Article
Computer Science, Artificial Intelligence
Runxing Zhao, Zhiwen Wang, Wuyuan Guo, Canlong Zhang
Summary: This paper proposes an image enhancement algorithm that can adapt to different exposure conditions. The algorithm utilizes forward and reverse dual-channels as initial illumination maps, and applies a guided filter to retain more detailed information. An improved adaptive gamma correction method is also introduced, and the images are fused by multi-scale exposure to obtain high-quality results.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Automation & Control Systems
Dan Zhang, Zongxin He, Xiaohuan Zhang, Zhen Wang, Wenyi Ge, Taian Shi, Yi Lin
Summary: This paper proposes an underwater image enhancement method based on color correction and multi-scale fusion (CCMF). The method includes a color correction method with red channel compensation and a contrast enhancement method based on guided filtering. It also introduces an adaptive gamma correction method and a multi-scale pyramid fusion technique to integrate different feature information. Experimental results show that the proposed method outperforms other state-of-the-art methods in terms of objective indicators such as UCIQE, UIQM, and EG.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Computer Science, Information Systems
Inho Jeong, Chul Lee
Summary: The algorithm proposed an efficient low-light image enhancement by estimating gamma correction parameters through optimization, separating luminance and chrominance channels, normalizing the luminance channel with a logarithmic function, independently estimating optimal gamma parameters for dark and bright regions, and merging them for enhanced image. This approach demonstrates higher enhancement performance and speed improvement compared to state-of-the-art algorithms in both subjective and objective evaluations.
MULTIMEDIA TOOLS AND APPLICATIONS
(2021)
Article
Engineering, Marine
Farong Gao, Kai Wang, Zhangyi Yang, Yejian Wang, Qizhong Zhang
Summary: The proposed method addresses low contrast and color distortion in underwater images through local contrast correction and multi-scale fusion.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2021)
Article
Biotechnology & Applied Microbiology
Ying Sun, Zichen Zhao, Du Jiang, Xiliang Tong, Bo Tao, Guozhang Jiang, Jianyi Kong, Juntong Yun, Ying Liu, Xin Liu, Guojun Zhao, Zifan Fang
Summary: This paper proposes a low-light image enhancement algorithm based on improved multi-scale Retinex and Artificial Bee Colony algorithm optimization, which can solve the image quality problems in low-light conditions and improve the sharpness, details, and color restoration effect of the image.
FRONTIERS IN BIOENGINEERING AND BIOTECHNOLOGY
(2022)
Article
Computer Science, Information Systems
Xuan Liu, Chenfeng Zhang, Yingzhi Wang, Kai Ding, Tailin Han, Hong Liu, Yu Tian, Bo Xu, Mingchi Ju
Summary: This study proposes a low-light image enhancement method based on multi-scale network fusion to address the issue of object detection in low-light environments. By preprocessing the images and fusing features from different resolution levels, the proposed method improves the details and available information in low-light images. Experimental results show that this method outperforms current mainstream methods in terms of enhancement effects and object detection performance.
Article
Computer Science, Software Engineering
Kavinder Singh, Anil Singh Parihar
Summary: This paper proposes a new approach for estimating illumination in low-light image enhancement. The approach includes three major tasks: estimation of structure-aware initial illumination, refinement of the estimated illumination, and correction of lightness in refined illumination. A novel structure-aware initial illumination estimation method using multi-scale guided filtering approach is proposed. The algorithm refines the initial estimation by optimizing a new multi-objective function. Additionally, an adaptive illumination adjustment method is proposed for correcting lightness using the estimated illumination. Qualitative and quantitative analysis demonstrates that the proposed algorithm achieves image enhancement with color constancy and preserves natural details. Performance comparison with state-of-the-art algorithms shows the superiority of the proposed algorithm.
