Iterative Retinex-Based Decomposition Framework for Low Light Visibility Restoration
Images captured in low-light conditions often suffer from low brightness, low signal-to-noise ratio, low contrast, a narrow gray range, and color distortion, which can significantly impact human perception and limit the performance of various computer vision applications. Most existing low-light ima...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10107387/ |
| _version_ | 1797838016242253824 |
|---|---|
| author | Hayk A. Gasparyan Sargis A. Hovhannisyan Stepan V. Babayan Sos S. Agaian |
| author_facet | Hayk A. Gasparyan Sargis A. Hovhannisyan Stepan V. Babayan Sos S. Agaian |
| author_sort | Hayk A. Gasparyan |
| collection | DOAJ |
| description | Images captured in low-light conditions often suffer from low brightness, low signal-to-noise ratio, low contrast, a narrow gray range, and color distortion, which can significantly impact human perception and limit the performance of various computer vision applications. Most existing low-light image restoration methods require assistance with a color cast, local over-exposure, glow, and artificial light sources. This paper proposes a new framework called RSD-Net, incorporating several innovative blocks, including a novel iterative Retinex network decomposition and enhancement algorithms, to improve the visibility and quality of images captured in low-light or nighttime conditions. We have extensively evaluated our proposed method on various benchmarking datasets and under different real-world scenarios, including challenging conditions such as glow, artificial light sources, low illumination, and noise. Moreover, we have evaluated our method on a face detection algorithm using extremely dark images and compared its performance with other state-of-the-art methods. The simulation results show that our proposed framework achieves a noticeable improvement compared to other low-quality image restoration techniques and enhances face detection accuracy in low-quality environments. The proposed framework has the potential to substantially impact human perception and enhance the performance of numerous computer vision applications. |
| first_indexed | 2024-04-09T15:34:00Z |
| format | Article |
| id | doaj.art-09367b014ace46d69521f75956803da3 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-09T15:34:00Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-09367b014ace46d69521f75956803da32023-04-27T23:00:39ZengIEEEIEEE Access2169-35362023-01-0111402984031310.1109/ACCESS.2023.326971910107387Iterative Retinex-Based Decomposition Framework for Low Light Visibility RestorationHayk A. Gasparyan0Sargis A. Hovhannisyan1Stepan V. Babayan2https://orcid.org/0009-0008-0867-2932Sos S. Agaian3https://orcid.org/0000-0003-4601-4507Department of Mathematics and Mechanics, Yerevan State University, Yerevan, ArmeniaDepartment of Mathematics and Mechanics, Yerevan State University, Yerevan, ArmeniaDepartment of Information Security, National Polytechnic University of Armenia, Yerevan, ArmeniaDepartment of Computer Science, College of Staten Island (CSI), The City University of New York, New York, NY, USAImages captured in low-light conditions often suffer from low brightness, low signal-to-noise ratio, low contrast, a narrow gray range, and color distortion, which can significantly impact human perception and limit the performance of various computer vision applications. Most existing low-light image restoration methods require assistance with a color cast, local over-exposure, glow, and artificial light sources. This paper proposes a new framework called RSD-Net, incorporating several innovative blocks, including a novel iterative Retinex network decomposition and enhancement algorithms, to improve the visibility and quality of images captured in low-light or nighttime conditions. We have extensively evaluated our proposed method on various benchmarking datasets and under different real-world scenarios, including challenging conditions such as glow, artificial light sources, low illumination, and noise. Moreover, we have evaluated our method on a face detection algorithm using extremely dark images and compared its performance with other state-of-the-art methods. The simulation results show that our proposed framework achieves a noticeable improvement compared to other low-quality image restoration techniques and enhances face detection accuracy in low-quality environments. The proposed framework has the potential to substantially impact human perception and enhance the performance of numerous computer vision applications.https://ieeexplore.ieee.org/document/10107387/Glow decompositionlow light image enhancementnighttime visibility restorationretinex decomposition |
| spellingShingle | Hayk A. Gasparyan Sargis A. Hovhannisyan Stepan V. Babayan Sos S. Agaian Iterative Retinex-Based Decomposition Framework for Low Light Visibility Restoration IEEE Access Glow decomposition low light image enhancement nighttime visibility restoration retinex decomposition |
| title | Iterative Retinex-Based Decomposition Framework for Low Light Visibility Restoration |
| title_full | Iterative Retinex-Based Decomposition Framework for Low Light Visibility Restoration |
| title_fullStr | Iterative Retinex-Based Decomposition Framework for Low Light Visibility Restoration |
| title_full_unstemmed | Iterative Retinex-Based Decomposition Framework for Low Light Visibility Restoration |
| title_short | Iterative Retinex-Based Decomposition Framework for Low Light Visibility Restoration |
| title_sort | iterative retinex based decomposition framework for low light visibility restoration |
| topic | Glow decomposition low light image enhancement nighttime visibility restoration retinex decomposition |
| url | https://ieeexplore.ieee.org/document/10107387/ |
| work_keys_str_mv | AT haykagasparyan iterativeretinexbaseddecompositionframeworkforlowlightvisibilityrestoration AT sargisahovhannisyan iterativeretinexbaseddecompositionframeworkforlowlightvisibilityrestoration AT stepanvbabayan iterativeretinexbaseddecompositionframeworkforlowlightvisibilityrestoration AT sossagaian iterativeretinexbaseddecompositionframeworkforlowlightvisibilityrestoration |