检索结果-内蒙古大学图书馆

JIRE-Net: Low-light image enhancement with joint enhancement network of illumination and reflection maps

DIGITAL signal processing 2025年 159卷

作者： Wang, Yan Gao, Guohong Zhao, Chenping Jia, Xixi Wang, Jianping Luo, Shousheng Li, Zhiyu Henan Inst Sci & Technol Sch Comp Sci & Technol Xinxiang 453003 Henan Peoples R China Xidian Univ Sch Math & Stat Xian 710071 Shanxi Peoples R China Zhejiang Normal Univ Coll Math Med Jinhua 321004 Zhejiang Peoples R China

images captured in dark conditions unavoidably suffer from poor visibility issues. Numerous methods addressing these challenges are developed based on the Retinex theory, which decomposes an observed image into illumination and reflection maps, promoting refined processing to enhance image quality. However, most of such methods treat the illumination and reflection components separately, without considering their informational interaction. The proposed method reinforces the collaboration of illumination and reflection with a joint enhancement network named JIRE-Net. We first utilize the powerful feature extraction capability of the convolutional neural network (CNN) to construct a decomposition network. Subsequently, we elaborately designed an Illumination-Driven Transformer-based network structure to reconstruct the normal-light image. Specifically, the Channel Attention Module (IB-CAM) is formulated to promote the features in reflection, which utilize the information of attention weights calculated based on the illumination map. Thereafter, the Illumination-Driven Guidance Block (IDGB) is designed to capture dependencies across input features, cooperatively enhancing the reflection and illumination features. The experimental results on the existing benchmark datasets show that our method obtains better quantitative and qualitative results, achieving a more balanced overall brightness appearance and color quality while preserving finer texture and structural details.

关键词： Low-light image enhancement Retinex theory Deep learning JIRE-Net IB-CAM IDGB

来源：评论

学校读者我要写书评

暂无评论

Scalable Deep Color Quantization: A Cluster Imitation Approach

引用

IEEE TRANSACTIONS ON image processing 2024年 33卷 5273-5283页

作者： Hou, Yunzhong Gould, Stephen Zheng, Liang Australian Natl Univ Sch Comp Canberra ACT 2601 Australia

Color quantization reduces the number of colors used in an image while preserving its content, which is essential in pixel art and knitting art creation. Traditional methods primarily focus on visual fidelity and treat it as a clustering problem in the RGB space. While effective in large (5-6 bits) color spaces, these approaches cannot guarantee semantics in small (1-2 bits) color spaces. On the other hand, deep color quantization methods use network viewers such as AlexNet and ResNet for supervision, effectively preserving semantics in small color spaces. However, in large color spaces, they lag behind traditional methods in terms of visual fidelity. In this work, we propose ColorCNN+, a novel approach that combines the strengths of both. It uses network viewer signals for supervision in small color spaces and learns to cluster the colors in large color spaces. Noteworthily, it is non-trivial for neural networks to do clustering, where existing deep clustering methods often need K-means to cluster the features. In this work, through a newly introduced cluster imitation loss, ColorCNN+ learns to directly output the cluster assignment without any additional steps. Furthermore, ColorCNN+ supports multiple color space sizes and network viewers, offering scalability and easy deployment. Experimental results demonstrate competitive performance of ColorCNN+ across various settings. Code is available at link.

关键词： image color analysis Quantization (signal) Art Visualization Semantics neural networks image resolution Color quantization deep clustering imitation learning AI art creation

来源：评论

学校读者我要写书评

暂无评论

GreenSaliency: A Lightweight and Efficient image Saliency Detection Method

引用

APSIPA TRANSACTIONS ON signal AND INFORMATION processing 2024年第1期13卷

作者： Mei, Zhanxuan Wang, Yun-Cheng Kuo, C. -C. Jay Univ Southern Calif Los Angeles CA 90007 USA

image saliency detection is crucial in understanding human gaze patterns from visual stimuli. The escalating demand for research in image saliency detection is driven by the growing necessity to incorporate such techniques into various computer vision tasks and to understand human visual systems. Many existing image saliency detection methods rely on deep neural networks (DNNs) to achieve good performance. However, the high computational complexity associated with these approaches impedes their integration with other modules or deployment on resource-constrained platforms, such as mobile devices. To address this, we propose a novel image saliency detection method named GreenSaliency, which has a small model size, minimal carbon footprint, and low computational complexity. GreenSaliency can be a competitive alternative to the existing with limited computation resources. GreenSaliency comprises two GreenSaliency achieves comparable performance to the state-ofthe-art DL-based methods while possessing a considerably smaller model size and significantly reduced computational complexity.

