Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
303
datasets available to search
ShareScore release 0.7.1
Dataset results
303 results for “hyperspectral”
Hyperspectral images of the beehive panel from Slovenia
<p>Four hyperspectral imaging cameras were used for scanning cultural heritage objects provided by the Slovenian Ethnographic Museum. The objects were beehive panels from the museum collection. HIS cameras used were: FX10, FX17, SWIR, MWIR, all produced by SPECIM. Hyperspectral image files include the standard output generated when acquiring hyperspectral images with the Lumo software tool (SPECIM), including white and dark references. These files can be open in diverse other tools, including Matlab. </p>
SiEUGreen - Data for 'Deep Learning in Hyperspectral Image Reconstruction from Single RGB images—A Case Study on Tomato Quality Parameters'
<p>Dataset used in the scientific publication <a href="https://zenodo.org/record/4671852">'Deep Learning in Hyperspectral Image Reconstruction from Single RGB images—A Case Study on Tomato Quality Parameters'</a>. The data includes chemical contents of tomatoes that was measured, images and scripts used in the paper. The scripts here aim to predict tomato quality parameters, sugar content, acidity, sugar acid ratio and lycopene, of automatically segmented tomato through hyperspectral image reconstruction from single RGB image. The same data can also be found at the <a href="https://github.com/ZJiangsan/TomatoQualityPredictionOnAutomaticallySegmentedTomato">Github repository</a>. The data collection and scientific paper was produced by SiEUGreen partners at Norwegian Institute of Bioeconomy Research (NIBIO).</p>
Raw hyperspectral imaging data of Baltic Sea algae cultures
<p>This file archive contains the raw data from hyperspectral imaging of Baltic sea algae cultures performed on 16th of August, 2018 at the hyperspectral imaging laboratory of the Faculty of Information Technology, University of Jyväskylä, Finland.</p> <p>The dataset contains images of cultures of the following algal species in various dilutions and mixes:</p> <ul> <li> <p>Diatoma tenuis DTTV-1401</p> </li> <li> <p>Melosira arctica MATV-1402</p> </li> <li> <p>Scrippsiella hangoei (aka Apocalathium malmogiense) SHTV-1</p> </li> <li> <p>Kryptopendinium foliaceum KFF-1001</p> </li> <li> <p>Monoraphidinium sp. TV70</p> </li> <li> <p>Chlorella pyrenoidosa TV216</p> </li> </ul> <p>In addition, the dataset includes images of pure water samples, empty petri dishes and millimeter paper useful for transmittance calculations and size measurement.</p> <p>The imaging setup consisted of living samples pipeted on glass Petri dishes, with a halogen light source illuminating the dish from the bottom towards the camera on top.</p> <p>The signal in each image contains slight fluctuation in the spectral dimension due to the AC current light source used.</p>
A dataset of ground-based vertical profile observations of aerosol, NO2 and HCHO from the hyperspectral vertical remote sensing network in China (2019-2023)
<p>Vertical <span>profile </span>observations of atmospheric composition are crucial for understanding the generation, evolution, and transport of regional air pollution. However, existing technological limitations and costs have resulted in a scarcity of vertical profil<span>e</span> data. This study <span>introduces </span>a high-<span>time-</span>resolution (approximately 15 minutes) dataset of vertical <span>profile </span>observations of atmospheric composition (aerosols, NO2, and HCHO) conducted using passive remote sensing technology across 32 sites in seven major regions of China from 2019 to 2023. The study meticulously documents the vertical distribution, seasonal <span>variations and </span>diurnal <span>pattern</span> of these pollutants, revealing long-term trends in atmospheric composition across various regions of China. This dataset provides essential scientific evidence for regional environmental management and policy-making. Its sharing <span>would </span>facilitate the scientific community <span>in </span>explor<span>ing</span> of source-receptor relationships, investigating the impacts of atmospheric composition on regional and global climate <span>and </span>feedback mechanisms.</p>
Hyperspectral Oblique Plane Microscopy - microparticles
