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.
979
datasets available to search
ShareScore release 0.9.0
Dataset results
979 results for “Image Dataset”
NutriGreen Image Dataset: A Collection of Annotated Nutrition, Organic, and Vegan Food Products
<p>The generated dataset is an annotated collection, with each image carrying labels (NutriScore, V-label and Bio). The presence of annotated data is essential for developing a supervised machine-learning model capable of automatically identifying labels in new images. In our case, we utilize this data to train a model that can autonomously recognize labels on new images not present in the dataset, achieving a model accuracy of 94%. In the future, you have the option to train a new model using the dataset to achieve higher accuracy or employ the existing model to automatically identify bio and nutri labels in newly collected images, eliminating the need for manual review. We should emphasize that these resources should be utilized by a data science team. There is an opportunity for this model to be integrated with a mobile app, but this is a direction for future work, we included in the revised version.</p> <p>In this research, we introduce the NutriGreen dataset, which is a collection of images representing packaged food products. Each image in the dataset comes with three distinct labels: one indicating its nutritional value using the Nutri-Score, another denoting whether it's vegan or vegetarian with the V-label, and a third displaying the EU organic certification (BIO) logo. The dataset comprises a total of 10,472 images. Among these, the Nutri-Score label is distributed across five sub-labels: A with 1,250 images, B with 1,107 images, C with 867 images, D with 1,001 images, and E with 967 images. Additionally, there are 870 images featuring the V-Label, 2,328 images showcasing the BIO label, and 3201 images with no labels. Furthermore, we have fine-tuned the YOLOv5 model to demonstrate the practicality of using these annotated datasets, achieving an impressive accuracy of 94.0%. These promising results indicate that this dataset has significant potential for training innovative systems capable of detecting food labels. Moreover, it can serve as a valuable benchmark dataset for emerging computer vision systems.</p> <p> </p> <p> </p>
WhiteRoadLines: Dataset of 27,025 images (256x256 pixeles at 0.15 m/ pixel) containing representative road lines and markings labelled for multi-class semantic segmentation
<p>The dataset consists of 27,025 PNG images (256x256 pixels) of high resolution aerial orthoimages at 0,15 m/pixel of resolution. The images contain information related to representative road lines and markings found on highway pavement and is labelled for multi-class semantic segmentation with tree classes of white road<br>lines and markings: (1) continuous line (black color), (2) dashed line (dark gray color) and (3) separation of entry and exit lanes (light gray color), together with (4) the background (white color). <br> </p><p>The dataset has been created in the framework of the SROADEX project to train a multiclass semantic segmentation process based on Deep Learning.<br>The data have been generated using scripts developed in Python using Open Source libraries (GDAL/OGR and MapScript) for rasterization of vector cartography representing the three different types of white road lines. This cartography has been obtained from Spanish official sources (National Geographic Institute) that we have<br>revised and edited in a meticulous and systematic way to verify that the road lines are represented on the cartography according to the orthoimages, available on January 1, 2022 in the download center of the National Center of Geographic Information (CNIG). </p><p>In the digitisation process, 46 homogeneously distributed areas of Spain have been selected. The orthoimages used have been resampled from the original resolution of 0,25m/pixel to 0,15m/pixel, as this is closer to the width of two of the three classes of white lines in the dataset. It resulted in 80% of the images for training (21622), 10% for validation (2702) and 10% for testing (2701). The following table summarises the number of pixels of each category included in each of the three sub-datasets</p><p> </p><p>Set Nº images Class_1 (continuous line) Class_2 (discontinuous line) Class_3 (line defining highway entrance or exit) Class_4 (background)</p><p>Train 21,622 27,633,537 4,543,552 3,284,380 1,381,557,923</p><p>Validation 2,702 3,433,103 570,741 395,646 172,678,782</p><p>Test 2,701 3,435,072 536,838 429,527 172,611,299</p><p>Total 27,025 34,501,712 5,651,131 4,109,553 1,726,848,004</p>
Pleiades snow dataset from stereo-images
<p>Snow depth satellite observation datasets made from Pleiades stereo-images, used in the evaluation of the SURFEX/Crocus/SnowPappus simulation system.</p><p>Datasets are in the NETCDF4_CLASSIC format.</p><p>The observed snow depth field is named 'DSN_T_ISBA' with a 250m horizontal resolution.</p><p>Datasets projections are 'EPSG:2154' and is described in the Projection_Type field.</p><p>Datasets are CF Compliant.</p>
Wound image and transcriptome datasets of swine acute wounds
Open the record for dataset details and reuse information.
