检索结果-内蒙古大学图书馆

Deep side group sparse coding network for image denoising

IET image processing 2023年第1期17卷 1-11页

作者： Yin, Haitao Wang, Tianyou Nanjing Univ Posts & Telecommun Coll Automat Nanjing 210023 Peoples R China Nanjing Univ Posts & Telecommun Coll Artificial Intelligence Nanjing 210023 Peoples R China

Recently, deep learning has made significant progress in image denoising. However, most of existing deep learning based methods are purely data-driven, without considering the knowledge of image denoising. Moreover, the parameters of deep denoising network are not explainable. According to these issues, this paper proposes a deep side group sparse coding network for image denoising, named a side group sparse coding (SGSC)-Net. First, SGSC model for image denoising by exploiting prior information regarding the group sparse coefficients consistency is developed. Specifically, the side information is constructed as the weighted combination of intermediate estimations, and updated iteratively. Then, the optimisation solution of SGSC model is turned into a deep neural network using deep unfolding, that is, SGSC-Net. The computational path of SGSC-Net fully follows the iterations of optimisation solution, and consequently the network parameters are interpretable. Furthermore, the design of SGSC-Net employs the insight of SGSC denoising model. The experimental results on well-known datasets quantitatively and qualitatively demonstrate that SGSC-Net is competitive to existing deep unfolding-based and typical deep neural network-based methods.

关键词： SGSC-Net image denoising iterative methods side group sparse coding-Net deep learning based methods deep denoising network deep learning (artificial intelligence) neural nets typical deep neural network-based methods Optical, image and video signal processing group sparse coefficients consistency deep side group SGSC model SGSC denoising model Computer vision and image processing techniques

来源：评论

学校读者我要写书评

暂无评论

Classification of diabetic retinopathy based on Functional Linked neural network utilizing segmented fundus image features

引用

BIOMEDICAL signal processing AND CONTROL 2024年第PartA期95卷

作者： Sasikala, D. Kowsalya, T. Padmaloshani, P. Ravindrakumar, S. Muthayammal Engn Coll Dept Biomed Engn Rasipuram Tamil Nadu India Muthayammal Engn Coll Dept Elect & Commun Engn Rasipuram Tamil Nadu India Muthayammal Engn Coll Dept Elect & Commun Engn Rasipuram Tamil Nadu India KIT KalaignarKarunanidhi Inst Technol Dept Biomed Engn Coimbatore India

In this paper, the Classification of Diabetic Retinopathy based on Functional Linked neural Network utilizing Segmented Fundus image Features (CDR-FLNN-SFI) is proposed. The input fundus images are collected utilizing the DIARETDB1dataset. The input image is pre-processed using Federated neural Collaborative Filtering method. In pre-processing phase, the unwanted noises from input pictures are removed. Then, pre-processing output is segmented by using Variational Density Peak Clustering. Functional Linked neural Network (FLNN) is utilized to categorize fundus images into normal, abnormal. The proposed model is implemented on MATLAB2018b. System performance is measured utilizing various metrics including precision, specificity, sensitivity, F1-Score, kappa score, computational time, error rate, accuracy and RoC. The proposed method significantly improves fundus image DR detection performance. The proposed CDR-FLNN-SFI technique attained the greater accuracy of 99.87%, precision of 98.34%, F1-Score of 97.41%. The proposed approach intends to decrease computational time and increase accuracy. In fact, presentation of proposed approach associated additional existing methods utilizing DIARETDB1dataset. The performance of the proposed CDR-FLNN-SFI is evaluated to the existing techniques like deep learning manner based on segmented fundus image features organization of diabetic retinopathy (DLA-SFI-CDR), Fundus image lesion finding process for diabetic retinopathy screening (FILDA-DRS), improved swarm optimization-based deep neural network for diabetic retinopathy organization fundus pictures (ESO-DNN-CDR) respectively.

