Hyperspectral images(HSIs)are susceptible to various noise interferences during the imaging process,leading to degraded image quality and affecting the accuracy of information extraction.Efficient denoising methods ar...Hyperspectral images(HSIs)are susceptible to various noise interferences during the imaging process,leading to degraded image quality and affecting the accuracy of information extraction.Efficient denoising methods are crucial for ensuring the accuracy of subsequent remote sensing analysis and applications.In view of the characteristics of hyperspectral image data,such as high dimensionality,strong spectral correlation,and high computational complexity,a threedimensional visual state space U-Net(VSSU3D)was proposed in this paper.By introducing a visual state space module into the traditional U-Net,and combining the spatial-spectral characteristics of hyperspectral images with the core idea of the Mamba model,targeted optimizations wereachieved to effectively model global information dependencies while reducing computational complexity.Additionally,a simplified channel attention module was embedded between the encoder and decoder to enhance cross-scale feature fusion capabilities.Experimental results on multiple publicly available hyperspectral image datasets demonstrated that VSSU3D achieved denoising performance comparable to or superior to existing advanced methods,which verified its effectiveness.展开更多
Hyper Spectral Image Super-Resolution(HSI-SR) has gained significant attention in recent years due to its potential applications.However,the challenge of obtaining high-resolution hyperspectral images is compounded by...Hyper Spectral Image Super-Resolution(HSI-SR) has gained significant attention in recent years due to its potential applications.However,the challenge of obtaining high-resolution hyperspectral images is compounded by limitations in sensor resolution and the high dimensionality of spectral data.Traditional approaches,including interpolation-based methods and sparse representation techniques,often struggle to capture the intricate spectral-spatial dependencies in hyperspectral images.To address these limitations,this study proposes a Hadamard Self-Attention Network(HSAN) for fusing a High-resolution Multispectral Image(Hr-MSI) and a Low-resolution Hyper Spectral Image(Lr-HSI),achieving HSI-SR for obtaining a High-resolution Hyper Spectral Image(Hr-HSI).The core of HSAN is a new Hadamard self-attention mechanism that can be more efficient than traditional dot-product attention because it avoids matrix multiplications and softmax operations.Considering that deep learning-based data fusion typically entails a significant computational and storage burden,this new approach can be integrated with convolutional layers to form an unsupervised lightweight network,which significantly reduces dependence on computational resources.Experimental results across four datasets validate the effectiveness and advantages of HSAN,compared with state-of-the-art approaches.The source code will be available at https://github.com/zxnhkdm/HSAN.展开更多
Images obtained from hyperspectral sensors provide information about the target area that extends beyond the visible portions of the electromagnetic spectrum.However,due to sensor limitations and imperfections during ...Images obtained from hyperspectral sensors provide information about the target area that extends beyond the visible portions of the electromagnetic spectrum.However,due to sensor limitations and imperfections during the image acquisition and transmission phases,noise is introduced into the acquired image,which can have a negative impact on downstream analyses such as classification,target tracking,and spectral unmixing.Noise in hyperspectral images(HSI)is modelled as a combination from several sources,including Gaussian/impulse noise,stripes,and deadlines.An HSI restoration method for such a mixed noise model is proposed.First,a joint optimisation framework is proposed for recovering hyperspectral data corrupted by mixed Gaussian-impulse noise by estimating both the clean data as well as the sparse/impulse noise levels.Second,a hyper-Laplacian prior is used along both the spatial and spectral dimensions to express sparsity in clean image gradients.Third,to model the sparse nature of impulse noise,anℓ_(1)−norm over the impulse noise gradient is used.Because the proposed methodology employs two distinct priors,the authors refer to it as the hyperspectral dual prior(HySpDualP)denoiser.To the best of authors'knowledge,this joint optimisation framework is the first attempt in this direction.To handle the non-smooth and nonconvex nature of the generalℓ_(p)−norm-based regularisation term,a generalised shrinkage/thresholding(GST)solver is employed.Finally,an efficient split-Bregman approach is used to solve the resulting optimisation problem.Experimental results on synthetic data and real HSI datacube obtained from hyperspectral sensors demonstrate that the authors’proposed model outperforms state-of-the-art methods,both visually and in terms of various image quality assessment metrics.展开更多
Due to the limitations of existing imaging hardware, obtaining high-resolution hyperspectral images is challenging. Hyperspectral image super-resolution(HSI SR) has been a very attractive research topic in computer vi...Due to the limitations of existing imaging hardware, obtaining high-resolution hyperspectral images is challenging. Hyperspectral image super-resolution(HSI SR) has been a very attractive research topic in computer vision, attracting the attention of many researchers. However, most HSI SR methods focus on the tradeoff between spatial resolution and spectral information, and cannot guarantee the efficient extraction of image information. In this paper, a multidimensional features network(MFNet) for HSI SR is proposed, which simultaneously learns and fuses the spatial,spectral, and frequency multidimensional features of HSI. Spatial features contain rich local details,spectral features contain the information and correlation between spectral bands, and frequency feature can reflect the global information of the image and can be used to obtain the global context of HSI. The fusion of the three features can better guide image super-resolution, to obtain higher-quality high-resolution hyperspectral images. In MFNet, we use the frequency feature extraction module(FFEM) to extract the frequency feature. On this basis, a multidimensional features extraction module(MFEM) is designed to learn and fuse multidimensional features. In addition, experimental results on two public datasets demonstrate that MFNet achieves state-of-the-art performance.展开更多
Imaging hyperspectral technology has distinctive advantages of non-destructive and non-contact measurement,and the integration of spectral and spatial data.These characteristics present new methodologies for intellige...Imaging hyperspectral technology has distinctive advantages of non-destructive and non-contact measurement,and the integration of spectral and spatial data.These characteristics present new methodologies for intelligent geological sensing in tunnels and other underground engineering projects.However,the in situ acquisition and rapid classification of hyperspectral images in underground still faces great challenges,including the difficulty in obtaining uniform hyperspectral images and the complexity of deploying sophisticated models on mobile platforms.This study proposes an intelligent lithology identification method based on partition feature extraction of hyperspectral images.Firstly,pixel-level hyperspectral information from representative lithological regions is extracted and fused to obtain rock hyperspectral image partition features.Subsequently,an SG-SNV-PCA-DNN(SSPD)model specifically designed for optimizing rock hyperspectral data,performing spectral dimensionality reduction,and identifying lithology is integrated.In an experimental study involving 3420 hyperspectral images,the SSPD identification model achieved the highest accuracy in the testing set,reaching 98.77%.Moreover,the speed of the SSPD model was found to be 18.5%faster than that of the unprocessed model,with an accuracy improvement of 5.22%.In contrast,the ResNet-101 model,used for point-by-point identification based on non-partitioned features,achieved a maximum accuracy of 97.86%in the testing set.In addition,the partition feature extraction methods significantly reduce computational complexity.An objective evaluation of various models demonstrated that the SSPD model exhibited superior performance,achieving a precision(P)of 99.46%,a recall(R)of 99.44%,and F1 score(F1)of 99.45%.Additionally,a pioneering in situ detection work was carried out in a tunnel using underground hyperspectral imaging technology.展开更多