<p>Processed spectra data for microparticle classification and raw hyperspectral images from mixture of microparticles</p>
Predicting medicinal phytochemicals of Moringa oleifera using hyperspectral reflectance of tree canopies
<p>Research article: <a href="https://doi.org/10.1080/01431161.2021.1887541">https://doi.org/10.1080/01431161.2021.1887541</a></p><p>New technique for processing hyperspectral data: 1)https://www.researchgate.net/publication/349663204_Computer_vision_and_hyperspectral_imagery_in_orchards_and_in_fields_Data_processing_and_analysis_methods</p><p>2)https://www.researchgate.net/profile/Vjacheslav-Fisenko/publication/349663204/figure/fig13/AS:1139984849485825@1648804976658/3-D-visualization-of-reflectance-spectra-of-four-medicinal-plant-genotypesPredicting_W640.jpg</p>
Surface plasmons-phonons for mid-infrared hyperspectral imaging
<p>Dataset for the hyperspectral imaging of spike proteins of the severe acute respiratory syndrome coronavirus (SARS-CoV) using the synergistic plasmon-phonon hyperspectral bioimaging system.</p>
PCB-Vision: A Multiscene RGB-Hyperspectral Benchmark Dataset of Printed Circuit Boards
<p><strong>PCB-Vision Dataset</strong></p> <p>Description:</p> <p>The PCB-Vision dataset is a multiscene RGB-Hyperspectral benchmark dataset comprising 53 Printed Circuit Boards (PCBs). The RGB images are collected using a Teledyne Dalsa C4020 camera on a conveyor belt, while hyperspectral images (HSI) are acquired with a Specim FX10 spectrometer. The HSI data contains 224 bands in the VNIR range [400 - 1000]nm.</p> <p><strong>Data Format</strong></p> <ul> <li>RGB Images: .png files</li> <li>PCB Masks: .jpg files</li> <li>HSI Data: Each hyperspectral data cube is accompanied by a data file and a .hdr file.</li> </ul> <p><strong>Folder Organization</strong></p> <ul> <li>PCBVision <ul> <li>HSI/ <ul> <li>53 subfolders (one for each PCB)</li> <li>'General_masks' folder for 'General' segmentation ground truth</li> <li>'Monoseg_masks' folder for 'Monoseg' segmentation ground truth</li> <li>'PCB_Masks' folder for masks of the 53 PCBs in the hyperspectral cube</li> </ul> </li> <li>RGB/ <ul> <li>53 .jpg images</li> <li>'General' folder for RGB images 'General' segmentation ground truth</li> <li>'Monoseg_masks' folder for RGB images 'Monoseg' segmentation ground truth</li> </ul> </li> </ul> </li> </ul> <p><strong>Data Classes in Masks</strong></p> <ul> <li>Masks (both 'General' and 'Monoseg') contain 1 to 4 segmentation classes: <ul> <li>0: "Others"</li> <li>1: "IC"</li> <li>2: "Capacitors"</li> <li>3: "Connectors"</li> </ul> </li> </ul> <p><strong>Code Repository</strong></p> <p>To facilitate reading and working with the data, Python codes are available on the GitHub repository:</p> <p>https://github.com/hifexplo/PCBVision</p> <p><strong>Citation</strong></p> <p>If you use this dataset, please cite the following article:</p> <p><strong>Word</strong>:</p> <p>Arbash, Elias, Fuchs, Margret, Rasti, Behnood, Lorenz, Sandra, Ghamisi, Pedram, & Gloaguen, Richard. (2024). PCB-Vision: A Multiscene RGB-Hyperspectral Benchmark Dataset of Printed Circuit Boards (Version 1) [Data set]. Rodare. <a href="http://doi.org/10.14278/rodare.2704">http://doi.org/10.14278/rodare.2704</a></p> <p><strong>Latex:</strong></p> <p>@article{arbash2024pcb, title={PCB-Vision: A Multiscene RGB-Hyperspectral Benchmark Dataset of Printed Circuit Boards}, author={Arbash, Elias and Fuchs, Margret and Rasti, Behnood and Lorenz, Sandra and Ghamisi, Pedram and Gloaguen, Richard}, journal={arXiv preprint arXiv:2401.06528}, year={2024} }</p> <p><strong>Contact</strong></p> <p>For further information or inquiries, please visit our website:</p> <p>https://www.iexplo.space/</p> <p>Contact Email: e.arbash@hzdr.de</p>
Hyperspectral and Polarization images of an experimental oil painting
<p>This repository contains 4 hyperspectral images in the VNIR range (400 - 1000 nm) and 4 hyperspectral images in the SWIR range (1000 - 2500 nm) of an experimental oil painting.</p> <p>Each scene (P0,P1,P2,P3) is associated with the capturing with a linear polarization filter placed in front of the hyperspectral cameras. The rotation angles of the polarizers are found in the spreadsheet 'theta.xlsx'</p> <p>Please cite as:</p> <p>Grillini, Federico, et al. "Relationship between reflectance and degree of polarization in the VNIR-SWIR: A case study on art paintings with polarimetric reflectance imaging spectroscopy." <em>PloS one</em> 19.5 (2024): e0303018.</p>
