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”
Dataset for Super-Resolution Image Reconstruction based on Random-coupled Neural Network and EDSR
<p>This dataset folder contains the DIV2K public dataset, which is utilized for model training and comprises 900 high-quality, high-resolution images along with their corresponding low-resolution versions. Additionally, all pre-trained models used in the experiment and their associated test results are publicly available.</p> <p>The main directory is organized into two subfolders: one labeled "dataset," which houses the DIV2K dataset, and another named "Model_results," which contains the pre-trained models and their corresponding test outcomes. The Dataset folder includes the original DIV2K dataset (referred to as "DIV2K") as well as a channel-expanded dataset processed by the RCNN model (designated as "DIV2K-RCNN"). Within the Model_results folder, the Model_trained subfolder contains all pre-trained models employed during the experiment, while the Test_results subfolder holds the test results for each model.</p>
Mouse CA1 Calcium Imaging and Behavioural Dataset in 3x3 Geometric Morph Paradigm
<p>The following dataset was collected by Dr. J. Quinn Lee, Dr. Alexandra T. Keinath, and Erica Cianfarano in the laboratory of Dr. Mark P. Brandon. All methods and details are described in the original research article reporting these data published in <em>Neuron</em>: Lee, Keinath, Cianfarano, and Brandon (2025) Identifying representational structure in CA1 to benchmark theoretical models of cognitive mapping. Any use of the following dataset must cite the original publication in Neuron. The code base to reproduce all analyses and figures can be found at: <a href="https://github.com/jquinnlee/georepca1">https://github.com/jquinnlee/georepca1</a></p> <p dir="auto">The dataset (Python joblib files or MATLAB .mat files in the zipped "data" folder) are given names of animal IDs from the original study that can be downloaded from Zenodo and contain the following fields in each file:</p> <p dir="auto">SFPs: spatial footprints (also known as ROI) for every registered cell, centered over each cell. Shape - Dimx, dimy, number of SFPs (ROIs), number of days. If cell is not registered it will be nan along dimx and dimy for a given day.</p> <p dir="auto">blocked: location of blocked (occluded) partitions in 3x3 design of environment. Location of partitions are shown in paper, but are organized in the following way – [[0, 1, 2], [3, 4, 5], [6, 7, 8]]. If no partitions are blocked, value is -1.</p> <p dir="auto">centroids: centroid of spatial footprint. Shape – number of cells, x-y location, number of days.</p> <p dir="auto">envs: environment shape identified with string name</p> <p dir="auto">maps: three types of maps generated from the dataset. “sampling” is the occupancy of animal in each spatial bin, shape – xbins, ybins, number of days. “smoothed” is the event rate map smoothed with 2.5 cm gaussian kernel, shape – xbins, ybins, number of cells, number of days. “unsmoothed” is the same event rate map data without smoothing.</p> <p dir="auto">position: x-y position data for all days. List shape number of days, with shape on each day indicating x-y position in first dimension, and number of temporal bins / frames in second dimension.</p> <p dir="auto">trace: rise-extracted calcium traces, where “1” indicates a significant event. See paper for details on processing pipeline. If cell is not registered on given day, will appear as nan the same shape.</p> <p dir="auto">Precomputed results can also be downloaded in the zipped "results" folder to avoid recomputing main results from scratch using the Github code base linked above.</p>
Single-Shot Three-Dimensional Orientation Imaging of Nanorods Using Spin to Orbital Angular Momentum Conversion_experimental_dataset
<p>This is the datafile containing the raw experimental data to the article Fordey et al., Single-Shot Three-Dimensional Orientation Imaging of Nanorods Using Spin to Orbital Angular Momentum Conversion, <em>Nano Lett.</em> 2021, 21, 17, 7244–7251. </p>
Datasets for "Automated Detection of Portal Fields and Central Veins in Whole-Slide Images of Liver Tissue"
<p>Datasets and results for the manuscript “Automated Detection of Portal Fields and Central Veins in Whole-Slide<br> Images of Liver Tissue” (Journal of Pathology Informatics 13 (2022) 100001, https://doi.org/10.1016/j.jpi.2022.100001)</p>
Image Dataset-Drone-AI4Agriculture
<p>Dataset containing multispectral drone imagery from 3 Ribera de Duero vineyards This dataset comprises imagery from three vineyards in Ribera de Duero region, obtained with a multispectral sensor attached to a drone. Contents:</p> <p>• NIR, Red, Red-Edge, Green bands</p> <p>• NDVI Index</p>
Latent space images and related deep neural network for the BAGLS dataset