In hyperspectral image classification(HSIC),accurately extracting spatial and spectral information from hyperspectral images(HSI)is crucial for achieving precise classification.However,due to low spatial resolution an...In hyperspectral image classification(HSIC),accurately extracting spatial and spectral information from hyperspectral images(HSI)is crucial for achieving precise classification.However,due to low spatial resolution and complex category boundary,mixed pixels containing features from multiple classes are inevitable in HSIs.Additionally,the spectral similarity among different classes challenge for extracting distinctive spectral features essential for HSIC.To address the impact of mixed pixels and spectral similarity for HSIC,we propose a central-pixel guiding sub-pixel and sub-channel convolution network(CP-SPSC)to extract more precise spatial and spectral features.Firstly,we designed spatial attention(CP-SPA)and spectral attention(CP-SPE)informed by the central pixel to effectively reduce spectral interference of irrelevant categories in the same patch.Furthermore,we use CP-SPA to guide 2D sub-pixel convolution(SPConv2d)to capture spatial features finer than the pixel level.Meanwhile,CP-SPE is also utilized to guide 1D sub-channel con-volution(SCConv1d)in selecting more precise spectral channels.For fusing spatial and spectral information at the feature-level,the spectral feature extension transformation module(SFET)adopts mirror-padding and snake permutation to transform 1D spectral information of the center pixel into 2D spectral features.Experiments on three popular datasets demonstrate that ours out-performs several state-of-the-art methods in accuracy.展开更多
In Hyperspectral Imaging(HSI),the detrimental influence of noise and distortions on data quality is profound,which has severely affected the following-on analytics and decisionmaking such as land mapping.This study pr...In Hyperspectral Imaging(HSI),the detrimental influence of noise and distortions on data quality is profound,which has severely affected the following-on analytics and decisionmaking such as land mapping.This study presents an innovative framework for assessing HSI band quality and reconstructing the low-quality bands,based on the Prophet model.By introducing a comprehensive quality metric to start,the authors approach factors in both spatial and spectral characteristics across local and global scales.This metric effectively captures the intricate noise and distortions inherent in the HSI data.Subsequently,the authors employ the Prophet model to forecast information within the low-quality bands,leveraging insights from neighbouring high-quality bands.To validate the effectiveness of the authors’proposed model,extensive experiments on three publicly available uncorrected datasets are conducted.In a head-to-head comparison,the framework against six state-ofthe-art band reconstruction algorithms including three spectral methods,two spatialspectral methods and one deep learning method is benchmarked.The authors’experiments also delve into strategies for band selection based on quality metrics and the quality evaluation of the reconstructed bands.In addition,the authors assess the classification accuracy utilising these reconstructed bands.In various experiments,the results consistently affirm the efficacy of the authors’method in HSI quality assessment and band reconstruction.Notably,the authors’approach obviates the need for manually prefiltering of noisy bands.This comprehensive framework holds promise in addressing HSI data quality concerns whilst enhancing the overall utility of HSI.展开更多
Aflatoxin B1(AFB1)is a toxic fungal metabolite that contaminates almonds from cultivation to harvesting.It leads to chronic health problems and significant economic loss to the producers.Therefore,a fast and non-invas...Aflatoxin B1(AFB1)is a toxic fungal metabolite that contaminates almonds from cultivation to harvesting.It leads to chronic health problems and significant economic loss to the producers.Therefore,a fast and non-invasive detection technique is crucial for safeguarding food safety by swiftly identifying and eliminating contaminated almonds from the supply chain.Hyperspectral imaging has been explored as a potential non-destructive technology for detecting AFB1.However,the diverse geometries of almonds present a significant challenge on acquired images,thereby impacting the accuracy of the developed prediction and classification models.This study investigates the effectiveness of short-wave infrared(SwIR)hyperspectral imaging combined with deep learning for detecting AFB1 in almonds of varying geometries.Initially,partial least squares regression(PLSR)and support vector machine(SvM)regression models were evaluated for quantification,while SVM and quadratic discriminant analysis(QDA)classifiers were applied for classification.The results indicated that spectral responses varied with almond thickness,making quantification models unreliable for industrial applications.The Competitive Adaptive Reweighted Sampling(CARS)algorithm was employed to identify key spectral features for developing multi-spectral AFB1 classification models to evaluate the feasibility of high-speed,accurate in-line detection.The deep learning approach significantly outperformed traditional machine learning models,with the pre-trained Inception V3 network achieving a cross-validation accuracy of 84.82%,an F1-score of 0.8522,and an area under curve of 0.893.These findings highlight the superiority of deep learning-based hyperspectral imaging for accurate and reliable AFB1 detection in almonds with diverse shapes and thicknesses.展开更多
To extract vegetation pigment concentration and physiological status has been studied in two test areas covered with swamp and flourish vegetation using pushbroom hyperspectral imager (PHI) data which flied in Septemb...To extract vegetation pigment concentration and physiological status has been studied in two test areas covered with swamp and flourish vegetation using pushbroom hyperspectral imager (PHI) data which flied in September of 2000 at Daxing'anling district of Heilongjiang Province, China. The ratio analysis of reflectance spectra (RARS) indices, which were put forward by Chappelle et al (1992), are chosen in this paper owing to their effect and simpleness against both comparison with various methods and techniques for exploration of pigment concentration and characteristics of PHI data. The correlation coefficients between RARS indices and pigment concentration of vegetation were up to 0.8. The new RARS indices modes are established in the two test areas using both PHI data and spectra of different vegetations measured in the field. The indices' parameter images of chlorophyll a (Chl a), chlorophyll b (Chl b) and carotenoids (Cars) of the test areas covered with swamp and flourish vegetation are acquired by the new RARS indices modes. Furthermore, the regional concentration of Chl a and Chl b are extracted and quantified using regression equations between RARS indices and pigment concentrations, which were built by Blackburn (1998). The results showed the physiological status and variety clearly, and are in good agreement with the distribution of vegetation in the field.展开更多
Among hyperspectral imaging technologies, interferometric spectral imaging is widely used in remote sening due to advantages of large luminous flux and high resolution. However, with complicated mechanism, interferome...Among hyperspectral imaging technologies, interferometric spectral imaging is widely used in remote sening due to advantages of large luminous flux and high resolution. However, with complicated mechanism, interferometric imaging faces the impact of multi-stage degradation. Most exsiting interferometric spectrum reconstruction methods are based on tradition model-based framework with multiple steps, showing poor efficiency and restricted performance. Thus, we propose an interferometric spectrum reconstruction method based on degradation synthesis and deep learning.Firstly, based on imaging mechanism, we proposed an mathematical model of interferometric imaging to analyse the degradation components as noises and trends during imaging. The model consists of three stages, namely instrument degradation, sensing degradation, and signal-independent degradation process. Then, we designed calibration-based method to estimate parameters in the model, of which the results are used for synthesizing realistic dataset for learning-based algorithms.In addition, we proposed a dual-stage interferogram spectrum reconstruction framework, which supports pre-training and integration of denoising DNNs. Experiments exhibits the reliability of our degradation model and synthesized data, and the effectiveness of the proposed reconstruction method.展开更多
