检索结果-内蒙古大学图书馆

Mamba-based spatial-spectral fusion network for hyperspectral unmixing

Journal of King Saud University Computer and Information Sciences 2025年第3期37卷 1-24页

作者： Gan, Yuquan Wei, Jingtao Xu, Mengmeng School of Telecommunication and Information Engineering Xi’an University of Posts & Telecommunications Xi’an China Xi’ an Key Laboratory of Image Processing Technology and Applications for Public Security Xi’an University of Posts & Telecommunications Xi’an China Shaanxi Key Laboratory of Information Communication Network and Security Xi’an University of Posts & Telecommunications Xi’an China

Hyperspectral unmixing (HU) is a critical technique in hyperspectral image (HSI) analysis, aimed at decomposing mixed pixels into a set of spectral signatures (endmembers) and their corresponding abundance values. Recently, the Mamba model has gained significant attention for its exceptional performance in natural language processing and has been extended to vision research. With its strong capability for long-range modeling and linear computational complexity, Mamba demonstrates substantial potential in hyperspectral image processing. However, due to the intrinsic requirement of HU tasks for comprehensive integration of spatial and spectral information, challenges remain in effectively leveraging Mamba for hyperspectral representation. To address these issues, we propose a novel Mamba-based spatial-spectral fusion network for hyperspectral unmixing (Mamba-SSFN). This network introduces a fusion mechanism to jointly learn spectral and spatial feature representations, enabling more efficient extraction of critical HSI features. Specifically, in the spatial feature extraction module, we integrate multi-scale analysis with the Mamba module, enabling the capturing of both local and global spatial information. In the spectral feature extraction module, the Mamba module is employed in a grouped manner to process spectral vectors, exploring the correlations among different spectral groups. Finally, an effective fusion mechanism is implemented to integrate spatial and spectral *** results demonstrate that Mamba-SSFN achieves outstanding performance across multiple benchmark datasets, significantly surpassing existing state-of-the-art methods in terms of unmixing accuracy, model robustness, and computational efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tomato Leaf Disease recognition based on Fine-Grained Interpretable Knowledge Distillation model for smart agricultural

引用

Applied Soft Computing 2025年 176卷

作者： Li, Daxiang Hua, Cuiyun Liu, Ying School of Telecommunication and Information Engineering Xi'an University of Posts and Telecommunications Xi'an710121 China Xi'an Key Laboratory of Image Processing Technology and Applications for Public Security Xi'an710121 China

In large-scale smart agricultural plantations, in order to utilize computer vision technology for automatic recognition of Tomato Leaf Diseases (TLD) and improve the intelligence level of Smart Agricultural Internet of Things (SAIoT), this paper designs a novel Fine-Grained Interpretable Knowledge Distillation (FGIKD) model. Firstly, based on Deformable Dilated Convolution (DDC) and Simplified Self-Attention (SSA) mechanism, a new Deformable Multi-Scale Perception (DMSP) spatial attention module is designed to integrate the irregular local perception ability of DDC with the global modeling ability of self-attention, thereby enhancing the low-level visual feature extraction capability of the model. Secondly, based on Cross-Layer Feature Fusion (CLFF) and Graph Self-Supervised Learning (GSSL), a new Fine-Grained (FG) feature extraction module is designed to alleviate the problem of "high intra-class variance and low inter-class variance" in TLD images. Thirdly, DMSP and FG distillation functions are designed to transfer the knowledges from teacher network to student network, enabling it to achieve performance close to the teacher network with a small number of parameters. Finally, combining class activation maps with regional confidence weighting technique, a new CNN model post-hoc explanation scheme is designed in the form of "saliency map". In the comparison experiments of standard dataset validation and real-world application testing, the knowledge-distilled student network achieves 98.13 % and 97.56 % TLD recognition accuracies, while the number of model parameters is only 2.921MB, which can meet the requirements of SAIoT terminal model deployment. © 2025 Elsevier B.V.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

C2P-Net: Comprehensive Depth Map to Planar Depth Conversion for Room Layout Estimation