<p>In this repository, we provide the latent space images for the BAGLS (<a href="https://www.nature.com/articles/s41597-020-0526-3">Gómez, Kist et al., Sci Data 2020</a>, available at <a href="https://bagls.org/">www.bagls.org</a>) training dataset. We further provide a pre-trained deep neural network for glottis segmentation having only a single latent space, i.e. a latent space image, and no skip connections.</p>
Human ISMRMRD datasets for "MaxGIRF: Image Reconstruction Incorporating Concomitant Field and Gradient Impulse Response Function Effects"
<p>Human axial and sagittal ISMRMRD datasets for "MaxGIRF: Image Reconstruction Incorporating Concomitant Field and Gradient Impulse Response Function Effects".</p> <p>Code to process and reconstruct the data is available here: <a href="https://github.com/usc-mrel/lowfield_maxgirf">https://github.com/usc-mrel/lowfield_maxgirf</a></p>
Morphological features associated with Dapi and Nissl images from seqFISH and seqFISH+ datasets
<p>To go with the convnet.morpho package from:</p> <p>https://bitbucket.org/qzhudfci/convnet.morpho/src/master/</p> <p>Image data:</p> <p>brain1.images.zip</p> <p>brain2.images.zip</p> <p>seqfishplus.images.zip</p> <p> </p> <p>Alexnet extracted feature vectors (npy):</p> <p>brain1.image.data.zip</p> <p>brain2.image.data.zip</p> <p>seqfishplus.image.data.zip</p> <p> </p>
Phantom ISMRMRD datasets for "MaxGIRF: Image Reconstruction Incorporating Concomitant Field and Gradient Impulse Response Function Effects"
<p>Phantom ISMRMRD datasets for "MaxGIRF: Image Reconstruction Incorporating Concomitant Field and Gradient Impulse Response Function Effects".</p> <p>Code to process and reconstruct the data is available here: <a href="https://github.com/usc-mrel/lowfield_maxgirf">https://github.com/usc-mrel/lowfield_maxgirf</a></p>
Sythetic datasets of road images
<p>The detector of elongated boundaries in the image, such as road marking lines, rails, etc., is an important component of the visual system of a highly automated vehicle (HAV). It is used by HAV to solve self-localization problems, maintain the position inside the lane, warning about lane departure. Collecting and labeling data for solving these problems is always a time-consuming task.<br> We present two types of synthetic dataset of road images. The first type is aerial imagery dataset. It is intended to be used for road boundaries detector that works with bird's eye view road images. The second type of dataset is drawn road markings line on a black background. It is designed to optimize the parameters of elongated boundaries detectors that also works with bird's eye view road images but also first step of which is background suppression. Please note that not all parameters can be tuned but only those which affect steps followed by background suppression.<br> <br> There are 2 folders "aerial_imagery_dataset" and "drawn_road_markings_dataset", each corresponds of its own type of dataset. Each folder contains images and corresponding them markup in json files. Pair image and corresponded markup will be called sample. "aerial_imagery_dataset" consists of 5336 samples, "drawn_road_markings_dataset" consists of 660 samples.<br> Markup files contain information of road markings coordinates in the image. </p>
Novel Pixelwise Co-Registered Hematoxylin-Eosin and Multiphoton Microscopy Image Dataset for Human Colon Lesion Diagnosis
<p><strong>General Description:</strong></p> <p>The dataset consists of a set of 50 samples of lesions obtained by colonoscopies and colectomies carried out between the years 2012 and 2017 at at Digestive Service at OSI Bilbao Basurto. These are 24 malignant neoplasms (adenocarcinoma), 19 preneoplastic lesions (adenoma) and 2 hyperplasia and 5 healthy tissues, obtained from 24 men and 19 women. The samples were diagnosed by the Pathological Anatomy Department at OSI Bilbao Basurto and the FFPE (Formalin-Fixed Paraffin-Embedded) blocks were stored in the Basque Biobank. All the samples were processed after signing Informed Consent and following standard operation procedures. The samples were scanned using a multiphoton microscope (Lens, Florence, Italy) both for multi-photon fluorescence (MPM) and second harmonic generation (SHG) and later stained with H&E (Hematoxylin & Eosin).</p> <p>The different image modalities were reconstructed and corregistered by performing non-rigid deformation (Tecnalia, Bilbao, Spain) allowing pixel correspondence among the different modalities. Pathologists from Basurto Hospital manually labeled the regions where the lession is present. Scale of current dataset is 0.5um/px.</p> <p><strong>Technical Details:</strong></p> <p>On the data_info.csv information for each sample is included:<br> - SAMPLE_ID: Includes the tag "PICCOLO_XX_YY", where XX stands for the patient ID number and YY to the lesion suffix ID.<br> - LESION_ID: The lesion is classified as healthy, hyperplasia, benign neoplasia, and malign neoplasia.<br> - HISTOLOGICAL ANALYSIS: It includes informative test about the lesion.<br> - GRADE: In the case for malign neoplasia universal grading system grade is included.</p>
COVID Image segmentation datasets and trained model
