.

Low-Light Image Enhancement for Object Classification using Deep Learning

LAUR Repository

Show simple item record

dc.contributor.author Al Sobbahi, Rayan
dc.date.accessioned 2022-06-16T07:55:54Z
dc.date.available 2022-06-16T07:55:54Z
dc.date.copyright 2021 en_US
dc.date.issued 2021-05-11
dc.identifier.uri http://hdl.handle.net/10725/13703
dc.description.abstract Low-light image (LLI) enhancement is an important image processing task that aims at improving the illumination of images taken under low-light conditions. Recently, a remarkable progress has been made in utilizing deep learning (DL) approaches for LLI enhancement. In this thesis, we perform a concise and comprehensive review and comparative study of the most recent DL models used for LLI enhancement. We address LLI enhancement in two ways: i) standalone, as a separate task, and ii) end-to-end, as a pre-processing stage embedded within another high-level computer vision task, namely object detection and classification. We also conduct a feature analysis of DL feature maps extracted from normal, low-light, and enhanced images, and perform the occlusion experiment to better understand the effect of enhancement on object detection and classification. We then address a common problem of these models depicted by their design as standalone solutions without focusing on the impact of enhancement on high-level computer vision tasks like object classification. Our review and empirical evaluations show that enhancing LLI visual quality does not necessarily correlate with improved object detection and classification performance, and may even deteriorate it, especially in cases where enhanced images include extreme artifacts. To solve the problem, we propose a new LLI enhancement model that performs image-to-frequency filter learning and is designed for seamless integration into classification models. Through this integration, the classification model is embedded with an internal enhancement capability and is jointly trained to optimize both enhancement and classification performance. We conduct a large battery of experiments involving 76 testers to evaluate our approach’s LLI enhancement quality. When evaluated as a standalone enhancement model, our solution consistently ranks first or second among five state of the art enhancement techniques both quantitatively and qualitatively. When embedded with a classification model, our solution achieves an average of 5.5% improvement in classification accuracy, compared with the traditional pipeline of separate enhancement followed by classification. Results clearly produce robust classification performance on both low light and normal light images. en_US
dc.language.iso en en_US
dc.subject Image processing en_US
dc.subject Image processing -- Digital techniques en_US
dc.subject Detectors en_US
dc.subject Electrical engineering en_US
dc.subject Lebanese American University -- Dissertations en_US
dc.subject Dissertations, Academic en_US
dc.title Low-Light Image Enhancement for Object Classification using Deep Learning en_US
dc.type Thesis en_US
dc.term.submitted Spring en_US
dc.author.degree MS in Computer Engineering en_US
dc.author.school SOE en_US
dc.author.idnumber 201501537 en_US
dc.author.commembers Fawaz, Wissam
dc.author.commembers Nakad, Zahi
dc.author.department Electrical And Computer Engineering en_US
dc.description.physdesc 1 online resource (xiv, 100 leaves): col. ill. en_US
dc.author.advisor Tekli, Joe
dc.keywords Image Enhancement en_US
dc.keywords Low-light Conditions en_US
dc.keywords Deep Learning en_US
dc.keywords Object Detection and Classification en_US
dc.keywords Homomorphic Filtering en_US
dc.keywords Empirical Comparison en_US
dc.keywords Comparative Study en_US
dc.description.bibliographiccitations Includes bibliographical references (leaf 92-100) en_US
dc.identifier.doi https://doi.org/10.26756/th.2022.211
dc.author.email rayan.alsobbahi@lau.edu.lb en_US
dc.identifier.tou http://libraries.lau.edu.lb/research/laur/terms-of-use/thesis.php en_US
dc.publisher.institution Lebanese American University en_US
dc.author.affiliation Lebanese American University en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search LAUR


Advanced Search

Browse

My Account