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年 PP卷 PP页

作者： Zhang, Weidong Zhou, Mengjie Cheng, Jiyu Liu, Ying Zhang, Wei Xi'an University of Posts & Telecommunications School of Communications and Information Engineering China Xi'an Key Laboratory of Image Processing Technology and Applications for Public Security China Shandong University School of Control Science and Engineering China Ministry of Education Key Laboratory of Machine Intelligence and System Control China

Room layout estimation seeks to infer the overall spatial configuration of indoor scenes using perspective or panoramic images. As the layout is determined by the dominant indoor planes, this problem inherently requires the reconstruction of these planes. Some studies reconstruct indoor planes from perspective images by learning pixel-level or instance-level plane parameters. However, directly learning these parameters has the problems of susceptibility to occlusions and position dependency. In this paper, we introduce the Comprehensive depth map to Planar depth (C2P) conversion, which reformulates planar depth reconstruction into the prediction of a comprehensive depth map and planar visibility confidence. Based on the parametric representation of planar depth we propose, the C2P conversion is applicable to both panoramic and perspective images. Accordingly, we present an effective framework for room layout estimation that jointly learns the comprehensive depth map and planar visibility confidence. Due to the differentiability of the C2P conversion, our network autonomously learns planar visibility confidence by constraining the estimated plane parameters and reconstructed planar depth map. We further propose a novel approach for 3D layout generation through sequential planar depth map integration. Experimental results demonstrate the superiority of our method across all evaluated panoramic and perspective datasets. © 1979-2012 IEEE.

关键词： image-Text Matching Medical Report Generation Sample-graph Consistency Self-boosting framework

来源：评论

学校读者我要写书评

暂无评论

Possibilistic c-means clustering approach based on a novel weighted-kernel distance for imbalanced images with minority targets in sparsely distribution

引用

Engineering applications of Artificial Intelligence 2025年 154卷

作者： Haiyan Yu Yuting Wu Haocong Zheng Qianqian Luo Lu Zhang School of Telecommunication and Information Engineering Xi'an University of Posts and Telecommunications Xi'an 710121 China Xi'an Key Laboratory of Image Processing Technology and Applications for Public Security Xi'an 710121 China

Possibilistic c-means clustering (PCM), a classic partition clustering algorithm, is an important data mining technique for unsupervised image segmentation in the field of artificial intelligence. The typicalities (memberships) of PCM have better description of local information and excellent noise resistance due to its absolute attribute. However, it still faces the challenges of segmenting color images with multiple characteristics, such as feature imbalance, cluster-size imbalance, noise attack, especially sparsely distribution of minority targets in the feature space. Therefore, this paper introduces a weighted-kernel distance-based PCM (WK-PCM) algorithm. Firstly, a weighted-kernel distance (WK-distance) is defined by combining the absolute attribute of typicalities and the Gaussian kernel function to enhance the intra-class compactness of sparse targets. Meanwhile, the feature weighting scheme in the WK-distance is expected to avoid center offset caused by imbalanced features. Secondly, to overcome the issue of center overlapping caused by insufficient interclass relationships of typicalities, the cutset theory is introduced based on the WK-distance to select partial objects. Then the typicalities of these selected objects are suppressed to increase inter-class separateness and avoid the issue of coincident clustering (also called center overlapping). Finally, an improved WK-PCM image segmentation algorithm (LWK-PCM) based on local spatial information acquired through bilateral filtering is proposed for imbalanced color images with noise corruption. Experiments conducted on synthetic datasets and imbalanced color images indicate that the proposed WK-PCM and LWK-PCM algorithms get excellent clustering performance compared to the relevant clustering algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A comprehensive survey on shadow removal from document images: datasets, methods, and opportunities

引用

Vicinagearth 2025年第1期2卷 1-18页

作者： Wang, Bingshu Li, Changping Zou, Wenbin Zhang, Yongjun Chen, Xuhang Chen, C.L. Philip School of Software Northwestern Polytechnical University Xi’an China Guangdong Provincial Key Laboratory of Intelligent Information Processing & Shenzhen Key Laboratory of Media Security Shenzhen University Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing College of Electronics and Information Engineering Shenzhen University Shenzhen China Yongjun Zhang is with the State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang China School of Computer Science and Engineering Huizhou University Huizhou China School of Computer Science and Engineering South China University of Technology and Pazhou Lab Guangzhou China

