Article
Computer Science, Information Systems
Xiaoning Liu, Hui Li, Ce Zhu
Summary: In this work, we propose an efficient framework for image dehazing, which involves contrast enhancement and exposure fusion stages. The proposed method outperforms state-of-the-art methods in terms of visual and quantitative evaluation.
IEEE TRANSACTIONS ON MULTIMEDIA
(2022)
Article
Computer Science, Artificial Intelligence
Dong Han, Liang Li, Xiaojie Guo, Jiayi Ma
Summary: This paper presents a deep perceptual enhancement network for multi-exposure image fusion, which focuses on informativeness and visual realism, with two modules for content details and color mapping/correction, demonstrating its superiority over other state-of-the-art alternatives both quantitatively and qualitatively. The proposed strategy shows flexibility in improving exposure quality of single images, and can fuse 720p images in more than 60 pairs per second on an Nvidia 2080Ti GPU, making it practical for use.
INFORMATION FUSION
(2022)
Article
Engineering, Electrical & Electronic
Wencheng Wang, Dongliang Yan, Xiaojin Wu, Weikai He, Zhenxue Chen, Xiaohui Yuan, Lun Li
Summary: This paper proposes an adaptive enhancement method for single low-light images based on the strategy of virtual exposure, which generates a high-quality image by fusing multiexposure images. The method adaptively generates exposure control parameters through statistical analysis of the low-light image and applies a quadratic function to construct a virtual exposure enhancer, generating multiple image frames from a single input image. The image sequences and weight images are transformed by a Laplacian pyramid and Gaussian pyramid, respectively, and multiscale fusion is implemented layer by layer, resulting in an enhanced image obtained by pyramid reconstruction rule.
SIGNAL PROCESSING-IMAGE COMMUNICATION
(2023)
Article
Environmental Sciences
Weihong Zhang, Xiaobo Li, Shuping Xu, Xujin Li, Yiguang Yang, Degang Xu, Tiegen Liu, Haofeng Hu
Summary: This paper introduces an underwater color image processing approach that effectively enhances contrast and colors in underwater images by combining frequency and spatial domains. The method addresses challenges such as low contrast, color distortion, and obscured details in underwater images. Experimental results show that the proposed method outperforms other methods in terms of enhancing contrast and rendering natural colors.
Article
Computer Science, Information Systems
Meenakshi Pawar, Sanjay Talbar
Summary: Early detection of breast cancer is crucial for survival, and contrast enhancement techniques can provide accurate segmentation of mammogram images. The DWT coefficient fusion based on local entropy maximization algorithm shows superior performance compared to other contrast enhancement methods, improving edge contents, contrast measure, similarity index, and brightness error values.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2021)
Article
Computer Science, Artificial Intelligence
Haoxiang Lu, Zhenbing Liu, Rushi Lan, Xipeng Pan, Junming Gong
Summary: This paper proposes a new and efficient approach named MFMR for enhancing lowlight images by using the hue-saturation-value (HSV) colour space. The approach includes the estimation of artifact-free illumination and reflection component, adaptive bi-interval histogram and morphological operations for processing, adaptive gamma correction, and adaptive multi-scale fusion strategy for generating high-quality images. The experiments show that this method outperforms state-of-the-art comparison methods and can generate satisfying images in severe conditions such as heavy fog and underwater.
IET IMAGE PROCESSING
(2023)
Article
Automation & Control Systems
Shunmin An, Lihong Xu, Zhichao Deng, Huapeng Zhang
Summary: The article introduces a hybrid fusion method for underwater image enhancement, which solves the problems of white balance distortion, color shift, low visibility, and low contrast. Through experiments, the proposed method achieves optimal results in the application of geometric rotation estimation, feature point matching, and edge detection.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2024)
Article
Computer Science, Information Systems
Lalit Maurya, Viney Lohchab, Prasant Kumar Mahapatra, Janos Abonyi
Summary: Many vision-based systems suffer from poor levels of contrast and brightness due to inadequate and improper illumination during image acquisition. By using nature-inspired optimization, a balance between contrast and brightness can be achieved in image enhancement, improving image quality.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
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
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
Agriculture, Multidisciplinary
Weidong Zhang, Lili Dong, Wenhai Xu
Summary: This paper proposes a novel underwater image enhancement method based on Retinex-inspired color correction and detail preserved fusion technology. The method removes color cast induced by underwater light scattering using a Retinex-inspired color correction strategy, and blends three images to enhance the contrast and detail of the output image. Experimental results demonstrate that the proposed method achieves superior enhancement performance for underwater images of different scenes.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2022)
Article
Computer Science, Information Systems
Zhong Qu, Xu Huang, Ling Liu
Summary: The study introduces a new multi-exposure image fusion algorithm that effectively preserves details and reduces halo artifacts. By utilizing weight maps and pyramid decomposition, the algorithm improves the representation of details, resulting in more realistic images.