Classification and identification of pinecones mulching on blueberry cultivation based on crop leaf characteristics and hyperspectral data
<p><span>Supplementary Figure S1: Spectra preprocessing before and after.; Table S1: The evaluation results of the classification model of leaf growth and physiology.; Table S2: The evaluation results of the classification model of VIs.; Table S3: The evaluation results of the classification model of VNIR.; Table S4: The evaluation results of the classification model of SWIR.</span></p>
GlioHyper: Glioma Biopsy Hyperspectral Dataset
<p>A dataset of glioma biopsies which were examined using hyperspectral imaging. The details of the acquisition protocol and description of the data are provided in the accompaniying paper:</p> <p>"A transportable hyperspectral imaging setup based on fast, high-density spectral scanning for in situ quantitative biochemical mapping of fresh tissue biopsies", Luca Giannoni et. al.</p> <p> </p>
HYPERSPECTRAL DATASET OF PURE,LOW,MEDIUM AND HIGH INSECTICIDE CONCENTRATION IN LADY'SFINGER
<p>Hyperspectral Dataset of Ladysfinger immersed in Pure , Low, Medium, High concentration of insecticide. </p> <p>The dataset consists of hyperspectral images of ladysfinger immersed in various concentration of fertilizer. They are divided into four categories:</p> <p>1."Pure_ladysfinger" - images of ladysfinger bought from organic shops.<br>2."Low_concentration_insecticide_ladysfinger" - images of ladysfinger immersed in insecticide(M power) solution at low concentration level i.e 1g or 1ml of fertilizer in 1 liter water and <br>3."Medium_concentration_insecticide_ladysfinger" - images of ladysfinger immersed in insecticide(M power) solution at low concentration level i.e 3g or 3ml of fertilizer in 1 liter water and <br>4. "High_concentration_insecticide_ladysfinger"- images of ladysfinger immersed in insecticide(M power) solution at low concentration level i.e 5g or 5ml of fertilizer in 1 liter water and </p> <p>The hyperspectral images are saved by default in .bil format. This dataset is converted into .tiff format.</p> <p>The entire dataset is classified in four folders.1. Pure, 2. Low, 3. Medium, 4. High.It has 2 folders pure and M power fertilizer, which in turn is classified into High,Medium and Low insecticide sprayed ladysfinger. <br>Pure folder consist of 175 images. <br>Low concentration consist of 220 images and immersed in low concentration solution. The insecticide used for this experiment is m power(fipronil 2.92% W/W EC).<br>Medium concentration consist of 100 images and immersed in medium concentration solution. The insecticide used for this experiment is m power(fipronil 2.92% W/W EC).<br>Similarly, High concentration consist of 120 images and immersed in high concentration solution. The insecticide used for this experiment is M power(fipronil 2.92% W/W EC).This dataset contains 2 bil images of each class. and Pure ,Medium,Low and High images are represented with a prefix of p,m,l and h respective </p> <p> </p>
Hyperspectral images of patches at different stages of degraded alpine meadows
<p>This data contains hyperspectral images of degraded alpine meadow patches in four stages, which are:active patches (Stage 0), inactive patches (Stage 1), recovering patches (Stage 2), and healthy alpine meadow (Stage 3).</p>
MUESLI Hyperspectral & LiDar Data Set
<p>The data set contain the hyperspectral images and the corresponding LiDar data from the MUESLI project.</p> <p>The meta data is included in the tif files. For the spectral bands, a copy of the original hdr file is below:</p> <p>fwhm = {4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,4.5,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25,6.25}<br> wavelength = {414.681622,418.320307,421.958992,425.597676,429.236361,432.875046,436.513731,440.152415,443.7911,447.429785,451.06847,454.707155,458.345839,461.984524,465.623209,469.261894,472.900578,476.539263,480.177948,483.816633,487.455317,491.094002,494.732687,498.371372,502.010056,505.648741,509.287426,512.926111,516.564796,520.20348,523.842165,527.48085,531.119535,534.758219,538.396904,542.035589,545.674274,549.312958,552.951643,556.590328,560.229013,563.867697,567.506382,571.145067,574.783752,578.422437,582.061121,585.699806,589.338491,592.977176,596.61586,600.254545,603.89323,607.531915,611.170599,614.809284,618.447969,622.086654,625.725338,629.364023,633.002708,636.641393,640.280078,643.918762,647.557447,651.196132,654.834817,658.473501,662.112186,665.750871,669.389556,673.02824,676.666925,680.30561,683.944295,687.582979,691.221664,694.860349,698.499034,702.137719,705.776403,709.415088,713.053773,716.692458,720.331142,723.969827,727.608512,731.247197,734.885881,738.524566,742.163251,745.801936,749.44062,753.079305,756.71799,760.356675,763.99536,767.634044,771.272729,774.911414,778.550099,782.188783,785.827468,789.466153,793.104838,796.743522,800.382207,804.020892,807.659577,811.298261,814.936946,818.575631,822.214316,825.853,829.491685,833.13037,836.769055,840.40774,844.046424,847.685109,851.323794,854.962479,858.601163,862.239848,865.878533,869.517218,873.155902,876.794587,880.433272,884.071957,887.710641,891.349326,894.988011,898.626696,902.265381,905.904065,909.54275,913.181435,916.82012,920.458804,924.097489,927.736174,931.374859,935.013543,938.652228,942.290913,945.929598,949.568282,953.206967,956.845652,960.484337,964.123022,967.761706,971.400391,977.281135,982.74497,988.208806,993.672641,999.136476,1004.600311,1010.064146,1015.527981,1020.991816,1026.455651,1031.919486,1037.383321,1042.847156,1048.310991,1053.774826,1059.238662,1064.702497,1070.166332,1075.630167,1081.094002,1086.557837,1092.021672,1097.485507,1102.949342,1108.413177,1113.877012,1119.340847,1124.804682,1130.268518,1135.732353,1141.196188,1146.660023,1152.123858,1157.587693,1163.051528,1168.515363,1173.979198,1179.443033,1184.906868,1190.370703,1195.834538,1201.298374,1206.762209,1212.226044,1217.689879,1223.153714,1228.617549,1234.081384,1239.545219,1245.009054,1250.472889,1255.936724,1261.400559,1266.864394,1272.32823,1277.792065,1283.2559,1288.719735,1294.18357,1299.647405,1305.11124,1310.575075,1316.03891,1321.502745,1326.96658,1332.430415,1337.89425,1343.358086,1348.821921,1354.285756,1359.749591,1365.213426,1370.677261,1376.141096,1381.604931,1387.068766,1392.532601,1397.996436,1403.460271,1408.924106,1414.387942,1419.851777,1425.315612,1430.779447,1436.243282,1441.707117,1447.170952,1452.634787,1458.098622,1463.562457,1469.026292,1474.490127,1479.953962,1485.417798,1490.881633,1496.345468,1501.809303,1507.273138,1512.736973,1518.200808,1523.664643,1529.128478,1534.592313,1540.056148,1545.519983,1550.983818,1556.447654,1561.911489,1567.375324,1572.839159,1578.302994,1583.766829,1589.230664,1594.694499,1600.158334,1605.622169,1611.086004,1616.549839,1622.013674,1627.477509,1632.941345,1638.40518,1643.869015,1649.33285,1654.796685,1660.26052,1665.724355,1671.18819,1676.652025,1682.11586,1687.579695,1693.04353,1698.507365,1703.971201,1709.435036,1714.898871,1720.362706,1725.826541,1731.290376,1736.754211,1742.218046,1747.681881,1753.145716,1758.609551,1764.073386,1769.537221,1775.001057,1780.464892,1785.928727,1791.392562,1796.856397,1802.320232,1807.784067,1813.247902,1818.711737,1824.175572,1829.639407,1835.103242,1840.567077,1846.030913,1851.494748,1856.958583,1862.422418,1867.886253,1873.350088,1878.813923,1884.277758,1889.741593,1895.205428,1900.669263,1906.133098,1911.596933,1917.060769,1922.524604,1927.988439,1933.452274,1938.916109,1944.379944,1949.843779,1955.307614,1960.771449,1966.235284,1971.699119,1977.162954,1982.626789,1988.090625,1993.55446,1999.018295,2004.48213,2009.945965,2015.4098,2020.873635,2026.33747,2031.801305,2037.26514,2042.728975,2048.19281,2053.656645,2059.120481,2064.584316,2070.048151,2075.511986,2080.975821,2086.439656,2091.903491,2097.367326,2102.831161,2108.294996,2113.758831,2119.222666,2124.686501,2130.150337,2135.614172,2141.078007,2146.541842,2152.005677,2157.469512,2162.933347,2168.397182,2173.861017,2179.324852,2184.788687,2190.252522,2195.716357,2201.180193,2206.644028,2212.107863,2217.571698,2223.035533,2228.499368,2233.963203,2239.427038,2244.890873,2250.354708,2255.818543,2261.282378,2266.746213,2272.210049,2277.673884,2283.137719,2288.601554,2294.065389,2299.529224,2304.993059,2310.456894,2315.920729,2321.384564,2326.848399,2332.312234,2337.776069,2343.239905,2348.70374,2354.167575,2359.63141,2365.095245,2370.55908,2376.022915,2381.48675,2386.950585,2392.41442,2397.878255,2403.34209,2408.805925,2414.269761,2419.733596,2425.197431,2430.661266,2436.125101,2441.588936,2447.052771,2452.516606,2457.980441,2463.444276,2468.908111,2474.371946,2479.835781,2485.299617,2490.763452,2496.227287,2501.691122,2507.154957,2512.618792,2518.082627,2523.546462}</p> <p> </p> <p> </p> <p> </p>