关键词： Federated neural Collaborative Filtering Functional Linked neural Network Improved Black Hole optimization algorithm Variational Density Peak Clustering MATLAB

来源：评论

学校读者我要写书评

暂无评论

Dual-Branch Network for No-Reference Super-Resolution image Quality Assessment

引用

IEEE signal processing LETTERS 2025年 32卷 1366-1370页

作者： Tang, Tong Yang, Fan Lin, Xinyu Li, Weisheng Chongqing Univ Posts & Telecommun Sch Comp Sci & Technol Chongqing 400065 Peoples R China Chongqing Univ Posts & Telecommun Sch Commun & Informat Engn Chongqing 400065 Peoples R China

No-reference super-resolution image quality assessment (SR-IQA) has become an critical technique for optimizing SR algorithms, the key challenge is how to comprehensively learn visual related features of SR image. Existing methods ignore the context information and feature correlation. To tackle this problem, this letter proposes a dual-branch network for no-reference super-resolution image quality assessment (DBSRNet). First, dual-branch feature extraction module is designed, where residual network and receptive field block net are combined to learn multi-scale local features, stacked vision transformer blocks are utilized to learn global features. Then, correlations between dual-branch features are learned and fused based on self-attention mechanism structure, final predicted score is obtained by adaptive feature pooling strategy. Finally, experimental results show that DBSRNet significantly outperforms State-of-the-Art methods in terms of prediction accuracy on all SR-IQA datasets.

关键词： Feature extraction Correlation Convolutional neural networks Accuracy Residual neural networks Training image quality Superresolution Predictive models neural networks image quality assessment super resolution feature correlation

来源：评论

学校读者我要写书评

暂无评论

A Compound Gaussian Least Squares Algorithm and Unrolled Network for Linear Inverse Problems

引用

IEEE TRANSACTIONS ON signal processing 2023年 71卷 4303-4316页

作者： Lyons, Carter Raj, Raghu G. Cheney, Margaret US Naval Res Lab Washington DC 20375 USA Colorado State Univ Ft Collins CO 80523 USA

For solving linear inverse problems, particularly of the type that appears in tomographic imaging and compressive sensing, this paper develops two new approaches. The first approach is an iterative algorithm that minimizes a regularized least squares objective function where the regularization is based on a compound Gaussian prior distribution. The compound Gaussian prior subsumes many of the commonly used priors in image reconstruction, including those of sparsity-based approaches. The developed iterative algorithm gives rise to the paper's second new approach, which is a deep neural network that corresponds to an "unrolling" or "unfolding" of the iterative algorithm. Unrolled deep neural networks have interpretable layers and outperform standard deep learning methods. This paper includes a detailed computational theory that provides insight into the construction and performance of both algorithms. The conclusion is that both algorithms outperform other state-of-the-art approaches to tomographic image formation and compressive sensing, especially in the difficult regime of low training.

关键词： Artificial neural networks Training Tomography signal reconstruction signal processing algorithms Imaging Compounds Machine learning neural networks inverse problems nonlinear programming least squares methods

来源：评论

学校读者我要写书评

暂无评论

Fast single-image denoising through self-observation

引用

JOURNAL OF ELECTRONIC IMAGING 2025年第2期34卷

作者： Zhang, Derui Bian, He Wang, Hao Zhao, Qing Liao, Jiawen Chinese Acad Sci Xian Inst Opt & Precis Mech Xian Peoples R China Xi An Jiao Tong Univ Sch Elect & Informat Engn Xian Peoples R China Univ Chinese Acad Sci Beijing Peoples R China

Self-supervised neural networks have demonstrated remarkable performance in image-denoising applications. However, existing dataset-free methods have limitations, including their high computational overhead, noise model requirements, and compromised image quality. To address these problems, we proposed a dataset-free method for image denoising using a single noisy image. The proposed method uses a lightweight neural network with slightly more than 3000 parameters to achieve effective denoising. Inspired by the Zero-Shot Noise2Noise framework, we downsampled noisy images and employed downscaled nonfused images for training, achieving denoising by cross-mapping the denoised subimages with the original noisy subimages. To further reduce the high-frequency noise, we employed cross-mapping among the denoised subimages. The numerical results demonstrated the superior performance of the proposed algorithm compared with other dataset-free neural network algorithms. The proposed method exhibited a shorter processing time and fewer network parameters yet yielded denoised images with a higher signal-to-noise ratio. Moreover, it demonstrated superior performance and processing speed in both synthetic and actual noise experiments, making it suitable for practical applications.