Graph learning is an effective manner to analyze the intrinsic properties of data.It has been widely used in the fields of dimensionality reduction and classification for data.In this paper,we focus on the graph learn...Graph learning is an effective manner to analyze the intrinsic properties of data.It has been widely used in the fields of dimensionality reduction and classification for data.In this paper,we focus on the graph learning-based dimensionality reduction for a hyperspectral image.Firstly,we review the development of graph learning and its application in a hyperspectral image.Then,we mainly discuss several representative graph methods including two manifold learning methods,two sparse graph learning methods,and two hypergraph learning methods.For manifold learning,we analyze neighborhood preserving embedding and locality preserving projections which are two classic manifold learning methods and can be transformed into the form of a graph.For sparse graph,we introduce sparsity preserving graph embedding and sparse graph-based discriminant analysis which can adaptively reveal data structure to construct a graph.For hypergraph learning,we review binary hypergraph and discriminant hyper-Laplacian projection which can represent the high-order relationship of data.展开更多
Hyperspectral image super-resolution,which refers to reconstructing the high-resolution hyperspectral image from the input low-resolution observation,aims to improve the spatial resolution of the hyperspectral image,w...Hyperspectral image super-resolution,which refers to reconstructing the high-resolution hyperspectral image from the input low-resolution observation,aims to improve the spatial resolution of the hyperspectral image,which is beneficial for subsequent applications.The development of deep learning has promoted significant progress in hyperspectral image super-resolution,and the powerful expression capabilities of deep neural networks make the predicted results more reliable.Recently,several latest deep learning technologies have made the hyperspectral image super-resolution method explode.However,a comprehensive review and analysis of the latest deep learning methods from the hyperspectral image super-resolution perspective is absent.To this end,in this survey,we first introduce the concept of hyperspectral image super-resolution and classify the methods from the perspectives with or without auxiliary information.Then,we review the learning-based methods in three categories,including single hyperspectral image super-resolution,panchromatic-based hyperspectral image super-resolution,and multispectral-based hyperspectral image super-resolution.Subsequently,we summarize the commonly used hyperspectral dataset,and the evaluations for some representative methods in three categories are performed qualitatively and quantitatively.Moreover,we briefly introduce several typical applications of hyperspectral image super-resolution,including ground object classification,urban change detection,and ecosystem monitoring.Finally,we provide the conclusion and challenges in existing learning-based methods,looking forward to potential future research directions.展开更多
Hyperspectral image(HSI)classification has been one of themost important tasks in the remote sensing community over the last few decades.Due to the presence of highly correlated bands and limited training samples in H...Hyperspectral image(HSI)classification has been one of themost important tasks in the remote sensing community over the last few decades.Due to the presence of highly correlated bands and limited training samples in HSI,discriminative feature extraction was challenging for traditional machine learning methods.Recently,deep learning based methods have been recognized as powerful feature extraction tool and have drawn a significant amount of attention in HSI classification.Among various deep learning models,convolutional neural networks(CNNs)have shown huge success and offered great potential to yield high performance in HSI classification.Motivated by this successful performance,this paper presents a systematic review of different CNN architectures for HSI classification and provides some future guidelines.To accomplish this,our study has taken a few important steps.First,we have focused on different CNN architectures,which are able to extract spectral,spatial,and joint spectral-spatial features.Then,many publications related to CNN based HSI classifications have been reviewed systematically.Further,a detailed comparative performance analysis has been presented between four CNN models namely 1D CNN,2D CNN,3D CNN,and feature fusion based CNN(FFCNN).Four benchmark HSI datasets have been used in our experiment for evaluating the performance.Finally,we concluded the paper with challenges on CNN based HSI classification and future guidelines that may help the researchers to work on HSI classification using CNN.展开更多
Hyperspectral images(HSI)provide a new way to exploit the internal physical composition of the land scene.The basic platform for acquiring HSI data-sets are airborne or spaceborne spectral imaging.Retrieving useful in...Hyperspectral images(HSI)provide a new way to exploit the internal physical composition of the land scene.The basic platform for acquiring HSI data-sets are airborne or spaceborne spectral imaging.Retrieving useful information from hyperspectral images can be grouped into four categories.(1)Classification:Hyperspectral images provide so much spectral and spatial information that remotely sensed image classification has become a complex task.(2)Endmember extraction and spectral unmixing:Among images,only HSI have a complete model to represent the internal structure of each pixel where the endmembers are the elements.Identification of endmembers from HSI thus becomes the foremost step in interpretation of each pixel.With proper endmembers,the corresponding abundances can also be exactly calculated.(3)Target detection:Another practical problem is how to determine the existence of certain resolved or full pixel objects from a complex background.Constructing a reliable rule for separating target signals from all the other background signals,even in the case of low target occurrence and high spectral variation,comprises the key to this problem.(4)Change detection:Although change detection is not a new problem,detecting changes from hyperspectral images has brought new challenges,since the spectral bands are so many,accurate band-to-band correspondences and minor changes in subclass land objects can be depicted in HSI.In this paper,the basic theory and the most canonical works are discussed,along with the most recent advances in each aspect of hyperspectral image processing.展开更多
With limited number of labeled samples,hyperspectral image(HSI)classification is a difficult Problem in current research.The graph neural network(GNN)has emerged as an approach to semi-supervised classification,and th...With limited number of labeled samples,hyperspectral image(HSI)classification is a difficult Problem in current research.The graph neural network(GNN)has emerged as an approach to semi-supervised classification,and the application of GNN to hyperspectral images has attracted much attention.However,in the existing GNN-based methods a single graph neural network or graph filter is mainly used to extract HSI features,which does not take full advantage of various graph neural networks(graph filters).Moreover,the traditional GNNs have the problem of oversmoothing.To alleviate these shortcomings,we introduce a deep hybrid multi-graph neural network(DHMG),where two different graph filters,i.e.,the spectral filter and the autoregressive moving average(ARMA)filter,are utilized in two branches.The former can well extract the spectral features of the nodes,and the latter has a good suppression effect on graph noise.The network realizes information interaction between the two branches and takes good advantage of different graph filters.In addition,to address the problem of oversmoothing,a dense network is proposed,where the local graph features are preserved.The dense structure satisfies the needs of different classification targets presenting different features.Finally,we introduce a GraphSAGEbased network to refine the graph features produced by the deep hybrid network.Extensive experiments on three public HSI datasets strongly demonstrate that the DHMG dramatically outperforms the state-ofthe-art models.展开更多
