Enhancing Low-Light Images using Deep Learning

Raju, Linda Susan (2023) Enhancing Low-Light Images using Deep Learning. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (4MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

This research addresses the challenge of low-light image denoising through a multi-stage approach involving convolutional neural networks (CNNs) and a generative adversarial network (GAN) for enhancement. Motivated by the persistent issue of noise in low-light conditions impacting image quality, the study aims to integrate the denoising capabilities of CNN with the refinement offered by a GAN. The CNN models are trained separately to denoise the low-light images. Subsequently, the GAN model is used where its generator component is replaced with the pre-trained denoising CNN model and after the training process, the enhancement using the GAN shows improvements in image quality. It highlights the benefit of the integrated approach compared to the standalone denoising models of sequential processing in achieving low-light image enhancement.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Milosavljevic, Vladimir UNSPECIFIED
Uncontrolled Keywords:	Low-light images; Denoising; Enhancement; Convolutional Neural Networks (CNN); Generative Adversarial Networks (GANs); Feature Map Based Convolutional Neural Networks (FMBCNN)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > TR Photography Q Science > Q Science (General) > Research > Research--Equipment and Supplies > Scientific apparatus and instruments > Physical instruments > Detectors > Remote sensing > Electronic surveillance > Video surveillance Z Bibliography. Library Science. Information Resources > ZA Information resources > Research > Research--Equipment and Supplies > Scientific apparatus and instruments > Physical instruments > Detectors > Remote sensing > Electronic surveillance > Video surveillance
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	21 May 2025 10:30
Last Modified:	21 May 2025 10:30
URI:	https://norma.ncirl.ie/id/eprint/7599

Actions (login required)

View Item