A Comparative Study of Image Dehazing Techniques for Image Restoration

Savitri, Khairunnisa (2023) A Comparative Study of Image Dehazing Techniques for Image Restoration. Tugas Akhir (S1) - thesis, UNIVERSITAS BAKRIE.

[thumbnail of Cover]
Preview
Text (Cover)
00. Cover.pdf - Submitted Version

Download (195kB) | Preview
[thumbnail of BAB I-III] Text (BAB I-III)
01. BAB I-III.pdf - Submitted Version
Restricted to Registered users only

Download (1MB) | Request a copy
[thumbnail of BAB IV] Text (BAB IV)
02. BAB IV.pdf - Submitted Version
Restricted to Registered users only

Download (2MB) | Request a copy
[thumbnail of 03. BAB V.pdf] Text
03. BAB V.pdf - Submitted Version
Restricted to Registered users only

Download (31kB) | Request a copy
[thumbnail of Daftar Pustaka]
Preview
Text (Daftar Pustaka)
04. Daftar Pustaka.pdf - Draft Version

Download (100kB) | Preview
[thumbnail of Lampiran] Text (Lampiran)
05 Lampiran.pdf - Submitted Version
Restricted to Registered users only

Download (193kB) | Request a copy

Abstract

Image dehazing is the process of removing haze from images. It is a challenging problem due to the non-linear nature of the haze process and the lack of ground truth data. In recent years, deep learning techniques have been shown to be effective for image dehazing. This research presents a comparative study on image dehazing using CycleGAN and GMAN-Net. CycleGAN is a generative adversarial network that can translate images from one domain to another. GMAN-Net is a generic model-agnostic convolutional neural network that can be used to dehaze images by jointly estimating the transmission map and scene radiance. The study evaluated the performance of CycleGAN and GMAN-Net on a dataset of hazy images with ground truth clear images. The evaluation metrics were PSNR, SSIM, entropy, UIQM, and UCIQE. The results showed that GMAN-Net outperformed CycleGAN on all of the evaluation metrics. GMAN-Net also showed better visual results, with dehazed images that were more accurate and realistic than CycleGAN. The research concludes that GMAN-Net is better for image dehazing than CycleGAN. It is more accurate, realistic, and versatile than CycleGAN.

Item Type: Thesis (Tugas Akhir (S1) - )
Uncontrolled Keywords: image dehazing, CycleGAN, GMAN-Net, objective IQA, PSNR, SSIM, entropy, UIQM, UCIQE
Subjects: Computer Science > Image Processing
Thesis > Thesis (S1)
Divisions: Fakultas Teknik dan Ilmu Komputer > Program Studi Informatika
Depositing User: Khairunnisa Savitri
Date Deposited: 28 Aug 2023 04:19
Last Modified: 28 Aug 2023 04:19
URI: https://repository.bakrie.ac.id/id/eprint/8221

Actions (login required)

View Item View Item