Low-Rank and Sparse Representation(LRSR)method has gained popularity in Hyperspectral Image(HSI)processing.However,existing LRSR models rarely exploited spectral-spatial classification of HSI.In this paper,we proposed...Low-Rank and Sparse Representation(LRSR)method has gained popularity in Hyperspectral Image(HSI)processing.However,existing LRSR models rarely exploited spectral-spatial classification of HSI.In this paper,we proposed a novel Low-Rank and Sparse Representation with Adaptive Neighborhood Regularization(LRSR-ANR)method for HSI classification.In the proposed method,we first represent the hyperspectral data via LRSR since it combines both sparsity and low-rankness to maintain global and local data structures simultaneously.The LRSR is optimized by using a mixed Gauss-Seidel and Jacobian Alternating Direction Method of Multipliers(M-ADMM),which converges faster than ADMM.Then to incorporate the spatial information,an ANR scheme is designed by combining Euclidean and Cosine distance metrics to reduce the mixed pixels within a neighborhood.Lastly,the predicted labels are determined by jointly considering the homogeneous pixels in the classification rule of the minimum reconstruction error.Experimental results based on three popular hyperspectral images demonstrate that the proposed method outperforms other related methods in terms of classification accuracy and generalization performance.展开更多
Convolutional neural network(CNN)has excellent ability to model locally contextual information.However,CNNs face challenges for descripting long-range semantic features,which will lead to relatively low classification...Convolutional neural network(CNN)has excellent ability to model locally contextual information.However,CNNs face challenges for descripting long-range semantic features,which will lead to relatively low classification accuracy of hyperspectral images.To address this problem,this article proposes an algorithm based on multiscale fusion and transformer network for hyperspectral image classification.Firstly,the low-level spatial-spectral features are extracted by multi-scale residual structure.Secondly,an attention module is introduced to focus on the more important spatialspectral information.Finally,high-level semantic features are represented and learned by a token learner and an improved transformer encoder.The proposed algorithm is compared with six classical hyperspectral classification algorithms on real hyperspectral images.The experimental results show that the proposed algorithm effectively improves the land cover classification accuracy of hyperspectral images.展开更多
To compress hyperspectral images, a low complexity discrete cosine transform （DCT）-based distributed source coding （DSC） scheme with Gray code is proposed. Unlike most of the existing DSC schemes, which utilize tr...To compress hyperspectral images, a low complexity discrete cosine transform （DCT）-based distributed source coding （DSC） scheme with Gray code is proposed. Unlike most of the existing DSC schemes, which utilize transform in spatial domain, the proposed algorithm applies transform in spectral domain. Set-partitioning-based approach is applied to reorganize DCT coefficients into waveletlike tree structure and extract the sign, refinement, and significance bitplanes. The extracted refinement bits are Gray encoded. Because of the dependency along the line dimension of hyperspectral images, low density paritycheck-（LDPC）-based Slepian-Wolf coder is adopted to implement the DSC strategy. Experimental results on airborne visible/infrared imaging spectrometer （AVIRIS） dataset show that the proposed paradigm achieves up to 6 dB improvement over DSC-based coders which apply transform in spatial domain, with significantly reduced computational complexity and memory storage.展开更多
Hyperspectral image(HSI)contains a wealth of spectral information,which makes fine classification of ground objects possible.In the meanwhile,overly redundant information in HSI brings many challenges.Specifically,the...Hyperspectral image(HSI)contains a wealth of spectral information,which makes fine classification of ground objects possible.In the meanwhile,overly redundant information in HSI brings many challenges.Specifically,the lack of training samples and the high computational cost are the inevitable obstacles in the design of classifier.In order to solve these problems,dimensionality reduction is usually adopted.Recently,graph-based dimensionality reduction has become a hot topic.In this paper,the graph-based methods for HSI dimensionality reduction are summarized from the following aspects.1)The traditional graph-based methods employ Euclidean distance to explore the local information of samples in spectral feature space.2)The dimensionality-reduction methods based on sparse or collaborative representation regard the sparse or collaborative coefficients as graph weights to effectively reduce reconstruction errors and represent most important information of HSI in the dictionary.3)Improved methods based on sparse or collaborative graph have made great progress by considering global low-rank information,local intra-class information and spatial information.In order to compare typical techniques,three real HSI datasets were used to carry out relevant experiments,and then the experimental results were analysed and discussed.Finally,the future development of this research field is prospected.展开更多
Most methods for classifying hyperspectral data only consider the local spatial relation-ship among samples,ignoring the important non-local topological relationship.However,the non-local topological relationship is b...Most methods for classifying hyperspectral data only consider the local spatial relation-ship among samples,ignoring the important non-local topological relationship.However,the non-local topological relationship is better at representing the structure of hyperspectral data.This paper proposes a deep learning model called Topology and semantic information fusion classification network(TSFnet)that incorporates a topology structure and semantic information transmis-sion network to accurately classify traditional Chinese medicine in hyperspectral images.TSFnet uses a convolutional neural network(CNN)to extract features and a graph convolution network(GCN)to capture potential topological relationships among different types of Chinese herbal medicines.The results show that TSFnet outperforms other state-of-the-art deep learning classification algorithms in two different scenarios of herbal medicine datasets.Additionally,the proposed TSFnet model is lightweight and can be easily deployed for mobile herbal medicine classification.展开更多
文摘Hyperspectral images(HSIs)are susceptible to various noise interferences during the imaging process,leading to degraded image quality and affecting the accuracy of information extraction.Efficient denoising methods are crucial for ensuring the accuracy of subsequent remote sensing analysis and applications.In view of the characteristics of hyperspectral image data,such as high dimensionality,strong spectral correlation,and high computational complexity,a threedimensional visual state space U-Net(VSSU3D)was proposed in this paper.By introducing a visual state space module into the traditional U-Net,and combining the spatial-spectral characteristics of hyperspectral images with the core idea of the Mamba model,targeted optimizations wereachieved to effectively model global information dependencies while reducing computational complexity.Additionally,a simplified channel attention module was embedded between the encoder and decoder to enhance cross-scale feature fusion capabilities.Experimental results on multiple publicly available hyperspectral image datasets demonstrated that VSSU3D achieved denoising performance comparable to or superior to existing advanced methods,which verified its effectiveness.
