Publication:
Real-time Restoration of Quality Distortions in Mobile Images using Deep Learning

Simple item page
dc.contributor.authorKocak, Taskin
dc.contributor.authorCiloglu, Cagkan
dc.contributor.institutionKocak, Taskin, University of New Orleans Dr. Robert A. Savoie College of Engineering, New Orleans, United States
dc.contributor.institutionCiloglu, Cagkan, Department of Computer Engineering, Bahçeşehir Üniversitesi, Istanbul, Turkey
dc.date.accessioned2025-10-05T15:42:04Z
dc.date.issued2020
dc.description.abstractFrames provided by camera on mobile devices may be distorted because of camera defects and/or weather conditions such as rain and snow. These distortions affect image classifiers. This paper proposes using deep-learning architectures to restore quality distortions in real-time mobile video for image classifiers. An iOS based app is developed using CoreML to show that deep convolutional auto-encoder (CAE) based methods can be used to restore picture quality. © 2021 Elsevier B.V., All rights reserved.
dc.description.sponsorshipIEEE Computer Society Technical Committee on Semantic Computing (TCSEM)
dc.identifier.conferenceName3rd IEEE International Conference on Artificial Intelligence and Knowledge Engineering, AIKE 2020
dc.identifier.conferencePlaceIrvine, CA
dc.identifier.doi10.1109/AIKE48582.2020.00025
dc.identifier.endpage129
dc.identifier.isbn9781728187082
dc.identifier.scopus2-s2.0-85102401711
dc.identifier.startpage126
dc.identifier.urihttps://doi.org/10.1109/AIKE48582.2020.00025
dc.identifier.urihttps://hdl.handle.net/20.500.14719/10144
dc.language.isoen
dc.publisherInstitute of Electrical and Electronics Engineers Inc.
dc.subject.authorkeywordsDeep Neural Network Model
dc.subject.authorkeywordsImage Classifer
dc.subject.authorkeywordsImage Restoration
dc.subject.authorkeywordsMobile Image
dc.subject.authorkeywordsCameras
dc.subject.authorkeywordsImage Classification
dc.subject.authorkeywordsImage Reconstruction
dc.subject.authorkeywordsRestoration
dc.subject.authorkeywordsAuto Encoders
dc.subject.authorkeywordsImage Classifiers
dc.subject.authorkeywordsLearning Architectures
dc.subject.authorkeywordsMobile Images
dc.subject.authorkeywordsPicture Quality
dc.subject.authorkeywordsReal Time
dc.subject.authorkeywordsReal-time Mobile Video
dc.subject.authorkeywordsDeep Learning
dc.subject.indexkeywordsCameras
dc.subject.indexkeywordsImage classification
dc.subject.indexkeywordsImage reconstruction
dc.subject.indexkeywordsRestoration
dc.subject.indexkeywordsAuto encoders
dc.subject.indexkeywordsImage Classifiers
dc.subject.indexkeywordsLearning architectures
dc.subject.indexkeywordsMobile images
dc.subject.indexkeywordsPicture quality
dc.subject.indexkeywordsReal time
dc.subject.indexkeywordsReal-time mobile video
dc.subject.indexkeywordsDeep learning
dc.titleReal-time Restoration of Quality Distortions in Mobile Images using Deep Learning
dc.typeConference Paper
dcterms.referencesSzegedy, Christian, Going deeper with convolutions, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 07-12-June-2015, pp. 1-9, (2015), He, Kaiming, Deep residual learning for image recognition, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016-December, pp. 770-778, (2016), Squeezenet Alexnet Level Accuracy with 50x Fewer Parameters and 1mb Model Size, (2016), Mobilenets Efficient Convolutional Neural Networks for Mobile Vision Applications, (2017)
dspace.entity.typePublication
local.indexed.atScopus
person.identifier.scopus-author-id7003330141
person.identifier.scopus-author-id57222349176

Files

Collections

Scopus İndeksli Yayınlar Koleksiyonu