Engineered cardiac microbundle time-lapse microscopy image dataset
Open the record for dataset details and reuse information.
BIFROST: A method for registering diverse imaging datasets
Open the record for dataset details and reuse information.
Analysis dataset from: Simultaneous dual-color calcium imaging in freely-behaving mice
Open the record for dataset details and reuse information.
An imaging flow cytometry dataset for profiling the immunological synapse of therapeutic antibodies
Open the record for dataset details and reuse information.
Mobile Brain-Body Imaging (MoBI) dual-tasking datasets (response inhibition while walking): Young adults
Open the record for dataset details and reuse information.
Mobile Brain-Body Imaging (MoBI) dual-tasking datasets (response inhibition while walking): Increased cognitive load
Open the record for dataset details and reuse information.
MODID: Multispectral oral disease image dataset with segmentaion
Open the record for dataset details and reuse information.
Active region magnetograms for solar flare prediction: Extra images dataset
Open the record for dataset details and reuse information.
Dataset for: Influence of colour vision on attention to, and impression of, complex aesthetic images
Open the record for dataset details and reuse information.
Deep learning chronic wasting disease (CWD) immunohistochemistry (IHC) image dataset
Open the record for dataset details and reuse information.
Mobile Brain-Body Imaging (MoBI) dual-tasking datasets (response inhibition while walking): Older adults
Open the record for dataset details and reuse information.
A curated dataset of aerial survey images over the central Congo Basin, 1958
<p>This dataset contains a subset data from the Belgian Science Policy Office funded “Congo basin eco-climatological data recovery and valorisation" project (COBECORE, contract BR/175/A3/COBECORE).</p> <p>The data included is curated and pre-processed aerial survey imagery as used in a a land-use land-cover change analysis "Historical aerial surveys map long-term changes of forest cover and structure in the central Congo Basin".</p> <p> The dataset includes:</p> <ul> <li>the pre-processed images (aerial_images.tar.gz)</li> <li>the meta-data associated with the aerial images (flight_paths*)</li> <li>the final orthomosaic (yangambi_orthomosaic.tif)</li> </ul> <p>For the full methodology we refer to the full paper:</p> <p><strong>Hufkens K.</strong>, et al. (2020) Historical Aerial Surveys Map Long-Term Changes of Forest Cover and Structure in the Central Congo Basin. <strong> Remote Sensing</strong>, 12, 638.</p> <p>Please cite the work as such.</p> <p> </p>
Datasets used in 'Streambed hydraulic conductivity estimated by spectral induced polarization imaging can help to improve groundwater modeling'
<p>These datasets pertain to the manuscript entitled 'Streambed hydraulic conductivity estimated by spectral induced polarization imaging can help to improve groundwater modeling', which is currently submitted for revision in Water Resources Research. They comprise raw data from measurements taken in the field at 2 sites in terms of (1) pressure time series during the performed slug tests, (2) impedance from spectral induced polarization, (3) submersion levels of the used electrodes below the top of the water column, and (4) three-dimensional Cartesian coordinates relating the measurements spatially. The coordinates have been projected to a local coordinate system for each site, to comply with a non-disclosure agreement of the measurement locations. The projection of the coordinates still allows to fully reproduce the presented results, if using the methods described in the manuscript. The naming convention throughout the datasets is consistent with site labels used in the manuscript. All data is given as comma-separated values with intuitive file names and self-explanatory headers containing a list of field names. The slug test data includes multiple repetitions of the same measurement, and the impedance measurements contain normal as well as reciprocal readings – as described in the manuscript.