关键词： dataset-free method downsampling image denoising self-supervised neural network

来源：评论

学校读者我要写书评

暂无评论

Application of image Big Data in the Ecological Agricultural Product Supply Chain

引用

TRAITEMENT DU signal 2025年第1期42卷 333-341页

作者： Zhang, Ruixue Dalian Minzu Univ Sch Econ & Management Dalian 116600 Peoples R China

With the rapid development of ecological agriculture and the increasing demand for agricultural product supply chain management, effectively monitoring the quality and circulation status of agricultural products has become an urgent issue. image big data technologies, particularly advancements in deep learning and computer vision, offer innovative solutions for surface quality detection, analysis, and traceability of agricultural products. By precisely estimating surface disparity and analyzing quality, these technologies not only improve the efficiency of quality control but also enhance supply chain transparency, ensuring the stability of product quality. However, existing image analysis methods face significant limitations when dealing with minor surface defects, lighting variations, and complex textures. Traditional image processing techniques are less effective in these areas, and the application of deep learning is still in the exploratory phase. To address these issues, this study proposes a deep learning-based method for surface disparity estimation of agricultural products and designs three innovative models: 1) a Convolutional neural Network (CNN) for surface disparity estimation of agricultural products, 2) an end- to-end deep learning stereo matching model for surface disparity estimation, and 3) a deep learning pyramid stereo matching network model for surface disparity estimation of agricultural products. These models aim to overcome the shortcomings of current methods and enhance the precision and stability of agricultural product image analysis, providing more efficient and intelligent technical means for quality control in the agricultural product supply chain.

关键词： ecological agricultural products image big data deep learning surface disparity estimation convolutional neural network (CNN) stereo matching supply chain management

来源：评论

学校读者我要写书评

暂无评论

FPNIE: a fast pure nighttime image enhancement method

引用

signal image AND VIDEO processing 2025年第1期19卷 1-12页

作者： Xiao, Xianghui Song, Yunhao Guan, Luchang Zeng, Junbing Foshan Univ Sch Mechatron Engn & Automat Foshan 528225 Guangdong Peoples R China Hunan Univ Coll Elect & Informat Engn Changsha 410082 Hunan Peoples R China

To achieve a visually captivating nocturnal image that closely resembles its natural daytime counterpart, people employ a range of techniques to process the nighttime image. The primary focus lies in achieving rapid and stable unsupervised image enhancement effects specifically tailored for nocturnal scenes, without relying on daytime contrast image. However, existing neural network-based methods for enhancing nighttime image often rely on supervised paired training data, which presents challenges in practical production scenarios. The acquisition of image pairs depicting the same scene and the creation of a large-scale, feature-rich training dataset pose significant difficulties. In this study, we propose a fast pure nighttime image enhancement technique based on preprocessing inspired by the varying light sensitivity exhibited by fish during night fishing. The sensitivity of fish to light varies at different depths, analogous to the concealed richness of effective information within seemingly dark nighttime image, which can be effectively and comprehensively unveiled through preprocessing techniques. Subsequently, we employ an improved dual logarithmic image processing method based on type-II fuzzy sets to fuse the layer information obtained from preprocessing, resulting in enhanced contrast, noise reduction, color enhancement, and improved illumination with superior quality. The extensive experimental and comparative results demonstrate that our method's robust enhancement and restoration capabilities surpass even those of state-of-the-art supervised methods.

关键词： Nighttime image enhancement Preprocessing Dual LIP Fast and pure

来源：评论

学校读者我要写书评

暂无评论

Modulation recognition of underwater acoustic communication signals based on neural architecture search

引用

APPLIED ACOUSTICS 2024年 225卷

作者： Jiang, Zhe Zhang, Jingbo Wang, Tianxing Wang, Haiyan Northwestern Polytech Univ Sch Marine Sci & Technol Xian Peoples R China

Modulation recognition of underwater communication signals is a critical aspect of underwater information confrontation. However, the current deep learning-based methods for underwater communication modulation recognition often mimic neural network architectures used in image processing and speech processing, tending to perform poorly in low signal-to-noise ratio (SNR) conditions. This paper introduces a novel approach by utilizing neural architecture search (NAS) method. By automatically searching for neural architectures that are wellsuited for modulation recognition in underwater environment, our proposed method improves the classification performance particularly in low SNR conditions. Furthermore, we have also proposed a recognition method based on attention mechanism and feature fusion, which substantially enhances the accuracy of identifying phasemodulated signals. Numerical simulation and experimental data are used to demonstrate performance of proposed methods.