关键词： image Saliency Detection Human Gaze Green Learning

来源：评论

学校读者我要写书评

暂无评论

Multi-scale representation for image deraining with state space model

引用

signal image AND VIDEO processing 2025年第1期19卷 1-8页

作者： Li, Yufeng Xie, Chuanlong Chen, Hongming Shenyang Aerosp Univ Coll Elect & Informat Engn Shenyang 110136 Peoples R China Dalian Maritime Univ Coll Informat & Sci Technol Dalian 116026 Peoples R China

With the rapid development of deep learning, significant progress has been made in image deraining techniques, with current methods primarily based on Convolutional neural Network (CNN) and Transformer architectures. However, these approaches often face limitations due to the fixed receptive fields of CNN and the computational complexity of Transformer. Moreover, most existing image deraining methods adopt a single-input single-output network architecture, which struggles with multi-scale feature representation, particularly in capturing both global and local information, leading to potential information loss. To address these issues, this paper proposes a multi-scale visual state space model for image deraining, aiming to improve deraining performance and image restoration quality by combining multi-scale networks with state space model. Specifically, we design a multi-scale Mamba block that models global features with linear computational complexity, and we develop an efficient multi-scale 2D scanning strategy that uses geometric transformations to apply different numbers of scanning directions at various scales, thereby better extracting feature information at each scale. Additionally, we introduce a Frequency Feature Enhancement Module to capture local feature information, and a Gated Feature Fusion Module to adaptively aggregate complementary features across scales, further enhancing image restoration quality and deraining performance. Experimental results demonstrate that our method achieves superior deraining performance on multiple public benchmark datasets, outperforming the current state-of-the-art methods, while significantly improving efficiency and maintaining low computational cost.

关键词： State space model image deraining Multi-scale Mamba Multi-scale 2D scanning

来源：评论

学校读者我要写书评

暂无评论

PMMWDECONV: UNSUPERVISED DATA-CONSISTENT BLIND PASSIVE MILLIMETER-WAVE image DECONVOLUTION WITH GLOBAL CONTEXT PRIORS 49

PMMWDECONV: UNSUPERVISED DATA-CONSISTENT BLIND PASSIVE MILLI...

引用

49th IEEE International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Yang, Hao Gu, Ruochen Yang, Zihan Hu, Anyong Cui, Tie Jun Miao, Jungang Beihang Univ Sch Elect & Informat Engn Beijing Peoples R China Southeast Univ Inst Elect Space & State Key Lab Millimeter Waves Nanjing Peoples R China

ISBN: (纸本)9798350344868;9798350344851

Passive millimeter-wave (PMMW) imaging is extensively employed in public security industries due to its privacy-safe and non-hazardous nature. Nevertheless, the quality of PMMW images is typically poor given blur and noise. Although the end-to-end learning-based image deconvolution methods have demonstrated promising results, they are highly sensitive to minor variations during tests, making them fail to recover small yet crucial details. On the other hand, the blur kernel estimation from textureless PMMW images is also challenging, since the mainstream methods usually adopt convolutional neural networks ( CNNs) with local receptive fields to estimate a blur kernel adapted to the entire image. To this end, we propose a dataset-free method (PMMWDeconv) for blind PMMW image deconvolution by integrating the physical generative model into the deconvolution process. The proposed method mainly contains two subnetworks, kernel generator and image generator, and we leverage data consistency and global context priors to help the network in learning from the blurry PMMW image, where the post-processing and transformer are employed to fulfill these goals. Comprehensive experiments are performed to validate the performance of PMMWDeconv, and the results demonstrate that the proposed method surpasses state-of-the-art methods in both robustness and generalization.