<p>COVID CT scan datasets for segmentation and trained model for prediction created by training uNet. The referred paper is: https://www.sciencedirect.com/science/article/pii/S2666990021000069</p> <p>Origin of datasets: https://medicalsegmentation.com/covid19/</p>
Datasets for neuronal imaging, extracellular recordings and behavioral rig code
<p>Rod and cone photoreceptors degenerate in retinitis pigmentosa (RP). While downstream neurons survive, they undergo physiological changes, including accelerated spontaneous firing in retinal ganglion cells (RGCs). Retinoic acid (RA) is the molecular trigger of RGC hyperactivity, but whether this interferes with visual perception is unknown. Here we show that inhibiting RA synthesis with disulfiram, a deterrent of human alcohol abuse, improves behavioral image detection in vision-impaired mice. <i>In vivo</i> Ca<sup>2+</sup> imaging shows that disulfiram sharpens orientation-tuning of visual cortical neurons and strengthens fidelity of responses to natural scenes. An RA receptor inhibitor also reduces RGC hyperactivity, sharpens cortical representations, and improves image detection. These findings suggest that photoreceptor degeneration is not the only cause of vision loss in RP. RA-induced corruption of retinal information processing also degrades vision, pointing to RA synthesis and signaling inhibitors as potential therapeutic tools for improving sight in RP and other retinal degenerative disorders.</p>
Dataset on Off-Axis holography images of the MINEON device at different potential bias values
<p>Dataset of Off-Axis holography images that show to us how the electron beam's phase is modified aquiring an azimuthally changing phase profile, confirming the presence of an electron vortex beam. In this dataset we recorded phase images of the electron beam in at different values of the potential bias between the two main tips of the MINEON/chopstic electrostatic device. It is possible to see how the phase scales linearly with increasing potential bias difference, i.e., the electron vortex beam's OAM increases as the bias increases</p> <p>A description of this dataset can and similar ones are reported in:https://arxiv.org/abs/2203.00477</p>
Image dataset to train a deep learning model to decode Leetspeak obfuscated characters
<p>The dataset contains an image database (18,981 images) that could be used to train a deep learning model to accurately detect characters. We have successfully used it to create a model that identifies characters encoded using LeetSpeak. The original dataset can be found in the Mondragon Unibertsitatea Repository -- https://gitlab.danz.eus/datasharing/ski4spam</p> <p>The training dataset consists of:</p> <p>- Alphabetic letters (a-z) written using different fonts and styles (regular, cursive, bold, cursive+bold)</p> <p>- Handwritten letters: English handwriting from the Chars74k dataset [2] which is available at http://www.ee.surrey.ac.uk/CVSSP/demos/chars74k/.</p>
Fused Image dataset for convolutional neural Network-based crack Detection (FIND)
<p>The “<strong>F</strong>used <strong>I</strong>mage dataset for convolutional neural <strong>N</strong>etwork-based crack <strong>D</strong>etection” (<strong>FIND</strong>) is a large-scale image dataset with pixel-level ground truth crack data for deep learning-based crack segmentation analysis. It features four types of image data including raw intensity image, raw range (i.e., elevation) image, filtered range image, and fused raw image. The FIND dataset consists of 2500 image patches (dimension: 256x256 pixels) and their ground truth crack maps for each of the four data types.</p> <p>The images contained in this dataset were collected from multiple bridge decks and roadways under real-world conditions. A laser scanning device was adopted for data acquisition such that the captured raw intensity and raw range images have pixel-to-pixel location correspondence (i.e., spatial co-registration feature). The filtered range data were generated by applying frequency domain filtering to eliminate image disturbances (e.g., surface variations, and grooved patterns) from the raw range data [1]. The fused image data were obtained by combining the raw range and raw intensity data to achieve cross-domain feature correlation [2,3]. Please refer to [4] for a comprehensive benchmark study performed using the FIND dataset to investigate the impact from different types of image data on deep convolutional neural network (DCNN) performance.</p> <p>If you share or use this dataset, please cite [4] and [5] in any relevant documentation. </p> <p>In addition, an image dataset for crack classification has also been published at [6].