With the rapid development of document digitization, people have become accustomed to capturing and processing documents using electronic devices such as smartphones. However, the captured document images often suffer from issues like shadows and noise due to environmental factors, which can affect their readability. To improve the quality of captured document images, researchers have proposed a series of models or frameworks and applied them in distinct scenarios such as image enhancement, and document information extraction. In this paper, we primarily focus on shadow removal methods and open-source datasets. We concentrate on recent advancements in this area, first organizing and analyzing nine available datasets. Then, the methods are categorized into conventional methods and neural network-based methods. Conventional methods use manually designed features and include shadow map-based approaches and illumination-based approaches. Neural network-based methods automatically generate features from data and are divided into single-stage approaches and multi-stage approaches. We detail representative algorithms and briefly describe some typical techniques. Finally, we analyze and discuss experimental results, identifying the limitations of datasets and methods. Future research directions are discussed, and nine suggestions for shadow removal from document images are proposed. To our knowledge, this is the first survey of shadow removal methods and related datasets from document images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Criminal Investigation image Classification Based on Spatial CNN Features and ELM 10

Criminal Investigation Image Classification Based on Spatial...

引用

10th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2018

作者： Li, Daxiang Qiu, xin Zhu, Zhiyu Liu, Ying Center for Image and Information Processing Xi'an University of Posts and Telecommunications Xi'an China Key Laboratory of Electronic Information Application Technology for Scene Investigation Ministry of Public Security Xi'an China

ISBN: (纸本)9781538658369

With the advent of the era of big data, the image of the criminal investigation has been explosively growing. To effectively help police officers classify suspect targets, a new classification method of criminal investigation image that combines spatial convolutional neural network (SCNN) and extreme learning machine (ELM) is proposed. Firstly, the image sub-blocks of different space are obtained by a five-block preprocessing on the criminal investigation image, which is part of the original image. Secondly, different image blocks are sent to a fine-tuned convolutional neural network to extract the features of the criminal investigation image. Finally, a criminal investigation image classification algorithm called SCNN-ELM is proposed in combination with extreme learning machine. The experimental results based on 2800 real criminal investigation image database and the standard Corel 1K image database show that the proposed method has an average accuracy improvement of 7.98% compared with the image classification method based on non-blocking CNN features, and the average classification accuracy is also superior than other similar methods. © 2018 IEEE.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

Transformer-based Lossless Compression of Aurora Spectral images: A Spatial-Temporal-Spectral Joint Approach 17

Transformer-based Lossless Compression of Aurora Spectral Im...

引用

17th IEEE International Conference on Signal processing, ICSP 2024

作者： Cao, xinlong Li, Jiaojiao Li, Yuanqing Yan, Jiapeng Zheng, Zhenxing Xi'an University of Posts & Telecommunications School of Communications and Information Engineering School of Artificial Intelligence Xi'an710121 China Xi'an Key Laboratory of Image Processing Technology and Applications for Public Security Xi'an710121 China International Joint Research Center for Wireless Communication and Information Processing Technology of Shaanxi Province Xi'an710121 China

ISBN: (纸本)9798350387384

Aurora spectral image lossless compression has seen significant advancements in recent years. However, most compression algorithms are based on traditional image compression techniques, focusing solely on spectral and spatial correlations without considering temporal correlations. To further enhance compression performance, this paper proposes a Transformer-based point-by-point prediction algorithm for auroral spectral images, which simultaneously uses spatial, spectral and temporal contexts for prediction. Our prediction network consists of two parts: an encoder and a decoder. The encoder is composed of the encoding unit of the original Transformer and is used to extract features from spatial, spectral and temporal contexts. The decoder consists of fully connected layers and is used for prediction. Experimental results show that the average bitrate of this method is reduced by 0.179 bpp compared with the JPEG2000 algorithm, and the average bitrate is reduced by 0.054 bpp compared with the online DPCM algorithm. © 2024 IEEE.

关键词： image compression

来源：评论

学校读者我要写书评

暂无评论

A Densely Connected Face Super-Resolution Network Based on Attention Mechanism 15

A Densely Connected Face Super-Resolution Network Based on A...