基金National Natural Science Foundation of China(No. 42571463)Macao Young Scholars Program(No. AM2023033)+1 种基金Shaanxi Province Youth Science and Technology Star Program(No. 2024ZCKJXX-115)Natural Science Foundation of Shaanxi Province(No.2025JC-YBMS-257)。
文摘Hyper Spectral Image Super-Resolution(HSI-SR) has gained significant attention in recent years due to its potential applications.However,the challenge of obtaining high-resolution hyperspectral images is compounded by limitations in sensor resolution and the high dimensionality of spectral data.Traditional approaches,including interpolation-based methods and sparse representation techniques,often struggle to capture the intricate spectral-spatial dependencies in hyperspectral images.To address these limitations,this study proposes a Hadamard Self-Attention Network(HSAN) for fusing a High-resolution Multispectral Image(Hr-MSI) and a Low-resolution Hyper Spectral Image(Lr-HSI),achieving HSI-SR for obtaining a High-resolution Hyper Spectral Image(Hr-HSI).The core of HSAN is a new Hadamard self-attention mechanism that can be more efficient than traditional dot-product attention because it avoids matrix multiplications and softmax operations.Considering that deep learning-based data fusion typically entails a significant computational and storage burden,this new approach can be integrated with convolutional layers to form an unsupervised lightweight network,which significantly reduces dependence on computational resources.Experimental results across four datasets validate the effectiveness and advantages of HSAN,compared with state-of-the-art approaches.The source code will be available at https://github.com/zxnhkdm/HSAN.
文摘Images obtained from hyperspectral sensors provide information about the target area that extends beyond the visible portions of the electromagnetic spectrum.However,due to sensor limitations and imperfections during the image acquisition and transmission phases,noise is introduced into the acquired image,which can have a negative impact on downstream analyses such as classification,target tracking,and spectral unmixing.Noise in hyperspectral images(HSI)is modelled as a combination from several sources,including Gaussian/impulse noise,stripes,and deadlines.An HSI restoration method for such a mixed noise model is proposed.First,a joint optimisation framework is proposed for recovering hyperspectral data corrupted by mixed Gaussian-impulse noise by estimating both the clean data as well as the sparse/impulse noise levels.Second,a hyper-Laplacian prior is used along both the spatial and spectral dimensions to express sparsity in clean image gradients.Third,to model the sparse nature of impulse noise,anℓ_(1)−norm over the impulse noise gradient is used.Because the proposed methodology employs two distinct priors,the authors refer to it as the hyperspectral dual prior(HySpDualP)denoiser.To the best of authors'knowledge,this joint optimisation framework is the first attempt in this direction.To handle the non-smooth and nonconvex nature of the generalℓ_(p)−norm-based regularisation term,a generalised shrinkage/thresholding(GST)solver is employed.Finally,an efficient split-Bregman approach is used to solve the resulting optimisation problem.Experimental results on synthetic data and real HSI datacube obtained from hyperspectral sensors demonstrate that the authors’proposed model outperforms state-of-the-art methods,both visually and in terms of various image quality assessment metrics.
基金supported by the Fundamental Research Funds for the Provincial Universities of Zhejiang (No.GK249909299001-036)National Key Research and Development Program of China (No. 2023YFB4502803)Zhejiang Provincial Natural Science Foundation of China (No.LDT23F01014F01)。
文摘Due to the limitations of existing imaging hardware, obtaining high-resolution hyperspectral images is challenging. Hyperspectral image super-resolution(HSI SR) has been a very attractive research topic in computer vision, attracting the attention of many researchers. However, most HSI SR methods focus on the tradeoff between spatial resolution and spectral information, and cannot guarantee the efficient extraction of image information. In this paper, a multidimensional features network(MFNet) for HSI SR is proposed, which simultaneously learns and fuses the spatial,spectral, and frequency multidimensional features of HSI. Spatial features contain rich local details,spectral features contain the information and correlation between spectral bands, and frequency feature can reflect the global information of the image and can be used to obtain the global context of HSI. The fusion of the three features can better guide image super-resolution, to obtain higher-quality high-resolution hyperspectral images. In MFNet, we use the frequency feature extraction module(FFEM) to extract the frequency feature. On this basis, a multidimensional features extraction module(MFEM) is designed to learn and fuse multidimensional features. In addition, experimental results on two public datasets demonstrate that MFNet achieves state-of-the-art performance.
基金support from the National Natural Science Foundation of China(Grant Nos.52379103,52279103)the Natural Science Foundation of Shandong Province(Grant No.ZR2023YQ049).
文摘Imaging hyperspectral technology has distinctive advantages of non-destructive and non-contact measurement,and the integration of spectral and spatial data.These characteristics present new methodologies for intelligent geological sensing in tunnels and other underground engineering projects.However,the in situ acquisition and rapid classification of hyperspectral images in underground still faces great challenges,including the difficulty in obtaining uniform hyperspectral images and the complexity of deploying sophisticated models on mobile platforms.This study proposes an intelligent lithology identification method based on partition feature extraction of hyperspectral images.Firstly,pixel-level hyperspectral information from representative lithological regions is extracted and fused to obtain rock hyperspectral image partition features.Subsequently,an SG-SNV-PCA-DNN(SSPD)model specifically designed for optimizing rock hyperspectral data,performing spectral dimensionality reduction,and identifying lithology is integrated.In an experimental study involving 3420 hyperspectral images,the SSPD identification model achieved the highest accuracy in the testing set,reaching 98.77%.Moreover,the speed of the SSPD model was found to be 18.5%faster than that of the unprocessed model,with an accuracy improvement of 5.22%.In contrast,the ResNet-101 model,used for point-by-point identification based on non-partitioned features,achieved a maximum accuracy of 97.86%in the testing set.In addition,the partition feature extraction methods significantly reduce computational complexity.An objective evaluation of various models demonstrated that the SSPD model exhibited superior performance,achieving a precision(P)of 99.46%,a recall(R)of 99.44%,and F1 score(F1)of 99.45%.Additionally,a pioneering in situ detection work was carried out in a tunnel using underground hyperspectral imaging technology.
基金supported by the National Natural Science Foundation of China(No.62071323).
文摘In hyperspectral image classification(HSIC),accurately extracting spatial and spectral information from hyperspectral images(HSI)is crucial for achieving precise classification.However,due to low spatial resolution and complex category boundary,mixed pixels containing features from multiple classes are inevitable in HSIs.Additionally,the spectral similarity among different classes challenge for extracting distinctive spectral features essential for HSIC.To address the impact of mixed pixels and spectral similarity for HSIC,we propose a central-pixel guiding sub-pixel and sub-channel convolution network(CP-SPSC)to extract more precise spatial and spectral features.Firstly,we designed spatial attention(CP-SPA)and spectral attention(CP-SPE)informed by the central pixel to effectively reduce spectral interference of irrelevant categories in the same patch.Furthermore,we use CP-SPA to guide 2D sub-pixel convolution(SPConv2d)to capture spatial features finer than the pixel level.Meanwhile,CP-SPE is also utilized to guide 1D sub-channel con-volution(SCConv1d)in selecting more precise spectral channels.For fusing spatial and spectral information at the feature-level,the spectral feature extension transformation module(SFET)adopts mirror-padding and snake permutation to transform 1D spectral information of the center pixel into 2D spectral features.Experiments on three popular datasets demonstrate that ours out-performs several state-of-the-art methods in accuracy.
基金National Natural Science Foundation Major Project of China,Grant/Award Number:42192580Guangdong Province Key Construction Discipline Scientific Research Ability Promotion Project,Grant/Award Number:2022ZDJS015。
文摘In Hyperspectral Imaging(HSI),the detrimental influence of noise and distortions on data quality is profound,which has severely affected the following-on analytics and decisionmaking such as land mapping.This study presents an innovative framework for assessing HSI band quality and reconstructing the low-quality bands,based on the Prophet model.By introducing a comprehensive quality metric to start,the authors approach factors in both spatial and spectral characteristics across local and global scales.This metric effectively captures the intricate noise and distortions inherent in the HSI data.Subsequently,the authors employ the Prophet model to forecast information within the low-quality bands,leveraging insights from neighbouring high-quality bands.To validate the effectiveness of the authors’proposed model,extensive experiments on three publicly available uncorrected datasets are conducted.In a head-to-head comparison,the framework against six state-ofthe-art band reconstruction algorithms including three spectral methods,two spatialspectral methods and one deep learning method is benchmarked.The authors’experiments also delve into strategies for band selection based on quality metrics and the quality evaluation of the reconstructed bands.In addition,the authors assess the classification accuracy utilising these reconstructed bands.In various experiments,the results consistently affirm the efficacy of the authors’method in HSI quality assessment and band reconstruction.Notably,the authors’approach obviates the need for manually prefiltering of noisy bands.This comprehensive framework holds promise in addressing HSI data quality concerns whilst enhancing the overall utility of HSI.
基金the Research Training Program International(RTPi)scholarship from Commonwealth Australiathe top-up scholarship provided by SureNut Ltd.SureNut Ltd.for supplying all the almonds used in this study.
文摘Aflatoxin B1(AFB1)is a toxic fungal metabolite that contaminates almonds from cultivation to harvesting.It leads to chronic health problems and significant economic loss to the producers.Therefore,a fast and non-invasive detection technique is crucial for safeguarding food safety by swiftly identifying and eliminating contaminated almonds from the supply chain.Hyperspectral imaging has been explored as a potential non-destructive technology for detecting AFB1.However,the diverse geometries of almonds present a significant challenge on acquired images,thereby impacting the accuracy of the developed prediction and classification models.This study investigates the effectiveness of short-wave infrared(SwIR)hyperspectral imaging combined with deep learning for detecting AFB1 in almonds of varying geometries.Initially,partial least squares regression(PLSR)and support vector machine(SvM)regression models were evaluated for quantification,while SVM and quadratic discriminant analysis(QDA)classifiers were applied for classification.The results indicated that spectral responses varied with almond thickness,making quantification models unreliable for industrial applications.The Competitive Adaptive Reweighted Sampling(CARS)algorithm was employed to identify key spectral features for developing multi-spectral AFB1 classification models to evaluate the feasibility of high-speed,accurate in-line detection.The deep learning approach significantly outperformed traditional machine learning models,with the pre-trained Inception V3 network achieving a cross-validation accuracy of 84.82%,an F1-score of 0.8522,and an area under curve of 0.893.These findings highlight the superiority of deep learning-based hyperspectral imaging for accurate and reliable AFB1 detection in almonds with diverse shapes and thicknesses.
文摘To extract vegetation pigment concentration and physiological status has been studied in two test areas covered with swamp and flourish vegetation using pushbroom hyperspectral imager (PHI) data which flied in September of 2000 at Daxing'anling district of Heilongjiang Province, China. The ratio analysis of reflectance spectra (RARS) indices, which were put forward by Chappelle et al (1992), are chosen in this paper owing to their effect and simpleness against both comparison with various methods and techniques for exploration of pigment concentration and characteristics of PHI data. The correlation coefficients between RARS indices and pigment concentration of vegetation were up to 0.8. The new RARS indices modes are established in the two test areas using both PHI data and spectra of different vegetations measured in the field. The indices' parameter images of chlorophyll a (Chl a), chlorophyll b (Chl b) and carotenoids (Cars) of the test areas covered with swamp and flourish vegetation are acquired by the new RARS indices modes. Furthermore, the regional concentration of Chl a and Chl b are extracted and quantified using regression equations between RARS indices and pigment concentrations, which were built by Blackburn (1998). The results showed the physiological status and variety clearly, and are in good agreement with the distribution of vegetation in the field.