关键词： image deconvolution passive millimeter-wave image neural network deep image prior

来源：评论

学校读者我要写书评

暂无评论

Intelligent identification of bolt looseness with one-dimensional deep convolutional neural networks

引用

signal image AND VIDEO processing 2025年第1期19卷 1-11页

作者： Zhang, Xiaoli Xia, Yong Zhao, Junfeng Changan Univ Minist Educ Key Lab Rd Construct Technol & Equipment Xian 710064 Peoples R China

The bolt connection has characteristics of strong bearing capacity, easy maintenance and replacement, but the bolt connection structure often has loose failures during operation due to the detachability of the bolts. Bolts looseness and connection failure will not only affect the normal use of the mechanism, shorten the service life, and even cause casualties. Online monitoring and evaluation of bolt assembly tightness have attracted numerous interest. Automatic feature extraction plays a crucial role in intelligent state monitoring of mechanical systems, which can adaptively learn features from raw data and discover new state-sensitive features. A one-dimensional deep convolutional neural network (1D-DCNN) with eight convolutional layers and five pooling layers is proposed to achieve high precision in identification of bolt looseness. Firstly, the data overlap sampling is used to obtain the sufficient data so as to satisfy the requirements of 1D-DCNN. Then the 1D-DCNN carries out the process of feature extraction, feature selection and classification, which can take the free vibration signal of the bolt connection structure as input, and then fuse the feature extraction and assembly tightness classification process together to realize the intelligent detection of bolts looseness. The validity of the proposed method is verified by the data acquired from the free vibration excitation experiment of the bolt connection rotor of aero-engine. The results show that the adaptively learned features of the 1D-DCNN can represent the complex mapping relationship between the signal and the assembly state, and achieve higher accuracy than other methods.

关键词： Bolt connection Feature learning Deep convolutional neural networks Data overlap sampling

来源：评论

学校读者我要写书评

暂无评论

The Digital Twin Framework for the Physical Wideband and Long-Haul Optical Fiber Communication Systems

引用

LASER & PHOTONICS REVIEWS 2024年第10期18卷

作者： Yang, Hang Niu, Zekun Fan, Qirui Li, Lyu Shi, Minghui Zeng, Chuyan Xiao, Shilin Hu, Weisheng Yi, Lilin Shanghai Jiao Tong Univ Sch Elect Informat & Elect Engn State Key Lab Adv Opt Commun Syst & Networks Shanghai 200240 Peoples R China Huawei Hong Kong Res Ctr Hong Kong 999077 Peoples R China

Digital twin (DT) modeling is essential to optical fiber communication systems, particularly for enhancing system performance, controlling the system in real time, and understanding signal nonlinearity. Conventional split-step Fourier method -based simulations, however, struggle with wide-band transmissions, plagued by increasing complexity and inherent biases due to inconsistent link parameter availability. Addressing these challenges, a hybrid data-driven and model-driven DT approach for the wide-band and long-haul physical systems with various system effects is developed. The approach utilizes a neural network (NN) to capture fiber nonlinear features as well as biased perturbations as "lumped" stochastic noises while offloading the linear effects to modules described by physical models of link elements. The model, tested in a 30.5-Tbps 1200 km fiber transmission link with 40 channels, achieves a mean Q factor error of less than 0.1 dB and a maximum runtime of 1.3 s for NN processing under various launch powers, transmission lengths, and optical signal-to-noise ratios. Furthermore, the study has implemented a nonlinear compensation algorithm on the DT model, yielding a consistent enhancement in experimental data. The accuracy and adaptability of the DT model underline its suitability for planning, design, and optimization within the physical optical fiber communication systems. Digital twin (DT) is crucial in optical fiber communication. A novel DT incorporates neural networks to model nonlinearities and stochastic noises, while linearities are handled by physical models. This model, validated on a 30.5-Tbps, 1200 km link with 40 channels, achieves a Q factor error of less than 0.1 dB and a maximum runtime of 1.3 s, enhancing system design and optimization. image

关键词： data-driven and model-driven digital twin generative neural networks optical fiber communications

