检索结果-内蒙古大学图书馆

convolutional sparse Modular Fusion Algorithm for Non-Rigid Registration of Visible-Infrared Images

APPLIED SCIENCES-BASEL 2025年第5期15卷 2508-2508页

作者： Luo, Tao Chen, Ning Zhu, Xianyou Yi, Heyuan Duan, Weiwen Zhejiang Univ Sci & Technol Sch Mech & Energy Engn Hangzhou 310023 Peoples R China

Existing image fusion algorithms involve extensive models and high computational demands when processing source images that require non-rigid registration, which may not align with the practical needs of engineering applications. To tackle this challenge, this study proposes a comprehensive framework for convolutional sparse fusion in the context of non-rigid registration of visible-infrared images. Our approach begins with an attention-based convolutional sparse encoder to extract cross-modal feature encodings from source images. To enhance feature extraction, we introduce a feature-guided loss and an information entropy loss to guide the extraction of homogeneous and isolated features, resulting in a feature decomposition network. Next, we create a registration module that estimates the registration parameters based on homogeneous feature pairs. Finally, we develop an image fusion module by applying homogeneous and isolated feature filtering to the feature groups, resulting in high-quality fused images with maximized information retention. Experimental results on multiple datasets indicate that, compared with similar studies, the proposed algorithm achieves an average improvement of 8.3% in image registration and 30.6% in fusion performance in mutual information. In addition, in downstream target recognition tasks, the fusion images generated by the proposed algorithm show a maximum improvement of 20.1% in average relative accuracy compared with the original images. Importantly, our algorithm maintains a relatively lightweight computational and parameter load.

关键词： multimodal image fusion convolutional sparse coding image registration feature extraction

来源：评论

学校读者我要写书评

暂无评论

Discriminative convolution sparse coding for robust image classification

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2022年第28期81卷 40849-40870页

作者： Nozaripour, Ali Soltanizadeh, Hadi Semnan Univ Dept Elect Comp Engn Semnan *** Iran Semnan Univ Fac Elect Comp Engn Semnan *** Iran

convolutional sparse coding (CSC) is a popular model in the signal and image processing communities, resolving some limitations of the traditional patch-based sparse representations. However, most existing CSC algorithms are suited for image restoration. Also, in some CSC-based classification methods, the CSC model is only used as a feature extractor and so other classifiers are needed for classification. In this paper, we present a novel discriminative model based on CSC for image classification. The proposed method, discriminative local block coordinate descent (D-LoBCoD), is based on extending the LoBCoD algorithm by incorporating the classification error into the objective function that considers the performance of a linear classifier and the representational power of the filters, simultaneously. Thus, in the training phase, in each iteration, after updating the sparse coefficients and convolutional filters, we minimize the classification error by updating the parameters of the classifier according to the class label information of the training samples. Also, in the test phase, the label of the query image is determined by the trained classifier. To demonstrate the performance of the proposed method, we conduct extensive experiments on image data sets in comparison with state-of-the-art classification methods. The experimental results show that our method outperforms other competing methods in most cases. Further, we demonstrate that our proposed method is less dependent on the number of training samples because of capturing more representative information from the corresponding images. Thus our proposed method can work better than other methods on all small databases that have fewer samples.

关键词： convolutional sparse coding sparse representation Classification Dictionary learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Approximate Online convolutional Dictionary Learning

IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING

引用

IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING 2023年 9卷 1165-1175页

作者： Veshki, Farshad G. Vorobyov, Sergiy A. Aalto Univ Dept Informat & Commun Engn Espoo 02150 Finland Nokia Espoo 11351 Finland

Most existing convolutional dictionary learning (CDL) algorithms are based on batch learning, where the dictionary filters and the convolutional sparse representations are optimized in an alternating manner using a training dataset. When large training datasets are used, batch CDL algorithms become prohibitively memory-intensive. An online-learning technique is used to reduce the memory requirements of CDL by optimizing the dictionary incrementally after finding the sparse representations of each training sample. Nevertheless, learning large dictionaries using the existing online CDL (OCDL) algorithms remains highly computationally expensive. In this paper, we present a novel approximate OCDL method that incorporates sparse decomposition of the training samples. The resulting optimization problems are addressed using the alternating direction method of multipliers. Extensive experimental evaluations using several image datasets and based on an image fusion task show that the proposed method substantially reduces computational costs while preserving the effectiveness of the state-of-the-art OCDL algorithms.