</p> <p>The data is separated into two compressed file archives, named according to the site names given in the manuscript. Each file pertaining to slug tests at a certain location, in the subfolder “slugTestRecordings” has the following naming convention: “<locationTag>_<finalDepth>.csv”, where <locationTag> corresponds to the local coordinates given in “coordinates.txt”, and where <finalDepth> is an integer describing the largest depth in cm at which a slug test was performed according to the protocol described in the manuscript. Each file pertaining to impedance measurements at a certain profile, in the subfolder “SIPRecordings”, has the following naming convention: “<locationTag>_<frequency>.dat”, where <locationTag> corresponds to the local coordinates given in “coordinates.txt”, and where <frequency> is a zero-padded integer describing the measurement frequency in Hz at which the measurement was performed according to the protocol described in the manuscript. Submersion levels of the electrodes below the top of the stream’s water column are given in m in the file “submersionLevels.txt”, corresponding to the local coordinates given in “coordinates.txt”. The local coordinates given in m in “coordinates.txt” have the following convention for the column “locationTag”: “<profileTag>-<electrodeNumber>, where <profileTag> pertains to a name of the electrical array and <electrodeNumber”> is a continuous number for the electrode. Slug tests were exclusively perfomed at the location of electrodes and files are, thus, as described above, named accordingly.</p>
Dataset of PNT1A and PC-3 cells - efect of FITC phototoxicity, quantitative phase imaging (1/2)
<p>Part of article Feith, M,Vičar, T., Gumulec, J., Raudenská, M. Wingren, AG, Masařík, M., Balvan, J. Quantitative Phase Dynamics of Cancer Cell Populations Affected by Blue Light, <em>Appl. Sci.</em> <strong>2020</strong>, <em>10</em></p> <p>Increased exposition to blue light may induce many changes in cell behavior and significantly affect the critical characteristics of cells. Here we show that multimodal holographic microscopy (MHM) within advanced image analysis is capable of correctly distinguishing between changes in cell motility, cell dry mass, cell density, and cell death induced by blue light. We focused on the effect of blue light with a wavelength of 485 nm on morphological and dynamical parameters of four cell lines, malignant PC-3, A2780, G361 cell lines, and the benign PNT1A cell line. We used MHM with blue light doses 24 mJ/cm<sup>2</sup>, 208 mJ/cm<sup>2 </sup>and two kinds of expositions (500 and 1000 ms) to acquire real-time quantitative phase information about cellular parameters. It has been shown that specific doses of the blue light significantly influence cell motility, cell dry mass and cell density. These changes were often specific for the malignant status of tested cells. Blue light dose 208 mJ/cm<sup>2 </sup>× 1000 ms affected malignant cell motility but did not change the motility of benign cell line PNT1A. This light dose also significantly decreased proliferation activity in all tested cell lines but was not so deleterious for benign cell line PNT1A as for malignant cells. Light dose 208 mJ/cm<sup>2 </sup>× 1000 ms oppositely affected cell mass in A2780 and PC-3 cells and induced different types of cell death in A2780 and G361 cell lines. Cells obtained the least damage on lower doses of light with shorter time of exposition.