关键词： Underwater communication modulation classification neural architecture search Attention mechanism Feature fusion

来源：评论

学校读者我要写书评

暂无评论

Spike Camera image Reconstruction Using Deep Spiking neural Networks

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2024年第6期34卷 5207-5212页

作者： Zhao, Rui Xiong, Ruiqin Zhang, Jian Yu, Zhaofei Zhu, Shuyuan Ma, Lei Huang, Tiejun Peking Univ Natl Engn Res Ctr Visual Technol Sch Comp Sci Beijing 100871 Peoples R China Peking Univ Shenzhen Grad Sch Sch Elect & Comp Engn Shenzhen 518055 Peoples R China Univ Elect Sci & Technol China Sch Informat & Commun Engn Chengdu 611731 Peoples R China

Spike camera is a bio-inspired sensor with ultra-high temporal resolution and low energy consumption. It captures visual signals using an "integrate-and-fire" mechanism and outputs a continuous stream of binary spikes. Reconstructing image sequence from spikes streams is critical for spike camera. Several reconstruction methods have been proposed in recent years. However, the computational cost of these methods is relatively high. Inspired by the fact that spiking neural networks (SNNs) are energy efficient and support time-series signal processing inherently, we propose a lightweight SNN for spike camera image reconstruction (abbreviated to SSIR). Experimental results show that SSIR achieves comparable performance with the state-of-the-art (SOTA) methods at much lower computation and energy cost.

关键词： Cameras image reconstruction Neurons Feature extraction Convolution Training Streaming media Spike camera image reconstruction spiking neural networks

来源：评论

学校读者我要写书评

暂无评论

MulitDeepsurv: survival analysis of gastric cancer based on deep learning multimodal fusion models

引用

BIOMEDICAL OPTICS EXPRESS 2025年第1期16卷 126-141页

作者： Mao, Songren Liu, Jie Taiyuan Normal Univ Coll Comp Sci & Technol Jinzhong 030619 Peoples R China Taiyuan Inst Technol Comp Engn Dept Taiyuan 030008 Peoples R China

Gastric cancer is a leading cause of cancer-related deaths globally. As mortality rates continue to rise, predicting cancer survival using multimodal data-including histopathological images, genomic data, and clinical information-has become increasingly crucial. However, extracting effective predictive features from this complex data has posed challenges for survival analysis due to the high dimensionality and heterogeneity of histopathology images and genomic data. Furthermore, existing methods often lack sufficient interaction between intra- and inter- modal features, significantly impacting model performance. To address these challenges, we developed a deep learning-based multimodal feature fusion model, MultiDeepsurv, designed to predict the survival of gastric cancer patients by integrating histopathological images, clinical data, and gene expression data. Our approach includes a two-branch hybrid network, GLFUnet, which leverages the attention mechanism for enhanced pathology image representation learning. Additionally, we employ a graph convolutional neural network (GCN) to extract features from gene expression data and clinical information. To capture the correlations between different modalities, we utilize the SFusion fusion strategy that employs a self-attention mechanism to learn potential correlations across modalities. Finally, these deeply processed features are fed into Cox regression models for an end-to-end survival analysis. Comprehensive experiments and analyses conducted on a gastric cancer cohort from The Cancer Genome Atlas (TCGA) demonstrate that our proposed MultiDeepsurv model outperforms other methods in terms of prognostic accuracy, with a C-index of 0.806 and an AUC of 0.842. (c) 2024 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement

关键词： Deep learning image enhancement Machine learning neural networks Spatial filtering stochastic gradient descent

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：