MULTIMEDIA SYSTEMS
(2021)
Article
Microscopy
Harbinder Singh, Gabriel Cristobal, Gloria Bueno, Saul Blanco, Simrandeep Singh, P. N. Hrisheekesha, Nitin Mittal
Summary: This paper presents a microscopy image fusion approach to retrieve the complete dynamic range of diatoms with complex cell walls and patterns. The method preserves details in poorly and brightly illuminated regions of the diatom shells by selecting well-exposed regions and improving histogram equalization. The proposed fusion method outperforms state-of-the-art algorithms in quantitative and qualitative assessments.
Article
Computer Science, Information Systems
Rizwan Khan, Adeel Akram, Atif Mehmood
Summary: In this article, a multiview ghost-free image enhancement strategy is proposed for in-the-wild images with unknown exposure and geometry, addressing issues such as highlighted and shadow regions and contrast distortion. By detecting features among multiple viewpoints and synthesizing virtual images, relative brightness and color distortions are compensated for, resulting in high-quality images. The proposed method is shown to outperform state-of-the-art approaches, making it more frequent and feasible for future multiview systems with varying baselines.
Article
Computer Science, Information Systems
Wei Huang, Kaili Li, Mengfan Xu, Rui Huang
Summary: This study proposes a self-supervised framework for non-uniform low-light image enhancement, which only requires low-light images for training. By designing image exposure enhancement networks and exposure fusion networks, global brightness enhancement, noise removal, and detail-rich image enhancement are achieved.
Article
Computer Science, Information Systems
Sheng-Bin Hsu, Chang-Hsing Lee, Pei-Chun Chang, Chin-Chuan Han, Kuo-Chin Fan
IEEE TRANSACTIONS ON MULTIMEDIA
(2018)
Article
Computer Science, Hardware & Architecture
Chih-Hsun Chou, Chang-Hsing Lee, Ya-Hui Chen
Article
Acoustics
Chang-Hsing Lee, Chin-Chuan Han, Ching-Chien Chuang
IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING
(2008)
Article
Computer Science, Information Systems
Chang-Hsing Lee, Jau-Ling Shih, Kun-Ming Yu, Hwai-San Lin
IEEE TRANSACTIONS ON MULTIMEDIA
(2009)
Article
Computer Science, Information Systems
Chang-Hsing Lee, Sheng-Bin Hsu, Jau-Ling Shih, Chih-Hsun Chou
IEEE TRANSACTIONS ON MULTIMEDIA
(2013)
Article
Engineering, Electrical & Electronic
Chang-Hsing Lee, Pei-Ying Lin, Ling-Hwei Chen, Wei-Kang Wang
JOURNAL OF ELECTRONIC IMAGING
(2012)
Article
Computer Science, Information Systems
Tzu-Hsiang Hsu, Chang-Hsing Lee, Ling-Hwei Chen
MULTIMEDIA TOOLS AND APPLICATIONS
(2011)
Proceedings Paper
Acoustics
Chang-Hsing Lee, Jau-Ling Shih, Chih-Hsun Chou, Kung-Ming Yu, Chuan-Yen Hung
2012 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
(2012)
Article
Computer Science, Artificial Intelligence
Jau-Ling Shih, Chang-Hsing Lee, Chang-Shen Yang
PATTERN RECOGNITION LETTERS
(2007)
Article
Engineering, Electrical & Electronic
Chang-Hsing Lee
IEEE TRANSACTIONS ON COMMUNICATIONS
(2007)
Article
Computer Science, Artificial Intelligence
Chin-Chuan Han, Chang-Hsing Lee, Wen-Li Peng
PATTERN RECOGNITION
(2007)
Article
Computer Science, Information Systems
Cheng-Chang Lien, Chiu-Lung Chiang, Chang-Hsing Lee
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION
(2007)
Article
Computer Science, Artificial Intelligence
CH Lee, CH Chou, CC Han, RZ Huang
PATTERN RECOGNITION LETTERS
(2006)
Article
Computer Science, Artificial Intelligence
Jau-Ling Shih, Chang-Hsing Lee, Jian Tang Wang
PATTERN RECOGNITION
(2007)