</p> <p><strong>Materials and Methods </strong></p> <p><em>Cell Lines</em></p> <p>The PC-3, A2780, PNT1A, and G361 cell lines were purchased from HPA Culture Collections (Salisbury, UK). PC-3 prostate cancer cell line was derived from bone metastasis of a 4-grade prostatic adenocarcinoma of a 62-year-old Caucasian male The A2780 cell line was derived from the ovarian carcinoma of a nontreated patient according to ECACC. PNT1A cell line was established from prostatic epithelial tissue of healthy 35-years old male and immortalized by plasmid transfection containing the SV40 genome with defective replication origin. The G361 cell line was established from a malignant melanoma of a 31-year-old male Caucasian. The G361 cells produce melanin for up to 50 population doublings. As the aim of this study is to compare the effect of blue light on the cell lines differing by morphology, transformation state, sensitivity to cell death, and origin, we decided to use the cell lines listed above. PC-3 cells are larger in comparison with small A2780 cells. Benign PNT1A cell line differs from malignant PC-3, and all four cell lines are derived from diverse tissues of origin. Furthermore, melanoma G361 cells expressing melanin may differ in the reaction of cells to blue light exposure.</p> <p></p> <p><em>Cell Cultivation</em></p> <p>All four cell lines were cultivated in 25 cm<sup>2</sup> flasks with 5 ml of media at 37 °C in a humidified incubator (60%) with 5% CO<sub>2 </sub>(Sanyo, Osaka City, Japan). Cell lines A2780, PNT1A and G361 were cultured in RPMI-1640 medium with phenol red indicator, L–glutamine, FBS and antibiotics penicillin/streptomycin (Sigma Aldrich Co., St. Louise, MO, USA). For the PC-3 cell line cultivation, Ham´s F-12 medium with FBS and antibiotics (Sigma Aldrich Co., St. Louis, MO, USA) was used. The same supplementation with antibiotics (penicillin 100 U/mL and streptomycin 0.1 mg/mL) and 10% FBS was used in both media. The cell medium was changed two times per week. Cell subculturing was done with 10% of trypsin solution (PAA, Pasching, Austria) with previous washing with EDTA (0.02% in PBS buffer).</p> <p><em>QPI and Holographic Microscopy and Fluorescence Setting</em></p> <p>QPI was performed by using a Q-PHASE multimodal holographic microscope (Telight, Brno, CZ). The Q-PHASE is equipped with fluorescence module using a halogen lamp as a non-coherent source of blue light. In this work, the module was used as a source of blue light for treatment of observed cell lines. The 485 nm light waves are emitted by the fluorescence light source of the attached module. Before the imaging experiment, cells were cultivated overnight in a concentration of 7000 cells/mL in flow chamber µ-Slide I Lauer Family (Ibidi, Martinsried, Germany). During the measurements, the chamber with cells was incubated in 37 °C humidified, 5% CO<sub>2</sub> atmosphere in H201–for Mad City Labs Z100/Z500 piezo Z-stages (Okolab, Ottaviano NA, Italy). Images and holograms were captured with lens Nikon Plan 10/0.3 and CCD camera (XIMEA MR4021 MC-VELETA, Münster, Germany) respectively. The fluorescence mode used was a plasma light source (Sutter Instrument Lambda XL Novato, CA, USA). Cells were irradiated with a 485 nm light with a 25 nm bandwidth. Light doses 0 mJ/cm<sup>2</sup>, 24 mJ/cm<sup>2</sup> and 208 mJ/cm<sup>2 </sup>were achieved by the combination of time exposition and light intensity.</p> <p>The images were acquired automatically from seven positions every 3 min for 24 h. Holographic images were collected by custom software and raw data were numerically reconstructed. The numerical reconstruction was performed by custom software where the established methods of the fast Fourier-transform and phase unwrapping are implemented. The output from the software is an unwrapped phase image. This image has high intrinsic contrast and can be processed by an available image processing software. The unwrapped phase image is integrated phase shift through the cell and it is proportional to integrated cell dry mass density.</p> <p></p>