Sedimentary structure discrimination with hyperspectral imaging in sediment cores
<p>The LDB17_P11Ax (IGSN: TOAE0000000243); Datation Age 1040 +/- 30 to 2017 CE by core correlation, 14C, lamina counting) core from the Bourget Lake (France) was analyzed in 2018 by hyperspectral imaging. We studied the potential of hyperspectral sensor to image a sediment cores and created machine learning models. The hyperspectral images were acquired in order to develop quantitative (estimating particle size and loss on ignition) and qualitative (detection of instantaneous events or lamina) methods.<br> All these methods allow to reconstruct the past environment and climate at high resolution (pixel size: 50-250 microns) and without destroying the sample for archiving for future analysis.<br> These images have been valorized in publications for the detection of instantaneous events with hyperspectral and combined with XRF data, for the combination of the two images into a composite image.<br> image (.hdr, .dat, .jpg)</p>
Hyperspectral X-ray CT dataset of a single, iodine-stained lizard head sample
<p><strong>General Data description:</strong></p> <p>This is a hyperspectral (energy-resolved) X-ray CT projection dataset of a lizard head sample, stained with an iodine contrast agent. It was acquired in a custom-built, laboratory micro-CT scanner with an energy-sensitive HEXITEC detector in the Henry Moseley X-ray Imaging Facility at The University of Manchester.</p> <p>The following data contains all the files necessary for reconstruction, after a hyperspectral scan was taken of a single, iodine-stained lizard head sample. The iodine contrast agent provided a spectral marker, measured by an energy-sensitive detector, which may be used for spatial mapping and segmentation of stained soft tissue regions.</p> <p><strong>File descriptions:</strong></p> <p>Contained are four MATLAB (.mat) data files, as well as a single text (.txt) file.</p> <p>Lizard_head_scan_parameters.txt provides the full sample and detector geometry of the scan acquisition.</p> <p>lizard_180Proj_noSupp_1_180.mat contains the full 4D sinogram constructed following flatfield normalisation of the raw projection data. The 4D array contains the total number of energy channels acquired during scanning, vertical and horizontal pixel number, and total projections angles acquired. The data provided is prior to application of any post-processing filters. The first 180 energy channels are included.</p> <p>lizard_180Proj_Supp_1_180.mat contains the full 4D sinogram constructed following flatfield normalisation of the raw projection data. This dataset is identical to the .mat file above, however here we have also applied a ring-reduction filter, using a wavelet-based Fourier filter which suppresses the presence of ring artefacts in every energy channel. The first 180 energy channels are included.</p> <p>Energy_axis.mat provides a direct conversion between the energy channels, and the energies (in keV) that they correspond to, following a calibration procedure prior to scanning.</p> <p>FF.mat contains the 4D flatfield data acquired when no sample was present. This data was used to normalise the projection datasets, as the sinogram was constructed. The first 180 energy channels are included.</p>
Image dataset: Applicability of hyperspectral imaging during salinity stress in rice for tracking Na+ and K+ levels in planta
<p>The ratio of Na<sup>+</sup> and K<sup>+</sup> is an important determinant of the magnitude of Na<sup>+</sup> toxicity and osmotic stress in plant cells. Traditional analytical approaches involve destructive tissue sampling and chemical analysis, where real-time observation of spatio-temporal experiments across genetic or breeding populations is unrealistic. Such an approach can also be very inaccurate and prone to erroneous biological interpretation. Analysis by Hyperspectral Imaging (HSI) is an emerging non-destructive alternative for tracking plant nutrient status in a time-course with higher accuracy and reduced cost for chemical analysis. In this study, the feasibility and predictive power of HSI-based approach for spatio-temporal tracking of Na<sup>+</sup> and K<sup>+</sup> levels in tissue samples was explored using a panel recombinant inbred line (RIL) of rice (Oryza sativa L.; salt-sensitive IR29 