Title:
Understanding perceived quality through visual representations

dc.contributor.advisor AlRegib, Ghassan
dc.contributor.author Temel, Dogancan
dc.contributor.committeeMember McClellan, James H.
dc.contributor.committeeMember Anderson, David V.
dc.contributor.committeeMember Yezzi, Anthony J.
dc.contributor.committeeMember Gebraeel, Nagi
dc.contributor.department Electrical and Computer Engineering
dc.date.accessioned 2017-01-11T14:03:32Z
dc.date.available 2017-01-11T14:03:32Z
dc.date.created 2016-12
dc.date.issued 2016-10-25
dc.date.submitted December 2016
dc.date.updated 2017-01-11T14:03:32Z
dc.description.abstract The formatting of images can be considered as an optimization problem, whose cost function is a quality assessment algorithm. There is a trade-off between bit budget per pixel and quality. To maximize the quality and minimize the bit budget, we need to measure the perceived quality. In this thesis, we focus on understanding perceived quality through visual representations that are based on visual system characteristics and color perception mechanisms. Specifically, we use the contrast sensitivity mechanisms in retinal ganglion cells and the suppression mechanisms in cortical neurons. We utilize color difference equations and color name distances to mimic pixel-wise color perception and a bio-inspired model to formulate center surround effects. Based on these formulations, we introduce two novel image quality estimators PerSIM and CSV, and a new image quality-assistance method BLeSS. We combine our findings from visual system and color perception with data-driven methods to generate visual representations and measure their quality. The majority of existing data-driven methods require subjective scores or degraded images. In contrast, we follow an unsupervised approach that only utilizes generic images. We introduce a novel unsupervised image quality estimator UNIQUE, and extend it with multiple models and layers to obtain MS-UNIQUE and DMS-UNIQUE. In addition to introducing quality estimators, we analyze the role of spatial pooling and boosting in image quality assessment.
dc.description.degree Ph.D.
dc.format.mimetype application/pdf
dc.identifier.uri http://hdl.handle.net/1853/56289
dc.language.iso en_US
dc.publisher Georgia Institute of Technology
dc.subject Perceived quality
dc.subject Visual system
dc.subject Contrast sensitivity
dc.subject Suppression
dc.subject Color perception
dc.subject Color name
dc.subject Color difference
dc.subject Unsupervised learning
dc.subject Spatial pooling
dc.subject Boosting
dc.title Understanding perceived quality through visual representations
dc.type Text
dc.type.genre Dissertation
dspace.entity.type Publication
local.contributor.advisor AlRegib, Ghassan
local.contributor.corporatename School of Electrical and Computer Engineering
local.contributor.corporatename College of Engineering
relation.isAdvisorOfPublication 7942fed2-1bb6-41b8-80fd-4134f6c15d8f
relation.isOrgUnitOfPublication 5b7adef2-447c-4270-b9fc-846bd76f80f2
relation.isOrgUnitOfPublication 7c022d60-21d5-497c-b552-95e489a06569
thesis.degree.level Doctoral
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
TEMEL-DISSERTATION-2016.pdf
Size:
14.19 MB
Format:
Adobe Portable Document Format
Description:
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
LICENSE.txt
Size:
3.87 KB
Format:
Plain Text
Description: