- 标题
- 摘要
- 关键词
- 实验方案
- 产品
过滤筛选
- 2018
- Fruit defects
- Jujube
- Principal component analysis
- Hyperspectral imaging
- hyperspectral images
- spectral and spatial features
- classification
- SVM
- mutual information
- GLCM
- Optoelectronic Information Science and Engineering
- Mohammed V University in Rabat
- Southern Taiwan University of Science and Technology
-
Variety Identification of Raisins Using Near-Infrared Hyperspectral Imaging
摘要： Different varieties of raisins have different nutritional properties and vary in commercial value. An identification method of raisin varieties using hyperspectral imaging was explored. Hyperspectral images of two different varieties of raisins (Wuhebai and Xiangfei) at spectral range of 874–1734 nm were acquired, and each variety contained three grades. Pixel-wise spectra were extracted and preprocessed by wavelet transform and standard normal variate, and object-wise spectra (sample average spectra) were calculated. Principal component analysis (PCA) and independent component analysis (ICA) of object-wise spectra and pixel-wise spectra were conducted to select effective wavelengths. Pixel-wise PCA scores images indicated differences between two varieties and among different grades. SVM (Support Vector Machine), k-NN (k-nearest Neighbors Algorithm), and RBFNN (Radial Basis Function Neural Network) models were built to discriminate two varieties of raisins. Results indicated that both SVM and RBFNN models based on object-wise spectra using optimal wavelengths selected by PCA could be used for raisin variety identification. The visualization maps verified the effectiveness of using hyperspectral imaging to identify raisin varieties.
关键词： object-wise,pixel-wise,support vector machine,near-infrared hyperspectral imaging,raisins
更新于2025-09-23 15:21:21
-
Hyperspectral image classification via compact-dictionary-based sparse representation
摘要： In this paper, a compact-dictionary-based sparse representation (CDSR) method is proposed for hyperspectral image (HSI) classification. The proposed dictionary in CDSR is dynamically generated according to the spatial and spectral context of each pixel. It can effectively shrink the decision range for classification, and reduce the computational burden since the compact dictionary is composed of the classes correlated with the target pixel in terms of spatial location and spectral information. In order to obtain better spatial context information, a spatial location expanding strategy is designed for spreading local explicit label information to a wider region. Experimental results demonstrate the effectiveness and superiority of the proposed method when compared with some widely used HSI classification approaches.
关键词： Compact dictionary,Hyperspectral image,Sparse representation,Classification
更新于2025-09-23 15:21:21
-
Non-Lorentzian Local Density of States in Coupled Photonic Crystal Cavities Probed by Near- and Far-Field Emission
摘要： Recent theories proposed a deep revision of the well-known expression for the Purcell factor, with counterintuitive effects, such as complex modal volumes and non-Lorentzian local density of states. We experimentally demonstrate these predictions in tailored coupled cavities on photonic crystal slabs with relatively low optical losses. Near-field hyperspectral imaging of quantum dot photoluminescence is proved to be a direct tool for measuring the line shape of the local density of states. The experimental results clearly evidence non-Lorentzian character, in perfect agreement with numerical and theoretical predictions. Spatial maps with deep subwavelength resolution of the real and imaginary parts of the complex mode volumes are presented. The generality of these results is confirmed by an additional set of far-field and time-resolved experiments in cavities with larger modal volume and higher quality factors.
关键词： non-Lorentzian local density of states,Purcell factor,quantum dot photoluminescence,photonic crystal cavities,near-field hyperspectral imaging
更新于2025-09-23 15:21:01
-
Silk fibroin enabled optical fiber methanol vapor sensor
摘要： The linear mixture model (LMM) plays a crucial role in the spectral unmixing of hyperspectral data. Under the assumption of LMM, the solution with the minimum reconstruction error is considered to be the ideal endmember. However, for practical hyperspectral data sets, endmembers that enclose all the pixels are physically meaningless due to the effect of noise. Therefore, in many cases, it is not sufficient to consider only the reconstruction error, some constraints (for instance, volume constraint) need to be added to the endmembers. The two terms can be considered as serving two forces: minimizing the reconstruction error forces the endmembers to move outward the simplex while the endmember constraint acts in the opposite direction by driving the endmembers to move inward so as to constrain the volume to be smaller. Many existing methods obtain their solution just by balancing the two contradictory forces. The solution acquired in this way can not only minimize the reconstruction error but also be physically meaningful. Interestingly, we find, in this paper, that the two forces are not completely contradictory with each other, and the reconstruction error can be further reduced without changing the volume of the simplex. And more interestingly, our method can further optimize the solution provided by all the endmember extraction methods (both endmember selection methods and endmember generation methods). After optimization, the final endmembers outperform the initial solution in terms of reconstruction error as well as accuracy. The experiments on simulated and real hyperspectral data verify the validation of our method.
关键词： Hyperspectral data,volume,endmember,LMM,simplex
更新于2025-09-23 15:21:01
-
Temperature and Emissivity Inversion Accuracy of Spectral Parameter Changes and Noise of Hyperspectral Thermal Infrared Imaging Spectrometers
摘要： The emergence of hyperspectral thermal infrared imaging spectrometers makes it possible to retrieve both the land surface temperature (LST) and the land surface emissivity (LSE) simultaneously. However, few articles focus on the problem of how the instrument?s spectral parameters and instrument noise level affect the LST and LSE inversion errors. In terms of instrument development, this article simulated three groups of hyperspectral thermal infrared data with three common spectral parameters and each group of data includes tens of millions of simulated radiances of 1525 emissivity curves with 17 center wavelength shift ratios, 6 full width at half maximum (FWHM) change ratios and 6 noise equivalent differential temperatures (NEDTs) under 15 atmospheric conditions with 6 object temperatures, inverted them by two temperature and emissivity separation methods (ISSTES and ARTEMISS), and analyzed quantitatively the effects of the spectral parameters change and noise of an instrument on the LST and LSE inversion errors. The results show that: (1) center wavelength shifts and noise affect the inversion errors strongly, while FWHM changes affect them weakly; (2) the LST and LSE inversion errors increase with the center wavelength shift ratio in a quadratic function and increase with FWHM change ratio slowly and linearly for both the inversion methods, however they increase with NEDT in an S‐curve for ISSTES while they increase with NEDT slightly and linearly for ARTEMISS. During the design and development of a hyperspectral thermal infrared instrument, it is highly recommended to keep the potential center wavelength shift within 1 band and keep NEDT within 0.1K (corresponding LST error < 1K and LSE error < 0.015) for normal applications and within 0.03K (corresponding LST error < 0.5K and LSE error < 0.01) for better application effect and level.
关键词： inversion error,hyperspectral thermal infrared,FWHM change,instrument noise,center wavelength shift,temperature and emissivity separation
更新于2025-09-23 15:21:01
-
Hyperspectral band selection using genetic algorithm and support vector machines for early identification of charcoal rot disease in soybean stems
摘要： Background: Charcoal rot is a fungal disease that thrives in warm dry conditions and affects the yield of soybeans and other important agronomic crops worldwide. There is a need for robust, automatic and consistent early detection and quantification of disease symptoms which are important in breeding programs for the development of improved cultivars and in crop production for the implementation of disease control measures for yield protection. Current methods of plant disease phenotyping are predominantly visual and hence are slow and prone to human error and variation. There has been increasing interest in hyperspectral imaging applications for early detection of disease symptoms. However, the high dimensionality of hyperspectral data makes it very important to have an efficient analysis pipeline in place for the identification of disease so that effective crop management decisions can be made. The focus of this work is to determine the minimal number of most effective hyperspectral wavebands that can distinguish between healthy and diseased soybean stem specimens early on in the growing season for proper management of the disease. 111 hyperspectral data cubes representing healthy and infected stems were captured at 3, 6, 9, 12, and 15 days after inoculation. We utilized inoculated and control specimens from 4 different genotypes. Each hyperspectral image was captured at 240 different wavelengths in the range of 383–1032 nm. We formulated the identification of best waveband combination from 240 wavebands as an optimization problem. We used a combination of genetic algorithm as an optimizer and support vector machines as a classifier for the identification of maximally-effective waveband combination. Results: A binary classification between healthy and infected soybean stem samples using the selected six waveband combination (475.56, 548.91, 652.14, 516.31, 720.05, 915.64 nm) obtained a classification accuracy of 97% for the infected class. Furthermore, we achieved a classification accuracy of 90.91% for test samples from 3 days after inoculation using the selected six waveband combination. Conclusions: The results demonstrated that these carefully-chosen wavebands are more informative than RGB images alone and enable early identification of charcoal rot infection in soybean. The selected wavebands could be used in a multispectral camera for remote identification of charcoal rot infection in soybean.
关键词： Band selection,Soybean disease,Precision agriculture,Hyperspectral,Support vector machines,Genetic algorithm,Charcoal rot
更新于2025-09-23 15:21:01
-
Hierarchical Sub-Pixel Anomaly Detection Framework for Hyperspectral Imagery
摘要： Anomaly detection is an important task in hyperspectral processing. Some previous works, based on statistical information, focus on Reed-Xiaoli (RX), as it is one of the most classical and commonly used methods. However, its performance tends to be affected when anomaly target size is smaller than spatial resolution. Those sub-pixel anomaly target spectra are usually much similar with background spectra, and may results in false alarm for traditional RX method. To address this issue, this paper proposes a hierarchical RX (H-RX) anomaly detection framework to enhance the performance. The proposed H-RX method consists of several different layers of original RX anomaly detector. In each layer, the RX’s output of each pixel is restrained by a nonlinear function and then imposed as a coef?cient on its spectrum for the next iteration. Furthermore, we design a spatial regularization layer to enhance the sub-pixel anomaly detection performance. To better illustrate the hierarchical framework, we provide a theoretical explanation of the hierarchical background spectra restraint and regularization process. Extensive experiments on three hyperspectral images illustrate that the proposed anomaly detection algorithm outperforms the original RX algorithm and some other classical methods.
关键词： hyperspectral image (HSI) analysis,RX,hierarchical structure,anomaly detection
更新于2025-09-23 15:21:01
-
[IEEE 2018 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR) - Chengdu, China (2018.7.15-2018.7.18)] 2018 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR) - Spectral-Spatial Graph Convolutional Networks for Semel-Supervised Hyperspectral Image Classification
摘要： Collecting label samples is quite costly and time consuming for hyperspectral image (HSI) classification tasks. Semi-supervised learning framework, which combines the intrinsic information of labeled and unlabeled samples can alleviate the deficient labeled samples and increase the accuracy of HSI classification. In this paper, we propose a novel framework for semi-supervised learning on multiple spectral-spatial graphs that is based on graph convolutional networks (SGCN). In the filtering operation on graphs we consider the spatial information and spectral signatures of HSI simultaneously. The experimental results on three real-life HSI data sets, i.e. Botswana Hyperion, Kennedy Space Center, and Indian Pines, show that the proposed SGCN can significantly improve the classification accuracy. For instance, the over accuracy on Indian Pine data is increased from 78% to 93%.
关键词： Hyperspectral image classification,Graph fourier transform,Graph convolutional,Neural networks,Semi-supervised learning
更新于2025-09-23 15:21:01
-
The long-wave infrared (8-12 μm) spectral features of selected rare earth element—Bearing carbonate, phosphate and silicate minerals
摘要： Rare earth elements (REEs) are a group of metals essential to high technology industries. This high demand, combined with a high supply risk, has led to an understanding that REEs are critical to society. Despite the potential that hyperspectral imaging (HSI) data offers for a fast and non-invasive characterization of the REEs, it is still poorly understood whether REEs have some information in the long-wave infrared (LWIR; 8–12 μm) wavelength range that can be used for their identification. To partially fill this gap, we have investigated the spectroscopy of twelve REE-bearing mineral samples using relatively high spatial and spectral resolution LWIR hyperspectral imaging data. These samples were formerly characterized using electron probe microanalysis (EPMA), scanning electron microscopy (SEM), and hyperspectral imaging data acquired in the 0.4–2.5 μm wavelength range. Results from these analyses were compared to and used to guide the analysis of the HSI data recorded in the LWIR range. This information was further compared to a reference spectral library of rare earth oxides. Our findings suggest that the spectral features of the samples can generally be traced to the asymmetric degenerate stretching and bending modes of the X-O (X = C, Si, P) groups. Moreover and contrary to what has been observed in the shorter wavelengths, there are no definitive spectral features in the LWIR wavelength region that could be assigned to any specific REE.
关键词： Imaging spectroscopy,Long-wave infrared,Rare earth element,Hyperspectral,Mineral
更新于2025-09-23 15:21:01
-
KNN-Based Representation of Superpixels for Hyperspectral Image Classification
摘要： Superpixel segmentation has been demonstrated to be a powerful tool in hyperspectral image (HSI) classification. Each superpixel region can be regarded as a homogeneous region, which is composed of a series of spatial neighboring pixels. However, a superpixel region may contain the pixels from different classes. To further explore the optimal representations of superpixels, a new framework based on two k selection rules is proposed to find the most representative training and test samples. The proposed method consists of the following four steps: first, a superpixel segmentation algorithm is performed on the HSI to cluster the pixels with similar spectral features into the same superpixel. Then, a domain transform recursive filtering is used to extract the spectral–spatial features of the HSI. Next, the k nearest neighbor (KNN) method is utilized to select k1 representative training samples and k2 test pixels for each superpixel, which can effectively overcome the within-class variations and between-class interference, respectively. Finally, the class label of superpixels can be determined by measuring the averaged distances among the selected training and test samples. Experiments conducted on four real hyperspectral datasets show that the proposed method provides competitive classification performances with respect to several recently proposed spectral–spatial classification methods.
关键词： superpixel segmentation,hyperspectral image classification,k nearest neighbor (KNN),Domain transform recursive filtering (RF)
更新于2025-09-23 15:21:01