Article
Computer Science, Software Engineering
Chunxue Wang, Huayan Zhang, Ligang Liu
Summary: This paper introduces a reflectance and illumination decomposition model for the Retinex problem using total generalized variation regularization and H1 decomposition. Experimental results show that the proposed model is comparable both quantitatively and qualitatively with several state-of-the-art methods.
Article
Mathematics, Applied
Myeongmin Kang, Miyoun Jung
Summary: This article proposes a novel variational model for enhancing and restoring low-light images corrupted by blurring and/or noise, through decomposing and recovering reflectance and illumination images to achieve denoising while preserving details and edges, resulting in clean and sharp final images; Non-convex total variation regularization, proximal alternating minimization, iteratively reweighted l1 algorithm, and alternating direction method of multipliers are utilized to efficiently solve the non-convex model and prove its convergence; Experimental results demonstrate the effectiveness of the proposed model in terms of both visual aspect and image quality measures compared to other state-of-the-art methods.
JOURNAL OF SCIENTIFIC COMPUTING
(2021)
Article
Computer Science, Artificial Intelligence
Xueyan Ding, Yafei Wang, Zheng Liang, Xianping Fu
Summary: This study proposes a unified total variation method based on an extended underwater imaging model, aiming to achieve good performance in underwater image enhancement by eliminating the dual-path light attenuation in underwater images.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Limei Huo, Wengu Chen, Huanmin Ge, Michael K. Ng
Summary: This paper introduces a transformed total variation (TTV) minimization model to investigate robust image recovery from a certain number of noisy measurements. Numerical results demonstrate the effectiveness of the TTV minimization model in image reconstruction.
SIAM JOURNAL ON IMAGING SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Tao Sun, Dongsheng Li
Summary: Total Variation and Low-Rank regularizations have achieved significant success in the fields of machine learning, data mining, and image processing. This paper introduces a general nonconvex composite regularized model and proposes an Alternating Minimization algorithm to solve the optimization problem. Numerical results demonstrate the efficiency of the proposed model and algorithm.
PATTERN RECOGNITION
(2022)
Article
Geochemistry & Geophysics
Jingyu Wang, Pengfei Huang, Ke Zhang, Qi Wang
Summary: Anomaly detection on hyperspectral images has been extensively studied in recent decades, with most methods focusing on spectral information and neglecting spatial characteristics. This letter proposes a new method that combines spectral-spatial total variation regularization with low-rank matrix decomposition to maximize the utilization of spatial characteristics, achieving excellent performance on real datasets.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Computer Science, Information Systems
Norisato Suga, Ryohei Sasaki, Makoto Osawa, Toshihiro Furukawa
Summary: This letter presents a ray tracing acceleration method based on the TVNM scheme for radio map interpolation, which achieves better accuracy and considers known position selection for further enhancement. Computational simulations using commercial RT software show that the proposed method outperforms other interpolation methods with acceptable interpolation error in accelerating RT simulations.
IEEE WIRELESS COMMUNICATIONS LETTERS
(2021)
Article
Computer Science, Software Engineering
Chunxue Wang, Linlin Xu, Ligang Liu
Summary: This paper proposes a novel image decomposition model for various image processing applications such as compression, enhancement, and texture removal. The model utilizes non-convex regularization and convolutional sparse coding to accurately decompose images into structure and texture components. It also incorporates structure-aware and texture-aware measures to effectively distinguish between these components.
Article
Engineering, Electrical & Electronic
Deng Jiawei, Yu Zhenming, Pang Guangyao
Summary: This paper proposes a colour variation minimization retinex decomposition and enhancement with a multi-branch decomposition network to remove single image darkness. The method includes image decomposition and brightness optimization stages, as well as a reflection constant feature mechanism and a multi-branch decomposition network to address color distortion and noise amplification. Experimental results on benchmark datasets and real Skynet images demonstrate the effectiveness of the proposed approach in balancing noise interference and color restoration.
CHINESE JOURNAL OF ELECTRONICS
(2023)
Article
Optics
Uche A. Nnolim
Summary: This paper introduces a variational and partial differential equation-based approach for enhancing degraded document images, mitigating stain and uneven illumination degradation, and restoring faint text intensity and edges using augmented Homomorphic L1 Total Variation estimation and a fourth order forward-backward Diffusion-Laplacian contrast enhancement PDE. Pre-smoothing is also used for document images with extensive bleedthrough effects. Comparisons with existing methods demonstrate improved/superior binarization results based on subjective and objective analysis.
