual saliency
title_full Using the Earth Mover's Distance for perceptually meaningful visual saliency
title_fullStr Using the Earth Mover's Distance for perceptually meaningful visual saliency
title_full_unstemmed Using the Earth Mover's Distance for perceptually meaningful visual saliency
title_short Using the Earth Mover's Distance for perceptually meaningful visual saliency
title_sort using the earth mover s distance for perceptually meaningful visual saliency
topic Electrical Engineering
url http://hdl.handle.net/11427/24293
work_keys_str_mv AT dunbarlogan usingtheearthmoversdistanceforperceptuallymeaningfulvisualsaliency