Low-Light Image Enhancement Using Image-to-Frequency Filter Learning

Low-light image (LLI) enhancement techniques have recently demonstrated remarkable progress especially with the use of deep learning (DL) approaches. Yet most existing techniques adopt an image-to-image learning paradigm where DL model architectures are constrained due to latent image feature recons...

Full description

Saved in:
Bibliographic Details
Main Author: Al Sobbahi, Rayan (author)
Other Authors: Tekli, Joe (author)
Format: conferenceObject
Published: 2022
Subjects:
Online Access:http://hdl.handle.net/10725/16288
https://doi.org/10.1007/978-3-031-06430-2_58
http://libraries.lau.edu.lb/research/laur/terms-of-use/articles.php
https://link.springer.com/chapter/10.1007/978-3-031-06430-2_58
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513472550666240
author Al Sobbahi, Rayan
author2 Tekli, Joe
author2_role author
author_facet Al Sobbahi, Rayan
Tekli, Joe
author_role author
dc.contributor.none.fl_str_mv Sclaroff, Stan
Distante, Cosimo
Leo, Marco
dc.creator.none.fl_str_mv Al Sobbahi, Rayan
Tekli, Joe
dc.date.none.fl_str_mv 2022
2022-05-17
2024-11-08T11:37:50Z
2024-11-08T11:37:50Z
dc.identifier.none.fl_str_mv 9783031064302
http://hdl.handle.net/10725/16288
https://doi.org/10.1007/978-3-031-06430-2_58
Al Sobbahi, R., & Tekli, J. (2022, May). Low-light image enhancement using image-to-frequency filter learning. In International Conference on Image Analysis and Processing (pp. 693-705). Cham: Springer International Publishing.
http://libraries.lau.edu.lb/research/laur/terms-of-use/articles.php
https://link.springer.com/chapter/10.1007/978-3-031-06430-2_58
dc.language.none.fl_str_mv en
dc.publisher.none.fl_str_mv Springer
dc.relation.none.fl_str_mv 13231
dc.rights.*.fl_str_mv info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Image analysis -- Congresses
Image processing -- Digital techniques -- Congresses
dc.title.none.fl_str_mv Low-Light Image Enhancement Using Image-to-Frequency Filter Learning
Lecture Notes in Computer Science
dc.type.none.fl_str_mv Conference Paper / Proceeding
info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/conferenceObject
description Low-light image (LLI) enhancement techniques have recently demonstrated remarkable progress especially with the use of deep learning (DL) approaches. Yet most existing techniques adopt an image-to-image learning paradigm where DL model architectures are constrained due to latent image feature reconstruction. In this paper, we propose a new LLI enhancement solution titled LLHFNet (Low-light Homomorphic Filtering Network) which performs image-to-frequency filter learning. It is designed independently from custom DL architectures and can be seamlessly coupled with existing feature extractors like ResNet50 and VGG16. We have conducted a large battery of experiments using SICE and Pascal VOC datasets to evaluate LLHFNet’s enhancement quality. Our solution consistently ranks among the best existing image enhancement techniques and is able to robustly handle LLIs and normal-light images (NLIs).
eu_rights_str_mv openAccess
format conferenceObject
id LAURepo_1dfe9da70dd5d439180f1779f43b06d3
identifier_str_mv 9783031064302
Al Sobbahi, R., & Tekli, J. (2022, May). Low-light image enhancement using image-to-frequency filter learning. In International Conference on Image Analysis and Processing (pp. 693-705). Cham: Springer International Publishing.
language_invalid_str_mv en
network_acronym_str LAURepo
network_name_str Lebanese American University repository
oai_identifier_str oai:laur.lau.edu.lb:10725/16288
publishDate 2022
publisher.none.fl_str_mv Springer
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling Low-Light Image Enhancement Using Image-to-Frequency Filter LearningLecture Notes in Computer ScienceAl Sobbahi, RayanTekli, JoeImage analysis -- CongressesImage processing -- Digital techniques -- CongressesLow-light image (LLI) enhancement techniques have recently demonstrated remarkable progress especially with the use of deep learning (DL) approaches. Yet most existing techniques adopt an image-to-image learning paradigm where DL model architectures are constrained due to latent image feature reconstruction. In this paper, we propose a new LLI enhancement solution titled LLHFNet (Low-light Homomorphic Filtering Network) which performs image-to-frequency filter learning. It is designed independently from custom DL architectures and can be seamlessly coupled with existing feature extractors like ResNet50 and VGG16. We have conducted a large battery of experiments using SICE and Pascal VOC datasets to evaluate LLHFNet’s enhancement quality. Our solution consistently ranks among the best existing image enhancement techniques and is able to robustly handle LLIs and normal-light images (NLIs).1 online resource (xxviii, 793 pages) : illustrations.Includes bibliographical references.SpringerSclaroff, StanDistante, CosimoLeo, Marco2024-11-08T11:37:50Z2024-11-08T11:37:50Z20222022-05-17Conference Paper / Proceedinginfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObject9783031064302http://hdl.handle.net/10725/16288https://doi.org/10.1007/978-3-031-06430-2_58Al Sobbahi, R., & Tekli, J. (2022, May). Low-light image enhancement using image-to-frequency filter learning. In International Conference on Image Analysis and Processing (pp. 693-705). Cham: Springer International Publishing.http://libraries.lau.edu.lb/research/laur/terms-of-use/articles.phphttps://link.springer.com/chapter/10.1007/978-3-031-06430-2_58en13231info:eu-repo/semantics/openAccessoai:laur.lau.edu.lb:10725/162882024-11-08T11:37:50Z
spellingShingle Low-Light Image Enhancement Using Image-to-Frequency Filter Learning
Al Sobbahi, Rayan
Image analysis -- Congresses
Image processing -- Digital techniques -- Congresses
status_str publishedVersion
title Low-Light Image Enhancement Using Image-to-Frequency Filter Learning
title_full Low-Light Image Enhancement Using Image-to-Frequency Filter Learning
title_fullStr Low-Light Image Enhancement Using Image-to-Frequency Filter Learning
title_full_unstemmed Low-Light Image Enhancement Using Image-to-Frequency Filter Learning
title_short Low-Light Image Enhancement Using Image-to-Frequency Filter Learning
title_sort Low-Light Image Enhancement Using Image-to-Frequency Filter Learning
topic Image analysis -- Congresses
Image processing -- Digital techniques -- Congresses
url http://hdl.handle.net/10725/16288
https://doi.org/10.1007/978-3-031-06430-2_58
http://libraries.lau.edu.lb/research/laur/terms-of-use/articles.php
https://link.springer.com/chapter/10.1007/978-3-031-06430-2_58