Low-Light Image Enhancement Based on Generative Adversarial Network

Abirami R., Nandhini and Vincent P. M., Durai Raj (2021) Low-Light Image Enhancement Based on Generative Adversarial Network. Frontiers in Genetics, 12. ISSN 1664-8021

[thumbnail of pubmed-zip/versions/2/package-entries/fgene-12-799777-r1/fgene-12-799777.pdf] Text
pubmed-zip/versions/2/package-entries/fgene-12-799777-r1/fgene-12-799777.pdf - Published Version

Download (3MB)

Abstract

Image enhancement is considered to be one of the complex tasks in image processing. When the images are captured under dim light, the quality of the images degrades due to low visibility degenerating the vision-based algorithms’ performance that is built for very good quality images with better visibility. After the emergence of a deep neural network number of methods has been put forward to improve images captured under low light. But, the results shown by existing low-light enhancement methods are not satisfactory because of the lack of effective network structures. A low-light image enhancement technique (LIMET) with a fine-tuned conditional generative adversarial network is presented in this paper. The proposed approach employs two discriminators to acquire a semantic meaning that imposes the obtained results to be realistic and natural. Finally, the proposed approach is evaluated with benchmark datasets. The experimental results highlight that the presented approach attains state-of-the-performance when compared to existing methods. The models’ performance is assessed using Visual Information Fidelitysse, which assesses the generated image’s quality over the degraded input. VIF obtained for different datasets using the proposed approach are 0.709123 for LIME dataset, 0.849982 for DICM dataset, 0.619342 for MEF dataset.

Item Type: Article
Subjects: Souths Book > Medical Science
Depositing User: Unnamed user with email support@southsbook.com
Date Deposited: 16 Jan 2023 11:15
Last Modified: 29 Apr 2024 07:56
URI: http://research.europeanlibrarypress.com/id/eprint/2

Actions (login required)

View Item
View Item