文摘Among hyperspectral imaging technologies, interferometric spectral imaging is widely used in remote sening due to advantages of large luminous flux and high resolution. However, with complicated mechanism, interferometric imaging faces the impact of multi-stage degradation. Most exsiting interferometric spectrum reconstruction methods are based on tradition model-based framework with multiple steps, showing poor efficiency and restricted performance. Thus, we propose an interferometric spectrum reconstruction method based on degradation synthesis and deep learning.Firstly, based on imaging mechanism, we proposed an mathematical model of interferometric imaging to analyse the degradation components as noises and trends during imaging. The model consists of three stages, namely instrument degradation, sensing degradation, and signal-independent degradation process. Then, we designed calibration-based method to estimate parameters in the model, of which the results are used for synthesizing realistic dataset for learning-based algorithms.In addition, we proposed a dual-stage interferogram spectrum reconstruction framework, which supports pre-training and integration of denoising DNNs. Experiments exhibits the reliability of our degradation model and synthesized data, and the effectiveness of the proposed reconstruction method.
基金This work is supported by the National Natural Science Foundation of China[grant number 61801336]the China Postdoctoral Science Foundation[grant number 2019M662717 and 2017M622521]the China Postdoctoral Program for Innovative Talent[grant number BX201700182].
文摘Graph learning is an effective manner to analyze the intrinsic properties of data.It has been widely used in the fields of dimensionality reduction and classification for data.In this paper,we focus on the graph learning-based dimensionality reduction for a hyperspectral image.Firstly,we review the development of graph learning and its application in a hyperspectral image.Then,we mainly discuss several representative graph methods including two manifold learning methods,two sparse graph learning methods,and two hypergraph learning methods.For manifold learning,we analyze neighborhood preserving embedding and locality preserving projections which are two classic manifold learning methods and can be transformed into the form of a graph.For sparse graph,we introduce sparsity preserving graph embedding and sparse graph-based discriminant analysis which can adaptively reveal data structure to construct a graph.For hypergraph learning,we review binary hypergraph and discriminant hyper-Laplacian projection which can represent the high-order relationship of data.
基金supported in part by the National Natural Science Foundation of China(62276192)。
文摘Hyperspectral image super-resolution,which refers to reconstructing the high-resolution hyperspectral image from the input low-resolution observation,aims to improve the spatial resolution of the hyperspectral image,which is beneficial for subsequent applications.The development of deep learning has promoted significant progress in hyperspectral image super-resolution,and the powerful expression capabilities of deep neural networks make the predicted results more reliable.Recently,several latest deep learning technologies have made the hyperspectral image super-resolution method explode.However,a comprehensive review and analysis of the latest deep learning methods from the hyperspectral image super-resolution perspective is absent.To this end,in this survey,we first introduce the concept of hyperspectral image super-resolution and classify the methods from the perspectives with or without auxiliary information.Then,we review the learning-based methods in three categories,including single hyperspectral image super-resolution,panchromatic-based hyperspectral image super-resolution,and multispectral-based hyperspectral image super-resolution.Subsequently,we summarize the commonly used hyperspectral dataset,and the evaluations for some representative methods in three categories are performed qualitatively and quantitatively.Moreover,we briefly introduce several typical applications of hyperspectral image super-resolution,including ground object classification,urban change detection,and ecosystem monitoring.Finally,we provide the conclusion and challenges in existing learning-based methods,looking forward to potential future research directions.
文摘Hyperspectral image(HSI)classification has been one of themost important tasks in the remote sensing community over the last few decades.Due to the presence of highly correlated bands and limited training samples in HSI,discriminative feature extraction was challenging for traditional machine learning methods.Recently,deep learning based methods have been recognized as powerful feature extraction tool and have drawn a significant amount of attention in HSI classification.Among various deep learning models,convolutional neural networks(CNNs)have shown huge success and offered great potential to yield high performance in HSI classification.Motivated by this successful performance,this paper presents a systematic review of different CNN architectures for HSI classification and provides some future guidelines.To accomplish this,our study has taken a few important steps.First,we have focused on different CNN architectures,which are able to extract spectral,spatial,and joint spectral-spatial features.Then,many publications related to CNN based HSI classifications have been reviewed systematically.Further,a detailed comparative performance analysis has been presented between four CNN models namely 1D CNN,2D CNN,3D CNN,and feature fusion based CNN(FFCNN).Four benchmark HSI datasets have been used in our experiment for evaluating the performance.Finally,we concluded the paper with challenges on CNN based HSI classification and future guidelines that may help the researchers to work on HSI classification using CNN.
基金This work was supported in part by the National Basic Research Program of China(973 Program)under Grant 2012CB719905 and 2011CB707105the National Natural Science Foundation of China under Grant 61102128+2 种基金HuBei Province Natural Science Foundation under Grant No.2011CDB455China’s Post-doctoral Science Foundation under 211–180,788the Fundamental Research Funds for the Central Universities under 211-274633.
文摘Hyperspectral images(HSI)provide a new way to exploit the internal physical composition of the land scene.The basic platform for acquiring HSI data-sets are airborne or spaceborne spectral imaging.Retrieving useful information from hyperspectral images can be grouped into four categories.(1)Classification:Hyperspectral images provide so much spectral and spatial information that remotely sensed image classification has become a complex task.(2)Endmember extraction and spectral unmixing:Among images,only HSI have a complete model to represent the internal structure of each pixel where the endmembers are the elements.Identification of endmembers from HSI thus becomes the foremost step in interpretation of each pixel.With proper endmembers,the corresponding abundances can also be exactly calculated.(3)Target detection:Another practical problem is how to determine the existence of certain resolved or full pixel objects from a complex background.Constructing a reliable rule for separating target signals from all the other background signals,even in the case of low target occurrence and high spectral variation,comprises the key to this problem.(4)Change detection:Although change detection is not a new problem,detecting changes from hyperspectral images has brought new challenges,since the spectral bands are so many,accurate band-to-band correspondences and minor changes in subclass land objects can be depicted in HSI.In this paper,the basic theory and the most canonical works are discussed,along with the most recent advances in each aspect of hyperspectral image processing.