Datasets and images of publication: Self-healing and high interfacial strength in multi-material soft pneumatic robots via reversible Diels-Alder bonds
<p>Data and Figures of the publication:</p> <p>Terryn, S.; Roels, E.; Brancart, J.; Assche, G.V.; Vanderborght, B. Self-Healing and High Interfacial Strength in Multi-Material Soft Pneumatic Robots via Reversible Diels–Alder Bonds. <em>Actuators</em> <strong>2020</strong>, <em>9</em>, 34.</p>
Image Dataset for 'Digitally deconstructing leaves in 3D using X-ray microcomputed tomography and machine learning'
<p>Dataset used in the manuscript 'Digitally Deconstructing Leaves in 3D Using X-ray microcomputed Tomography and Machine Learning'. Please cite the paper presenting this dataset:</p> <p><strong>Citation:</strong> Théroux-Rancourt, G., M. R. Jenkins, C. R. Brodersen, A. McElrone, E. J. Forrestel, and J. M. Earles. 2020. Digitally deconstructing leaves in 3D using X-ray microcomputed tomography<strong> </strong>and machine learning. <em>Applications in Plant Sciences</em> 8(7): .</p> <p> </p> <p><strong>Description of the dataset</strong></p> <p>A 'Cabernet Sauvignon' grapevine (<em>Vitis vinifera</em> L.) leaf from a plant of the BOKU experimental vineyard in Tulln, Austria, was scanned using microCT at the Swiss Light Source. The original reconstructions of the scans are using the gridrec (<a href="https://zenodo.org/api/files/bbca544a-15d0-40f3-8cc9-a3ee3c08fd7e/Gridrec_reconstruction_downsized.zip?versionId=28d98982-f69d-4eac-9dfa-efcc89c6823c">Gridrec_reconstruction_downsized.zip</a>) and the paganin, or phase-contrast, algortithm (<a href="https://zenodo.org/api/files/bbca544a-15d0-40f3-8cc9-a3ee3c08fd7e/Phase_contrast_reconstruction_downsized.zip?versionId=bef3260d-2865-4c9b-b5e1-e692edefb691">Phase_contrast_reconstruction_downsized.zip</a>). To facilitate automated segmentation, the size of the image in the <em>x </em>and <em>y</em> dimensions have been halved, so that the size of the pixels is 0.325 µm in those dimensions, but 0.1625 µm in the <em>z</em> (slices) dimension.</p> <p>A binary image segmenting the leaf cells and the airspace for each gridrec and phase-contrast stacks are created, and both are combined together (<a href="https://zenodo.org/api/files/bbca544a-15d0-40f3-8cc9-a3ee3c08fd7e/Binary_stack_for_local_thickness.zip?versionId=165e3938-b490-4e56-9c8e-a2084cb39d49">Binary_stack_for_local_thickness.zip</a>), a map of the local thickness is created (<a href="https://zenodo.org/api/files/bbca544a-15d0-40f3-8cc9-a3ee3c08fd7e/Local_thickness_map.zip?versionId=ce0a7dc7-5e3f-44a4-8881-cf84b6efd87c">Local_thickness_map.zip</a>). This map gives information on the largest diameter of the pixels labeled as cells in the binary stack.</p> <p>Hand-labeled slices or ground truths were drawn on the following slices: 80, 140, 200, 260, 340, 400, 440, 540, 620, 740, 800, 860, 940, 1060, 1140, 1240, 1300, 1400, 1480, 1540, 1600, 1690, 1740, 1840 (<a href="https://zenodo.org/api/files/bbca544a-15d0-40f3-8cc9-a3ee3c08fd7e/Hand_labelled_slices.tif?versionId=a21a13ac-fa47-4ef8-a903-ecc433787184">Hand_labelled_slices.tif</a>).</p> <p>Using the hand-labeled slices and the different images, a random-forest model was trained, which allowed to automatically segment the remaining slices of the stack (<a href="https://zenodo.org/api/files/bbca544a-15d0-40f3-8cc9-a3ee3c08fd7e/Fullstack_Prediction_Example-6_training_slices-6_testing_slices.zip?versionId=02b69e65-da85-492e-9b72-9b2b3ccd085f">Fullstack_Prediction_Example-6_training_slices-6...</a>).</p> <p>The source code for the segmentation program is available <a href="https://github.com/plant-microct-tools/leaf-traits-microct/tree/master">here</a>, and the source code for the testing used in the paper is available <a href="https://github.com/plant-microct-tools/leaf-traits-microct/tree/nb-slices-eval">here</a>.</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.