关键词： Training Dictionaries convolutional codes Convolution Memory management Optimization Machine learning convolutional sparse coding online convolutional dictionary learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal convolutional Dictionary Learning

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2022年 31卷 1325-1339页

作者： Gao, Fangyuan Deng, Xin Xu, Mai Xu, Jingyi Dragotti, Pier Luigi Beihang Univ Sch Cyber Sci & Technol Beijing 100191 Peoples R China Beihang Univ Dept Elect Informat Engn Beijing 100191 Peoples R China Imperial Coll London Dept Elect & Elect Engn London SW7 2AZ England

convolutional dictionary learning has become increasingly popular in signal and image processing for its ability to overcome the limitations of traditional patch-based dictionary learning. Although most studies on convolutional dictionary learning mainly focus on the unimodal case, real-world image processing tasks usually involve images from multiple modalities, e.g., visible and near-infrared (NIR) images. Thus, it is necessary to explore convolutional dictionary learning across different modalities. In this paper, we propose a novel multi-modal convolutional dictionary learning algorithm, which efficiently correlates different image modalities and fully considers neighborhood information at the image level. In this model, each modality is represented by two convolutional dictionaries, in which one dictionary is for common feature representation and the other is for unique feature representation. The model is constrained by the requirement that the convolutional sparse representations (CSRs) for the common features should be the same across different modalities, considering that these images are captured from the same scene. We propose a new training method based on the alternating direction method of multipliers (ADMM) to alternatively learn the common and unique dictionaries in the discrete Fourier transform (DFT) domain. We show that our model converges in less than 20 iterations between the convolutional dictionary updating and the CSRs calculation. The effectiveness of the proposed dictionary learning algorithm is demonstrated on various multimodal image processing tasks, achieves better performance than both dictionary learning methods and deep learning based methods with limited training data.

关键词： Dictionaries Training Memory management Noise level Toy manufacturing industry Standards Paints Multi-modal dictionary learning convolutional sparse coding image denoising

来源：评论

学校读者我要写书评

暂无评论

A two-stage convolutional sparse prior model for image restoration

引用

JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION 2017年第Oct.期48卷 268-280页

作者： Xiong, Jiaojiao Liu, Qiegen Wang, Yuhao Xu, Xiaoling Nanchang Univ Dept Elect Informat Engn Nanchang Jiangxi Peoples R China

Image restoration (IR) from noisy, blurred or/and incomplete observed measurement is one of the important tasks in image processing community. Image prior is of utmost importance for recovering a high quality image. In this paper, we present a two-stage convolutional sparse prior model for efficient image restoration. The multi-view features prior is first obtained by convolving the image with the Fields-of Experts (FoE) filters and then the resulting multi-view features are represented by convolutional sparse coding (CSC) prior. By taking advantage of the convolutional filters, the proposed two-stage model inherits the strengths of multi-view features and CSC priors. The assembled multi-view features contain high frequency, redundancy, and large range of feature orientations, which are favor to be represented by CSC and consequently for better image recovery. Augmented Lagrangian and alternating direction method of multipliers are employed to decouple the nonlinear optimization problem in order to iteratively approach the optimum solution. The results of various experiments on image deblurring and compressed sensing magnetic resonance imaging (CS-MRI) reconstruction consistently demonstrate that the proposed algorithm efficiently recovers image and presents advantages over the current leading restoration approaches. (C) 2017 Elsevier Inc. All rights reserved.