</p> <p>References:</p> <p>[1] Shanglian Zhou, & Wei Song. (2020). Robust Image-Based Surface Crack Detection Using Range Data. Journal of Computing in Civil Engineering, 34(2), 04019054. <a href="https://doi.org/10.1061/(asce)cp.1943-5487.0000873">https://doi.org/10.1061/(asce)cp.1943-5487.0000873</a></p> <p>[2] Shanglian Zhou, & Wei Song. (2021). Crack segmentation through deep convolutional neural networks and heterogeneous image fusion. Automation in Construction, 125. <a href="https://doi.org/10.1016/j.autcon.2021.103605">https://doi.org/10.1016/j.autcon.2021.103605</a></p> <p>[3] Shanglian Zhou, & Wei Song. (2020). Deep learning–based roadway crack classification with heterogeneous image data fusion. Structural Health Monitoring, 20(3), 1274-1293. <a href="https://doi.org/10.1177/1475921720948434">https://doi.org/10.1177/1475921720948434</a> </p> <p>[4] Shanglian Zhou, Carlos Canchila, & Wei Song. (2023). Deep learning-based crack segmentation for civil infrastructure: data types, architectures, and benchmarked performance. Automation in Construction, 146. <a href="https://doi.org/10.1016/j.autcon.2022.104678">https://doi.org/10.1016/j.autcon.2022.104678</a></p> <p>[5] (<strong>This dataset</strong>) Shanglian Zhou, Carlos Canchila, & Wei Song. (2022). Fused Image dataset for convolutional neural Network-based crack Detection (FIND) [Data set]. Zenodo. <a href="https://doi.org/10.5281/zenodo.6383044">https://doi.org/10.5281/zenodo.6383044</a></p> <p>[6] Wei Song, & Shanglian Zhou. (2020). Laser-scanned roadway range image dataset (LRRD). Laser-scanned Range Image Dataset from Asphalt and Concrete Roadways for DCNN-based Crack Classification, DesignSafe-CI. <a href="https://doi.org/10.17603/ds2-bzv3-nc78">https://doi.org/10.17603/ds2-bzv3-nc78</a></p>
RGB and Thermal Integral Image dataset for Search and Rescue with Airborne Optical Sectioning.
<p>The `Integral Images` folder contains labels and augmented AOS integral images (both RGB and Thermal) used for training, validation and testing (`data`).</p> <p>The integral images are computed using the complete data that were recorded during 18 flights at 6 different sites over 10 different days.</p> <p> </p> <p>The dataset mirrors [YOLO (8GB)](https://zenodo.org/record/3894774/files/YOLO.zip?download=1) (`data`) for integral (`SARAOS/AOS`) images, however, now additionally contain corresponding RGB integral images in addition to corresponding thermal integral images.</p>
Image Dataset of Accessibility Barriers
<p><strong>The Data</strong><br> The dataset consist of 5538 images of public spaces, annotated with steps, stairs, ramps and grab bars for stairs and ramps. The dataset has annotations 3564 of steps, 1492 of stairs, 143 of ramps and 922 of grab bars.</p> <p>Each step annotation is attributed with an estimate of the height of the step, as falling into one of three categories: less than 3cm, 3cm to 7cm or more than 7cm. Additionally it is attributed with a 'type', with the possibilities 'doorstep', 'curb' or 'other'.</p> <p>Stair annotations are attributed with the number of steps in the stair.</p> <p>Ramps are attributed with an estimate of their width, also falling into three categories: less than 50cm, 50cm to 100cm and more than 100cm.</p> <p>In order to preserve all additional attributes of the labels, the data is published in the CVAT XML format for images.</p> <p> </p> <p><strong>Annotating Process</strong><br> The labelling has been done using bounding boxes around the objects. This format is compatible with many popular object detection models, e.g. the YOLO object model. A bounding box is placed so it contains exactly <em>the visible part</em> of the respective objects. This implies that only objects that are visible in the photo are annotated. This means in particular a photo of a stair or step from above, where the object cannot be seen, have not been annotated, even when a human viewer can possibly infer that there is a stair or a step from other features in the photo.</p> <p><strong>Steps</strong><br> A step is annotated, when there is an vertical increment that functions as a passage between two surface areas intended human or vehicle traffic. This means that we have not included:</p> <ul> <li>Increments that are to high to reasonably be considered at passage.</li> <li>Increments that does not lead to a surface intended for human or vehicle traffic, e.g. a 'step' in front of a wall or a curb in front of a bush.</li> </ul> <p>In particular, the bounding box of a step object contains exactly the incremental part of the step, but does not extend into the top or bottom horizontal surface any more than necessary to enclose entirely the incremental part. This has been chosen for consistency reasons, as including parts of the horizontal surfaces would imply a non-trivial choice of how much to include, which we deemed would most likely lead to more inconstistent annotations.</p> <p>The height of the steps are estimated by the annotators, and are therefore not guarranteed to be accurate.</p> <p>The type of the steps typically fall into the category 'doorstep' or 'curb'. Steps that are in a doorway, entrance or likewise are attributed as doorsteps. We also include in this category steps that are immediately leading to a doorway within a proximity of 1-2m. Steps between different types of pathways, e.g. between streets and sidewalks, are annotated as curbs. Any other type of step are annotated with 'other'. Many of the 'other' steps are for example steps to terraces.