x salt-tolerant Pokkali) with differential activities of the Na<sup>+</sup> exclusion mechanism conferred by the SalTol QTL. In this panel of RILs the spectrum of salinity tolerance was represented by FL499 (super-sensitive), FL454 (sensitive), FL478 (tolerant), and FL510 (super-tolerant). Whole-plant image processing pipeline was optimized to generate HSI spectra during salinity stress at EC = 9 dS m<sup>-1</sup>. Spectral data was used to create models for Na<sup>+</sup> and K<sup>+</sup> prediction by partial least squares regression (PLSR). Three datasets, i.e., mean image pixel spectra, smoothened version of mean image pixel spectra, and wavelength bands, with wide differences in intensity between control and salinity facilitated the prediction models with high R<sup>2</sup>. The smoothened and filtered datasets showed significant improvements over the mean image pixel dataset. However, model prediction was not fully consistent with the empirical data. While the outcome of modeling-based prediction showed a great potential for improving the throughput capacity for salinity stress phenotyping, additional technical refinements including tissue-specific measurements is necessary to maximize the accuracy of prediction models.</p>
Hyperspectral Pigments
<p>Hyperspectral dataset made of individual pigment patches, useful for the quality evaluation or validation of spectral image processing algorithms, e.g., classification. This dataset is published in the following upcoming conference article:</p> <p><strong>H. Deborah. 2022. <em>Hyperspectral Pigment Dataset. </em>12th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS). </strong></p> <p>An interactive explorer of the spectral library portion of this whole dataset can be accessed <a href="https://hyppigments.streamlit.app/">here</a>.</p>
Hyperspectral X-ray CT Voxelized TV reconstruction of a single, iodine-stained lizard head sample
<p><strong>Dataset description</strong></p> <p>These datasets are voxel based reconstructions of hyperspectral CT data using the Core Imaging Library (CIL). They are stored as NeXus files (derived from hdf5) which can be read in, visualised and manipulated using CIL.</p> <p> - PDHG_TV_1000_Sp_alpha_0.004.nxs</p> <p>Is the solution after 1000 iterations of PDHG with TV applied in the spatial domain. </p> <p> - PDHG_TV_1000_SpCh_alpha_0.003_beta_0.5.nxs</p> <p>Is the solution after 1000 iterations of PDHG with TV applied both in the spatial domain, and in the energy (channel) domain. </p> <p> </p> <p><strong>Dataset intended use</strong></p> <p>These datasets are used in the CIL training notebook:</p> <p>https://github.com/TomographicImaging/CIL-Demos/blob/main/examples/3_Multichannel/03_Hyperspectral_reconstruction.ipynb</p> <p>They can be imported using CIL, with the following code snippet:</p> <pre><code class="language-python">from cil.io import NEXUSDataReader reader = NEXUSDataReader(file_name='path/to/data/PDHG_TV_1000_Sp_alpha_0.004.nxs') data = reader.read()</code></pre> <p> </p>
HSICityV2: Urban Scene Understanding via Hyperspectral Images
<p>Light in all spectrum travel in the physical world. The trichromatism (RGB) human vision captures and understands it. Machine vision makes an analogy which use RGB camera for semantic segmentation and scene understanding. We argue that such machine vision suffers from metamerism, that different objects may appear in same RGB color while actually distinctive in spectrum. While learning based solutions, especially deep learning, have been heavily explored, they do not solve the fundamental physical limitation. In this paper, we propose to use Hyperspectral images (HSIs), which capture hundreds of consecutive narrow bands from the real visible world and therefore metamerism no longer exists. In short, we aim to 'see beyond human vision'. In practice, we introduce a novel large scale high quality HSI dataset for semantic segmentation in cityscapes. Namely, Hyperspectral City dataset. The dataset contains 1330 HSIs which are captured in typical urban driving scenes. Each HSI has 1889×1422 spatial resolution and 128 spectral channels ranged from 450nm to 950nm. The dataset provides semantic annotation at pixel level which is done manually by professional annotators. We believe this dataset enables a new direction for scene understanding.</p>
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.