关键词： Image deblurring CS-MRI Fields-of-Experts convolutional sparse coding Multi-view features prior Alternating direction method of multipliers

来源：评论

学校读者我要写书评

暂无评论

Tensor convolutional Dictionary Learning With CP Low-Rank Activations

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2022年 70卷 785-796页

作者： Humbert, Pierre Oudre, Laurent Vayatis, Nicolas Audiffren, Julien Univ Paris Saclay ENS Paris Saclay CNRS Ctr Borelli F-91190 Gif Sur Yvette France Univ Fribourg Cognit & Percept Lab CH-1700 Fribourg Switzerland

In this paper, we propose to extend the standard convolutional Dictionary Learning problem to a tensor representation where the activations are constrained to be "low-rank" through a Canonical Polyadic decomposition. We show that this additional constraint increases the robustness of the CDL with respect to noise and improve the interpretability of the final results. In addition, we discuss in detail the advantages of this representation and introduce two algorithms, based on ADMM or FISTA, that efficiently solve this problem. We show that by exploiting the low rank property of activations, they achieve lower complexity than the main CDL algorithms. Finally, we evaluate our approach on a wide range of experiments, highlighting the modularity and the advantages of this tensorial low-rank formulation.

关键词： Tensors Convolution convolutional codes Machine learning Signal processing algorithms Convergence Mathematical models convolutional dictionary learning convolutional sparse coding tensor canonical polyadic decomposition

来源：评论

学校读者我要写书评

暂无评论

LidarCSNet: A Deep convolutional Compressive Sensing Reconstruction Framework for 3D Airborne Lidar Point Cloud

引用

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING 2021年 180卷 313-334页

作者： Shinde, Rajat C. Durbha, Surya S. Potnis, Abhishek, V Indian Inst Technol Ctr Studies Resources Engn CSRE Mumbai Maharashtra India

Lidar scanning is a widely used surveying and mapping technique ranging across remote-sensing applications involving topological, and topographical information. Typically, lidar point clouds, unlike images, lack inherent consistent structure and store redundant information thus requiring huge processing time. The Compressive Sensing (CS) framework leverages this property to generate sparse representations and accurately reconstructs the signals from very few linear, non-adaptive measurements. The reconstruction is based on valid assumptions on the following parameters- (1) sampling function governed by sampling ratio for generating samples, and (2) measurement function for sparsely representing the data in a low-dimensional subspace. In our work, we address the following motivating scientific questions- Is it possible to reconstruct dense point cloud data from a few sparse measurements? And, what could be the optimal limit for CS sampling ratio with respect to overall classification metrics? Our work proposes a novel convolutional Neural Network based deep Compressive Sensing Network (named LidarCSNet) for generating sparse representations using publicly available 3D lidar point clouds of the Philippines. We have performed extensive evaluations for analysing the reconstruction for different sampling ratios {4%, 10%, 25%, 50% and 75%} and we observed that our proposed LidarCSNet reconstructed the 3D lidar point cloud with a maximum PSNR of 54.47 dB for a sampling ratio of 75%. We investigate the efficacy of our novel LidarCSNet framework with 3D airborne lidar point clouds for two domains - forests and urban environment on the basis of Peak Signal to Noise Ratio, Haussdorf distance, Pearson Correlation Coefficient and Kolmogorov-Smirnov Test Statistic as evaluation metrics for 3D reconstruction. The results relevant to forests such as Canopy Height Model and 2D vertical profile are compared with the ground truth to investigate the robustness of the LidarCSNet framewo

关键词： Compressive sensing Deep learning for point cloud classification 3D airborne lidar point cloud Deep network-based optimization Lidar for forests Urban environment convolutional sparse coding Ensemble deep learning

来源：评论

学校读者我要写书评

暂无评论

Generation model meets swin transformer for unsupervised low-dose CT reconstruction

引用

MACHINE LEARNING-SCIENCE AND TECHNOLOGY 2024年第2期5卷 025005页

作者： Li, Yu Sun, Xueqin Wang, Sukai Qin, Yingwei Pan, Jinxiao Chen, Ping North Univ China Dept Informat & Commun Engn Taiyuan Peoples R China North Univ China State Key Lab Elect Testing Technol Taiyuan Peoples R China