引用

15th IEEE Conference on Industrial Electronics and applications, ICIEA 2020

作者： Liu, Ying Dong, Zhanlong Pang Lim, Keng Ling, Nam Ministry of Public Security Key Laboratory of Electronic Information Application Technology for Scene Investigation Xi'an Shaanxi China Xi'an University of Posts Telecommunications Center for Image and Information Processing Xi'an China

ISBN: (纸本)9781728151694

Super resolution reconstruction of human face is a cost effective way to obtain high resolution images from its corresponding low resolution face. It is also known as face illusion. In order to obtain clearer texture details, this paper proposes a densely connected super-resolution algorithm based on attention mechanism which consists of feature extraction and image reconstruction. By integrating channel and spatial domain information of the feature map, the Multi Attention Domain Module (MADM) is proposed: Features are weighted and recombined by analyzing the relationship between channels and spatial information of feature maps. The features of different layers are fused using dense connections. Experimental results show that the proposed algorithm can improve by up to 0.5dB in PSNR and the reconstructed face image has clearer texture details compared to existing algorithms. © 2020 IEEE.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

An effective tread pattern image classification algorithm based on transfer learning 18

An effective tread pattern image classification algorithm ba...

引用

3rd International Conference on Multimedia Systems and Signal processing, ICMSSP 2018

作者： Liu, Y. Zhang, S. Li, D.X. Fan, J.L. Liu, W. Key Laboratory of Electronic Information Application Technology for Scene Investigation Ministry of Public Security Xi’an710121 China Center for Image and Information Processing Xi’an University of Posts and Telecommunications Xi’an710121 China

ISBN: (纸本)9781450364577

Tread pattern image classification is an important means in providing useful clues in traffic accident control and crime case solving. This paper proposes an effective tread pattern classification algorithm with feature fusion based on transfer learning. The algorithm consists of four parts, (1) Transfer the knowledge of a pre-trained CNN model on imageNet dataset to produce a new model for the task of tread pattern classification by fine-tuning the model parameters using tread pattern image data. (2) Extract features from multiple fully-connected layers as high-level features of tread pattern images. The concept of transfer learning solves the problem of lacking large training dataset. (3) Histogram of Oriented Gradient (HOG) is calculated as the low-level feature of the tread pattern images. (4) The features from the CNN model are combined with HOG as fusion feature, which is used to train SVM classifier for tread pattern image classification. Experimental results demonstrated the outstanding performance of the proposed algorithm for tread pattern image classification. © 2018 Association for Computing Machinery.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

Face Inpainting Combining Structured Forest Edge Information and Gated Convolution 3

Face Inpainting Combining Structured Forest Edge Information...

引用

3rd International Conference on Natural Language processing, ICNLP 2021

作者： Wang, Fuping Li, Wenlou Liu, Ying Gong, Yanchao Gao, Ziming Lu, Jin Center for Image and Information Processing Xi'An University of Posts and Telecommunications College Key Laboratory of Electronic Information Application Technology for Scene Investigation Ministry of Public Security Shaanxi Xi'an710121 China Center for Image and Information Processing Xi'An University of Posts and Telecommunications Shaanxi Xi'an710121 China

ISBN: (纸本)9781665414111

For the face inpainting under arbitrary shape occlusion, the existing methods are easy to produce edge blur and distortion of the inpainting results. In this paper, an algorithm for face inpainting combining structured forest edge information and gated convolution is proposed. Firstly, the edge contour of the occluded area is reconstructed by prior face knowledge to constrain the process of face inpainting. Secondary, the gated convolution holds the ability to extract accurate local feature when some pixels were missed, then a gated convolution based Generative Adversarial Network (GAN) for face inpainting is designed. The model consists of two parts: edge connection network and image inpainting network. The edge connection network accomplish the automatic completion and connection of the missing edge image. The image inpainting network takes the completed edge image as the guidance information, and combines the occlusion image to repair the missing face area. Compared with others, the experimental results show that the proposed algorithm has more precise detail information and better visual quality. © 2021 IEEE.

关键词： Convolution

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：