Low-Light Image Enhancement Using CycleGAN-Based Near-Infrared Image Generation and Fusion
Image visibility is often degraded under challenging conditions such as low light, backlighting, and inadequate contrast. To mitigate these issues, techniques like histogram equalization, high dynamic range (HDR) tone mapping and near-infrared (NIR)–visible image fusion are widely employed. However,...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/12/24/4028 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846103780083367936 |
|---|---|
| author | Min-Han Lee Young-Ho Go Seung-Hwan Lee Sung-Hak Lee |
| author_facet | Min-Han Lee Young-Ho Go Seung-Hwan Lee Sung-Hak Lee |
| author_sort | Min-Han Lee |
| collection | DOAJ |
| description | Image visibility is often degraded under challenging conditions such as low light, backlighting, and inadequate contrast. To mitigate these issues, techniques like histogram equalization, high dynamic range (HDR) tone mapping and near-infrared (NIR)–visible image fusion are widely employed. However, these methods have inherent drawbacks: histogram equalization frequently causes oversaturation and detail loss, while visible–NIR fusion requires complex and error-prone images. The proposed algorithm of a complementary cycle-consistent generative adversarial network (CycleGAN)-based training with visible and NIR images, leverages CycleGAN to generate fake NIR images by blending the characteristics of visible and NIR images. This approach presents tone compression and preserves fine details, effectively addressing the limitations of traditional methods. Experimental results demonstrate that the proposed method outperforms conventional algorithms, delivering superior quality and detail retention. This advancement holds substantial promise for applications where dependable image visibility is critical, such as autonomous driving and CCTV (Closed-Circuit Television) surveillance systems. |
| format | Article |
| id | doaj-art-4f6fe9a61cdd4f30b98dcdf14d75dfdb |
| institution | Kabale University |
| issn | 2227-7390 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj-art-4f6fe9a61cdd4f30b98dcdf14d75dfdb2024-12-27T14:38:20ZengMDPI AGMathematics2227-73902024-12-011224402810.3390/math12244028Low-Light Image Enhancement Using CycleGAN-Based Near-Infrared Image Generation and FusionMin-Han Lee0Young-Ho Go1Seung-Hwan Lee2Sung-Hak Lee3School of Electronic and Electrical Engineering, Kyungpook National University, 80 Daehak-ro, Buk-gu, Daegu 41566, Republic of KoreaSchool of Electronic and Electrical Engineering, Kyungpook National University, 80 Daehak-ro, Buk-gu, Daegu 41566, Republic of KoreaSchool of Electronic and Electrical Engineering, Kyungpook National University, 80 Daehak-ro, Buk-gu, Daegu 41566, Republic of KoreaSchool of Electronic and Electrical Engineering, Kyungpook National University, 80 Daehak-ro, Buk-gu, Daegu 41566, Republic of KoreaImage visibility is often degraded under challenging conditions such as low light, backlighting, and inadequate contrast. To mitigate these issues, techniques like histogram equalization, high dynamic range (HDR) tone mapping and near-infrared (NIR)–visible image fusion are widely employed. However, these methods have inherent drawbacks: histogram equalization frequently causes oversaturation and detail loss, while visible–NIR fusion requires complex and error-prone images. The proposed algorithm of a complementary cycle-consistent generative adversarial network (CycleGAN)-based training with visible and NIR images, leverages CycleGAN to generate fake NIR images by blending the characteristics of visible and NIR images. This approach presents tone compression and preserves fine details, effectively addressing the limitations of traditional methods. Experimental results demonstrate that the proposed method outperforms conventional algorithms, delivering superior quality and detail retention. This advancement holds substantial promise for applications where dependable image visibility is critical, such as autonomous driving and CCTV (Closed-Circuit Television) surveillance systems.https://www.mdpi.com/2227-7390/12/24/4028tone compressionCycleGANvisible–NIR image fusioncontrast-limited adaptive histogram equalization |
| spellingShingle | Min-Han Lee Young-Ho Go Seung-Hwan Lee Sung-Hak Lee Low-Light Image Enhancement Using CycleGAN-Based Near-Infrared Image Generation and Fusion Mathematics tone compression CycleGAN visible–NIR image fusion contrast-limited adaptive histogram equalization |
| title | Low-Light Image Enhancement Using CycleGAN-Based Near-Infrared Image Generation and Fusion |
| title_full | Low-Light Image Enhancement Using CycleGAN-Based Near-Infrared Image Generation and Fusion |
| title_fullStr | Low-Light Image Enhancement Using CycleGAN-Based Near-Infrared Image Generation and Fusion |
| title_full_unstemmed | Low-Light Image Enhancement Using CycleGAN-Based Near-Infrared Image Generation and Fusion |
| title_short | Low-Light Image Enhancement Using CycleGAN-Based Near-Infrared Image Generation and Fusion |
| title_sort | low light image enhancement using cyclegan based near infrared image generation and fusion |
| topic | tone compression CycleGAN visible–NIR image fusion contrast-limited adaptive histogram equalization |
| url | https://www.mdpi.com/2227-7390/12/24/4028 |
| work_keys_str_mv | AT minhanlee lowlightimageenhancementusingcycleganbasednearinfraredimagegenerationandfusion AT younghogo lowlightimageenhancementusingcycleganbasednearinfraredimagegenerationandfusion AT seunghwanlee lowlightimageenhancementusingcycleganbasednearinfraredimagegenerationandfusion AT sunghaklee lowlightimageenhancementusingcycleganbasednearinfraredimagegenerationandfusion |