Article
Geochemistry & Geophysics
Minghua Wang, Qiang Wang, Jocelyn Chanussot, Dan Li
Summary: This study introduces a novel approach for removing mixed noise from hyperspectral images using a multidirectional low-rank modeling and spatial-spectral total variation model. By combining weighted nuclear norm and SSTV regularization, it can estimate LR tensor more accurately and effectively remove noise.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2021)
Article
Computer Science, Information Systems
Rui Shi, Honglong Zheng, Xianguo Tuo, Changming Wang, Jianbo Yang, Yi Cheng, Mingzhe Liu, Songbai Zhang
Summary: Tomographic Gamma Scanning (TGS) is a crucial non-destructive technique for analyzing radioactive waste drums. By applying the TVM method, the MLEM-TVM and ART-TVM reconstruction methods show improved accuracy and signal-to-noise ratio compared to traditional algorithms, with MLEM-TVM achieving the best results in image quality. The TVM method not only enhances the TGS image resolution but also saves scanning time through sparse projection sampling.
Article
Environmental Sciences
Pengdan Zhang, Jifeng Ning
Summary: This paper proposes a new hyperspectral image (HSI) denoising model, GHSSTV, which combines group sparsity regularized hybrid spatio-spectral total variation (GHSSTV) and low-rank tensor decomposition. Experimental results demonstrate the superior performance of the GHSSTV method in HSI denoising.
Article
Multidisciplinary Sciences
Yaoling Zhou, Yueer Sun, Mu Yang, Junzhao Hou, Zhaolin Xiao, Asundi Anand, Liansheng Sui
Summary: An optical multiple-image authentication method is proposed using computational ghost imaging and total-variation minimization. It embeds encoded information into a cover image to avoid eavesdroppers' attention. The proposed approach allows for the direct recovery of original high-quality images using total-variation minimization and is validated through optical experiments.
Article
Computer Science, Information Systems
Yonglong Jiang, Liangliang Li, Jiahe Zhu, Yuan Xue, Hongbing Ma
Summary: In this paper, a novel convolutional neural network named DEANet is proposed for low-light image enhancement based on Retinex. DEANet combines the frequency and content information of images and is divided into three subnetworks: decomposition, enhancement, and adjustment networks, which perform image decomposition; denoising, contrast enhancement, and detail preservation; and image adjustment and generation, respectively. The model is trained on the public LOL dataset, and the experimental results show that it outperforms the existing state-of-the-art methods regarding visual effects and image quality.
TSINGHUA SCIENCE AND TECHNOLOGY
(2023)
Article
Computer Science, Information Systems
Jinjoo Song, Gangjoon Yoon, Heeryon Cho, Sang Min Yoon
MULTIMEDIA TOOLS AND APPLICATIONS
(2018)
Article
Chemistry, Analytical
Heeryon Cho, Sang Min Yoon
Article
Engineering, Electrical & Electronic
H. Cho, S. M. Yoon
ELECTRONICS LETTERS
(2019)
Article
Computer Science, Artificial Intelligence
Jinjoo Song, Gangjoon Yoon, Kwangsoo Hahn, Sang Min Yoon
Article
Computer Science, Information Systems
Jungwoo Choi, Heeryon Cho, Jinjoo Song, Sang Min Yoon
IEEE TRANSACTIONS ON MULTIMEDIA
(2019)
Article
Computer Science, Artificial Intelligence
Jinjoo Song, Gangjoon Yoon, Sang Min Yoon
Article
Computer Science, Information Systems
Hwanbok Mun, Gang-Joon Yoon, Jinjoo Song, Sang Min Yoon
Summary: This paper introduces a texture preserving photo style transfer algorithm that effectively changes the style characteristics of the structure by separating the input image into texture and structure. The proposed method overcomes the main drawback of previous approaches and shows universality compared to remarkable previous methods.
IEEE TRANSACTIONS ON MULTIMEDIA
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Song-Mi Lee, Heeryon Cho, Sang Min Yoon
2017 IEEE INTERNATIONAL CONFERENCE ON MULTISENSOR FUSION AND INTEGRATION FOR INTELLIGENT SYSTEMS (MFI)
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Heeryon Cho, Sang Min Yoon
2017 10TH INTERNATIONAL CONFERENCE ON HUMAN SYSTEM INTERACTIONS (HSI)
(2017)
Proceedings Paper
Computer Science, Interdisciplinary Applications
Heeryon Cho, Sang Min Yoon
2017 INTERNATIONAL CONFERENCE ON CULTURE AND COMPUTING (CULTURE AND COMPUTING)
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Jinjoo Song, Heeryon Cho, Sang Min Yoon
INTELLIGENT INFORMATION AND DATABASE SYSTEMS, ACIIDS 2017, PT I
(2017)
Proceedings Paper
Computer Science, Theory & Methods
Song-Mi Lee, Sang Min Yoon, Heeryon Cho
2017 IEEE INTERNATIONAL CONFERENCE ON BIG DATA AND SMART COMPUTING (BIGCOMP)
(2017)