Article
Computer Science, Information Systems
Yadong Xu, Cheng Yang, Beibei Sun, Xiaoan Yan, Minglong Chen
Summary: This paper proposes a novel multi-scale fusion framework for enhancing low-illumination images by generating a sequence of artificial multi-exposure images. The framework incorporates weight maps and a pyramid fusion scheme for layer-by-layer integration of different frequency bands of the image, along with a detail extraction strategy to maintain detail information effectively. Extensive experiments have shown that the framework yields comparable and better performances compared to state-of-the-art techniques in both qualitative and quantitative evaluations.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Information Systems
Jinyu Shi, Shanshan Yu, Huanan Li, Xiuguo Zhang, Changxin Liu
Summary: An underwater image enhancement method based on adaptive color correction and multi-scale fusion is proposed to address issues like color distortion, detail loss, and limited visibility in underwater images. The method does not rely on specific equipment or auxiliary information. It uses adaptive color correction to address color distortion, converts the color-corrected image to the CIE-Lab color space, and applies an updated logarithmic image processing (LIP) model to the luminance channel L to improve contrast. The final enhanced image is created by fusing the color-corrected image with the contrast-improved image using a multi-scale fusion technique based on contrast, saliency, and saturation. The proposed method produces better visual quality and higher average values in underwater image quality evaluation compared to state-of-the-art methods.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Chemistry, Multidisciplinary
Xinxin Pan, Changli Li, Zhigeng Pan, Jingwen Yan, Shiqiang Tang, Xinghui Yin
Summary: This study proposes a retinex-based method for low-light image enhancement, which improves image brightness and contrast by enhancing the illumination map. Experimental results demonstrate that it outperforms other state-of-the-art methods in both subjective vision and quantitative evaluation.
APPLIED SCIENCES-BASEL
(2022)
Article
Optics
Xiaoyan Lei, Huibin Wang, Jie Shen, Haiyun Liu
Summary: This paper proposes a novel underwater image enhancement method based on color correction and dual image multi-scale fusion. It addresses the issues of color cast, poor contrast, and detail loss in underwater images, resulting in high-quality images with improved details.
Article
Engineering, Biomedical
Shine P. James, D. Abraham Chandy
Summary: The paper proposes an algorithm called Gamma Correction of Illumination Component (GCIC) for devignetting fundus images. GCIC showed lower values of Average Gradient of the Illumination Component (AGIC), Lightness Order Error (LOE), and computational time. It outperforms other devignetting algorithms in terms of contrast-to-noise-ratio (CNR), peak-signal-to-noise-ratio (PSNR), structure similarity index (SSIM), and entropy.
BIOCYBERNETICS AND BIOMEDICAL ENGINEERING
(2021)
Article
Engineering, Electrical & Electronic
Ge Zhu, Yuhan Chen, Xianquan Wang, Yiheng Zhang
Summary: In this paper, a multi-layer and multi-scale feature fusion network (MMFF-Net) is proposed to enhance low-light infrared images. Features at different layers of the image are extracted using an adaptively modified deep network, and a multi-scale adaptive feature fusion module (MAFFM) is designed to preserve and fuse multi-scale information. Experimental results show that the algorithm performs well in enhancing low-light infrared images.
SIGNAL IMAGE AND VIDEO PROCESSING
(2023)
Article
Engineering, Electrical & Electronic
Yong Yang, Danjie Zhang, Weiguo Wan, Shuying Huang
Summary: A novel multiscale exposure image fusion method based on multivisual feature measurement and detail enhancement is proposed, which achieves better fusion performance by measuring the visual features of the source images and optimizing the weight maps.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Computer Science, Information Systems
Junyu Fan, Jinjiang Li, Lu Ren, Zheng Chen
Summary: In this article, the authors propose a multi-scale dynamic fusion method for correcting images captured under non-ideal lighting conditions. The method balances the overall illumination, maintains brightness contrast, enhances image details, and provides a better visual experience through the use of a multi-branch multi-scale neural network, attention mechanisms, and fusion methods.
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION
(2023)