Computed tomography (CT) has evolved into an indispensable tool for clinical diagnosis. Reducing radiation dose crucially minimizes adverse effects but may introduce noise and artifacts in reconstructed images, affecting diagnostic processes for physicians. Scholars have tackled deep learning training instability by exploring diffusion models. Given the scarcity of clinical data, we propose the unsupervised image domain score generation model (UISG) for low-dose CT reconstruction. During training, normal-dose CT images are utilized as network inputs to train a score-based generative model that captures the prior distribution of CT images. In the iterative reconstruction, the initial CT image is obtained using a filtered back-projection algorithm. Subsequently, diffusion-based prior, high-frequency convolutional sparse coding prior, and data-consistency steps are employed to obtain the high-quality reconstructed image. Given the global characteristics of noise, the score network of the diffusion model utilizes a swin transformer structure to enhance the model's ability to capture long-range dependencies. Furthermore, convolutional sparse coding is applied exclusively to the high-frequency components of the image, to prevent over-smoothing or the loss of crucial anatomical details during the denoising process. Quantitative and qualitative results indicate that UISG outperforms competing methods in terms of denoising and generalization performance.

关键词： low-dose CT score-based diffusion model swin transformer convolutional sparse coding data consistency

来源：评论

学校读者我要写书评

暂无评论

Multilayer convolutional sparse Modeling: Pursuit and Dictionary Learning

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2018年第15期66卷 4090-4104页

作者： Sulam, Jeremias Papyan, Vardan Romano, Yaniv Elad, Michael Technion Israel Inst Technol Dept Comp Sci IL-3200003 Haifa Israel Stanford Univ Dept Stat Stanford CA 94305 USA

The recently proposed multilayer convolutional sparse coding (ML-CSC) model, consisting of a cascade of convolutional sparse layers, provides a new interpretation of convolutional neural networks (CNNs). Under this framework, the forward pass in a CNN is equivalent to a pursuit algorithm aiming to estimate the nested sparse representation vectors from a given input signal. Despite having served as a pivotal connection between CNNs and sparse modeling, a deeper understanding of the ML-CSC is still lacking. In this paper, we propose a sound pursuit algorithm for the ML-CSC model by adopting a projection approach. We provide new and improved bounds on the stability of the solution of such pursuit and we analyze different practical alternatives to implement this in practice. We show that the training of the filters is essential to allow for nontrivial signals in the model, and we derive an online algorithm to learn the dictionaries from real data, effectively resulting in cascaded sparse convolutional layers. Last, but not least, we demonstrate the applicability of the ML-CSC model for several applications in an unsupervised setting, providing competitive results. Our work represents a bridge between matrix factorization, sparse dictionary learning, and sparse autoencoders, and we analyze these connections in detail.

关键词： convolutional sparse coding multilayer pursuit convolutional neural networks dictionary learning sparse convolutional filters

来源：评论

学校读者我要写书评

暂无评论

First- and Second-Order Methods for Online convolutional Dictionary Learning

引用

SIAM JOURNAL ON IMAGING SCIENCES 2018年第2期11卷 1589-1628页

作者： Liu, Jialin Garcia-Cardona, Cristina Wohlbereg, Brendt Yin, Wotao UCLA Dept Math Los Angeles CA 90095 USA Los Alamos Natl Lab CCS Div Los Alamos NM 87545 USA Los Alamos Natl Lab Theoret Div Los Alamos NM 87545 USA

convolutional sparse representations are a form of sparse representation with a structured, translation-invariant dictionary. Most convolutional dictionary learning algorithms to date operate in batch mode, requiring simultaneous access to all training images during the learning process, which results in very high memory usage and severely limits the training data size that can be used. Very recently, however, a number of authors have considered the design of online convolutional dictionary learning algorithms that offer far better scaling of memory and computational cost with training set size than batch methods. This paper extends our prior work, improving a number of aspects of our previous algorithm;proposing an entirely new one, with better performance, that supports the inclusion of a spatial mask for learning from incomplete data;and providing a rigorous theoretical analysis of these methods.

关键词： convolutional sparse coding convolutional dictionary learning online dictionary learning stochastic gradient descent recursive least squares

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：