文摘With limited number of labeled samples,hyperspectral image(HSI)classification is a difficult Problem in current research.The graph neural network(GNN)has emerged as an approach to semi-supervised classification,and the application of GNN to hyperspectral images has attracted much attention.However,in the existing GNN-based methods a single graph neural network or graph filter is mainly used to extract HSI features,which does not take full advantage of various graph neural networks(graph filters).Moreover,the traditional GNNs have the problem of oversmoothing.To alleviate these shortcomings,we introduce a deep hybrid multi-graph neural network(DHMG),where two different graph filters,i.e.,the spectral filter and the autoregressive moving average(ARMA)filter,are utilized in two branches.The former can well extract the spectral features of the nodes,and the latter has a good suppression effect on graph noise.The network realizes information interaction between the two branches and takes good advantage of different graph filters.In addition,to address the problem of oversmoothing,a dense network is proposed,where the local graph features are preserved.The dense structure satisfies the needs of different classification targets presenting different features.Finally,we introduce a GraphSAGEbased network to refine the graph features produced by the deep hybrid network.Extensive experiments on three public HSI datasets strongly demonstrate that the DHMG dramatically outperforms the state-ofthe-art models.
基金National Natural Foundation of China(No.41971279)Fundamental Research Funds of the Central Universities(No.B200202012)。
文摘Low-Rank and Sparse Representation(LRSR)method has gained popularity in Hyperspectral Image(HSI)processing.However,existing LRSR models rarely exploited spectral-spatial classification of HSI.In this paper,we proposed a novel Low-Rank and Sparse Representation with Adaptive Neighborhood Regularization(LRSR-ANR)method for HSI classification.In the proposed method,we first represent the hyperspectral data via LRSR since it combines both sparsity and low-rankness to maintain global and local data structures simultaneously.The LRSR is optimized by using a mixed Gauss-Seidel and Jacobian Alternating Direction Method of Multipliers(M-ADMM),which converges faster than ADMM.Then to incorporate the spatial information,an ANR scheme is designed by combining Euclidean and Cosine distance metrics to reduce the mixed pixels within a neighborhood.Lastly,the predicted labels are determined by jointly considering the homogeneous pixels in the classification rule of the minimum reconstruction error.Experimental results based on three popular hyperspectral images demonstrate that the proposed method outperforms other related methods in terms of classification accuracy and generalization performance.
基金National Natural Science Foundation of China(No.62201457)Natural Science Foundation of Shaanxi Province(Nos.2022JQ-668,2022JQ-588)。
文摘Convolutional neural network(CNN)has excellent ability to model locally contextual information.However,CNNs face challenges for descripting long-range semantic features,which will lead to relatively low classification accuracy of hyperspectral images.To address this problem,this article proposes an algorithm based on multiscale fusion and transformer network for hyperspectral image classification.Firstly,the low-level spatial-spectral features are extracted by multi-scale residual structure.Secondly,an attention module is introduced to focus on the more important spatialspectral information.Finally,high-level semantic features are represented and learned by a token learner and an improved transformer encoder.The proposed algorithm is compared with six classical hyperspectral classification algorithms on real hyperspectral images.The experimental results show that the proposed algorithm effectively improves the land cover classification accuracy of hyperspectral images.
基金supported by the National Natural Science Foundationof China (60702012)the Scientific Research Foundation for the Re-turned Overseas Chinese Scholars, State Education Ministry
文摘To compress hyperspectral images, a low complexity discrete cosine transform （DCT）-based distributed source coding （DSC） scheme with Gray code is proposed. Unlike most of the existing DSC schemes, which utilize transform in spatial domain, the proposed algorithm applies transform in spectral domain. Set-partitioning-based approach is applied to reorganize DCT coefficients into waveletlike tree structure and extract the sign, refinement, and significance bitplanes. The extracted refinement bits are Gray encoded. Because of the dependency along the line dimension of hyperspectral images, low density paritycheck-（LDPC）-based Slepian-Wolf coder is adopted to implement the DSC strategy. Experimental results on airborne visible/infrared imaging spectrometer （AVIRIS） dataset show that the proposed paradigm achieves up to 6 dB improvement over DSC-based coders which apply transform in spatial domain, with significantly reduced computational complexity and memory storage.
基金supported by the National Key Research and Development Project(No.2020YFC1512000)the National Natural Science Foundation of China(No.41601344)+2 种基金the Fundamental Research Funds for the Central Universities(Nos.300102320107 and 201924)in part by the General Projects of Key R&D Programs in Shaanxi Province(No.2020GY-060)Xi’an Science&Technology Project(Nos.2020KJRC0126 and 202018)。
文摘Hyperspectral image(HSI)contains a wealth of spectral information,which makes fine classification of ground objects possible.In the meanwhile,overly redundant information in HSI brings many challenges.Specifically,the lack of training samples and the high computational cost are the inevitable obstacles in the design of classifier.In order to solve these problems,dimensionality reduction is usually adopted.Recently,graph-based dimensionality reduction has become a hot topic.In this paper,the graph-based methods for HSI dimensionality reduction are summarized from the following aspects.1)The traditional graph-based methods employ Euclidean distance to explore the local information of samples in spectral feature space.2)The dimensionality-reduction methods based on sparse or collaborative representation regard the sparse or collaborative coefficients as graph weights to effectively reduce reconstruction errors and represent most important information of HSI in the dictionary.3)Improved methods based on sparse or collaborative graph have made great progress by considering global low-rank information,local intra-class information and spatial information.In order to compare typical techniques,three real HSI datasets were used to carry out relevant experiments,and then the experimental results were analysed and discussed.Finally,the future development of this research field is prospected.
基金supported by the National Natural Science Foundation of China(No.62001023)Beijing Natural Science Foundation(No.JQ20021)。
文摘Most methods for classifying hyperspectral data only consider the local spatial relation-ship among samples,ignoring the important non-local topological relationship.However,the non-local topological relationship is better at representing the structure of hyperspectral data.This paper proposes a deep learning model called Topology and semantic information fusion classification network(TSFnet)that incorporates a topology structure and semantic information transmis-sion network to accurately classify traditional Chinese medicine in hyperspectral images.TSFnet uses a convolutional neural network(CNN)to extract features and a graph convolution network(GCN)to capture potential topological relationships among different types of Chinese herbal medicines.The results show that TSFnet outperforms other state-of-the-art deep learning classification algorithms in two different scenarios of herbal medicine datasets.Additionally,the proposed TSFnet model is lightweight and can be easily deployed for mobile herbal medicine classification.