</p> <p><strong>Stairs</strong><br> The stair label is used whenever two or more steps directly follow each other in a consistent pattern. All vertical increments are enclosed in the bounding box, as well as intermediate surfaces of the steps. However the top and bottom surface is not included more than necessary for the same reason as for steps, as described in the previous section.</p> <p>The annotator counts the number of steps, and attribute this to the stair object label.</p> <p><strong>Ramps</strong><br> Ramps have been annotated when a sloped passage way has been placed or built to connect two surface areas intended for human or vehicle traffic. This implies the same considerations as with steps. Alike also only the sloped part of a ramp is annotated, not including the bottom or top surface area.</p> <p>For each ramp, the annotator makes an assessment of the width of the ramp in three categories: less than 50cm, 50cm to 100cm and more than 100cm. This parameter is visually hard to assess, and sometimes impossible due to the view of the ramp.</p> <p><strong>Grab Bars</strong><br> Grab bars are annotated for hand rails and similar that are in direct connection to a stair or a ramp. While horizontal grab bars could also have been included, this was omitted due to the implied ambiguities of fences and similar objects. As the grab bar was originally intended as an attributal information to stairs and ramps, we chose to keep this focus. The bounding box encloses the part of the grab bar that functions as a hand rail for the stair or ramp.</p> <p> </p> <p><strong>Usage</strong><br> As is often the case when annotating data, much information depends on the subjective assessment of the annotator. As each data point in this dataset has been annotated only by one person, caution should be taken if the data is applied.</p> <p>Generally speaking, the mindset and usage guiding the annotations have been wheelchair accessibility. While we have strived to annotate at an object level, hopefully making the data more widely applicable than this, we state this explicitly as it may have swayed untrivial annotation choices.</p> <p>The attributal data, such as step height or ramp width are highly subjective estimations. We still provide this data to give a post-hoc method to adjust which annotations to use. E.g. for some purposes, one may be interested in detecting only steps that are indeed more than 3cm. The attributal data makes it possible to sort away the steps less than 3cm, so a machine learning algorithm can be trained on this more appropriate dataset for that use case. We stress however, that one cannot expect to train accurate machine learning algorithms inferring the attributal data, as this is not accurate data in the first place.</p> <p>We hope this dataset will be a useful building block in the endeavours for automating barrier detection and documentation.</p>
Dataset for detecting the electrical behavior of photovoltaic panels from RGB images
<p>The dynamic reconfiguration and maximum power point tracking in large-scale photovoltaic (PV) systems require a large number of voltage and current sensors. In particular, the reconfiguration process requires a pair of voltage/current sensors for each panel, which introduces costs, increases size and reduces reliability of the installation. A suitable solutions for reducing the number of sensors is to adopt image-based solution to estimate the electrical characteristics of the PV panels, but the lack of reliable data with large diversity of irradiance and shading conditions is a major problem in this topic. Therefore, this paper presents dataset correlating RGB images and electrical data of PV panels with different irradiance and shading conditions. The dataset was designed to support the design of image-based estimators of electrical data, which could be used to replace large arrays of sensors. The paper also describes the measurement platform used to collect the data, which helps to replicate the experiments in different geographical locations.</p>
PrivacyAlert: a dataset for image privacy prediction
<p>This is a dataset for image privacy prediction. Images are from Flickr and annotated as private/public by crowd-sourcing platforms. Private images are ones that contain sensitive information and cannot be shared with everyone on social networking sites. Public images are ones that are safe to be shared with everyone. Our dataset can be used to train machine learning/deep learning models as binary classifiers to predict whether images contain sensitive information.</p> <p>Please cite: </p> <pre>@inproceedings{zhao2022privacyalert, title={PrivacyAlert: A Dataset for Image Privacy Prediction}, author={Zhao, Chenye and Mangat, Jasmine and Koujalgi, Sujay and Squicciarini, Anna and Caragea, Cornelia}, booktitle={Proceedings of the International AAAI Conference on Web and Social Media}, volume={16}, pages={1352--1361}, year={2022} }</pre>
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.