来源：评论

学校读者我要写书评

暂无评论

image interpolation with spiking neural network based pixel similarity

引用

signal image AND VIDEO processing 2024年第10期18卷 6925-6936页

作者： Kilicaslan, Mahmut Ankara Univ Dept Comp Technol Ankara Turkiye

image interpolation is an important topic in the field of image processing. It is defined as the process of transforming low-resolution images into high-resolution ones using image processing methods. Recent studies on interpolation have shown that researchers are focusing on successful interpolation techniques that preserve edge information. Therefore, the edge detection phase plays a vital role in interpolation studies. However, these approaches typically rely on gradient-based linear computations for edge detection. On the other hand, non-linear structures that effectively simulate the human visual system have gained attention. In this study, a non-linear method was developed to detect edge information using a pixel similarity approach. Pixel similarity-based edge detection approach offers both lower computational complexity and more successful interpolation results compared to gradient-based approaches. 1D cubic interpolation was applied to the pixels identified as edges based on pixel similarity, while bicubic interpolation was applied to the remaining pixels. The algorithm was tested on 12 commonly used images and compared with various interpolation techniques. The results were evaluated using metrics such as SSIM and PSNR, as well as visual assessment. The experimental findings clearly demonstrated that the proposed method outperformed other approaches. Additionally, the method offers significant advantages, such as not requiring any parameters and having competitive computational cost.

关键词： Interpolation Pixel similarity Edge preservation

来源：评论

学校读者我要写书评

暂无评论

Enhancement method of low illumination image based on deep neural network integration

Enhancement method of low illumination image based on deep n...

引用

2024 International Conference on image, signal processing, and Pattern Recognition, ISPP 2024

作者： Jun, Liu Shuai, Wang Shaohui, Qu Army Logistics Academy China

ISBN: (纸本)9781510680425

Aiming at the problem that existing low-illumination image enhancement methods cannot simultaneously take into account multiple degrading factors, which leads to poor processing effect when applied to real scenes, deep neural network models facing different image processing tasks are integrated based on neural network integration strategy, and multi-task and multi-stage cascade processing is *** low illumination image can be enhanced under the interference of multiple degrading *** experimental results show that the proposed method can significantly improve the overall brightness and contrast of the image, and the enhanced image has natural colour distribution and good visual effect, which is obviously superior to the existing mainstream low-illumination image enhancement methods. © 2024 SPIE.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

A new multi-scale CNN with pixel-wise attention for image denoising

引用

signal image AND VIDEO processing 2024年第3期18卷 2733-2741页

作者： Deng, Jibin Hu, Chaohua Nanchang Univ Sch Math & Comp Sci Nanchang 330031 Peoples R China Nanchang Univ Sch Informat Engn Nanchang 330031 Peoples R China

Convolutional neural networks (CNNs) are widely popular in the field of image denoising. A large number of CNN-based denoising methods exhibit superior denoising performance in comparison with most conventional denoising schemes. However, some of these approaches extract the noise by stacking many common convolutional layers, which makes them prone to overfitting and causes more loss of image details since the erroneous extraction of non-noise features. A new multi-scale denoising network (MSDNet) is proposed for better tackling these issues, which uses the multi-scale feature information and pixel-wise correlation to effectively remove more noise from noisy images and retain more image details. The denoising effectiveness of MSDNet is specifically attributed to its three key modules, namely multi-scale progressive fusion block (MSPFB), pixel-wise attention block (PWAB) and residual learning (RL), in which MSPFB helps MSDNet capture more useful context information and reduce important information loss caused by ignoring scale inconsistency for capturing more noise from noisy images while maintaining more image details, PWAB facilitates MSDNet to selectively focus on specific image pixels or regions for further effectively capturing noise from noisy images while better preserving image details, and RL is helpful for MSDNet to better address deeper neural network training difficulties and mitigate overfitting. Experimental results demonstrate that MSDNet exhibits superior denoising and single-image deraining performance.

关键词： image denoising Convolutional neural network Multi-scale progressive fusion block Pixel-wise attention block Residual learning Single-image deraining

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：