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 "Root Length Estimation: Automated Minirhizotron Image Analysis with Convolutional Networks without Segmentation"
<p>This data contains 4015 root images, splitted into 4 datasets, acquired using two minirhizotron (MR) system types - manual (Dataset 1 & Dataset 4) and automated (Dataset 2 & Dataset 3). It includes four crop species (corn, pepper, melon, and tomato) grown under various abiotic stresses. The data was acquired by researchers from Ben-Gurion University of the Negev, Beer Sheva, Israel, and used for research of automated TRL estimation with Convolutional Neural Networks.</p> <p>The annotations were conducted manually using the Rootfly software (Wells and Birchfield, Clemson University, South Carolina, USA), and data were transformed as CSV formats. In this software, the annotator must draw a root by marking points along the selected root. These points usually correspond to the coordinates at the start and the end of the root, and curving points along the root. These points are then connected in a line, the length of which reflects the real length of the selected root. The annotations has been done for all roots within an image, and for all images in the provided dataset.</p> <p>The provided annotations include the total root length (TRL) per image (mm) and the coordinates of annotated points.</p> <p>The annotations are given in two types of files:</p> <p>"TRL.csv" files: contain the image names and corresponding TRL values (mm).</p> <p>"pointsOutput.csv" files: contain the annotated image names and the coordinates of the points of the roots in the image (if the image contains roots) in the form of x1, y1, x2, y2, x3, y3, etc. It the image doesn't have roots, the file contains only its name.</p>
Datasets and Model for "Age-Independent Oceanic Plate Thickness and Asthenosphere Melting from SS Precursor Imaging"
<p>The Earth’s asthenosphere is a mechanically weak layer characterized by low seismic velocity and high attenuation. The nature of this layer has been strongly debated. In this study, we process twelve years of seismic data recorded at the global seismological network (GSN) stations to investigate SS waves reflected at the upper and lower boundaries of this layer in global oceanic regions. We observe strong reflections from both the top and the bottom of the asthenosphere, dispersive across all major oceans. The average depths of the two discontinuities are 120 km and 255 km, respectively. The SS waves reflected at the lithosphere and asthenosphere boundary are characterized by anomalously large amplitudes, which require ∼12.5% reduction in seismic velocity across the interface. This large velocity drop can not be explained by a thermal cooling model but indicates 1.5%-2% localized melt in the oceanic asthenosphere. The depths of the two discontinuities show large variations, indicating that the asthenosphere is far from a homogeneous layer but likely associated with strong and heterogeneous small-scale convections in the oceanic mantle. The average depths of the two boundaries are largely constant across different age bands. In contrast to the half space cooling model, this observation supports the existence of a constant-thickness plate in oceanic regions with a complex and heterogeneous origin. This repository contains four datasets and one reference earth model from this study.</p>
Dataset: Modelling surface color discrimination under different lighting environments using image chromatic statistics and convolutional neural networks
<p><strong>Associated publication</strong></p> <p>[1] Samuel Ponting*, <strong>Takuma Morimoto</strong>*, Hannah E. Smithson, “Modelling surface color discrimination under different lighting environments using image chromatic statistics and convolutional neural networks”, *equal contribution, bioRxiv, <a href="https://www.google.com/url?q=https%3A%2F%2Fdoi.org%2F10.1101%2F2022.11.02.514864&sa=D&sntz=1&usg=AOvVaw3KwSo7KmqPzBR1UMc1MHmk">https://doi.org/10.1101/2022.11.02.514864</a></p> <p>[2] Takuma Morimoto, and Hannah E. Smithson, “Discrimination of spectral reflectance under complex environmental illumination,” Journal of the Optical Society of America A, 35, 4, B244-B255 (2018) https://doi.org/10.1364/JOSAA.35.00B244</p> <p> </p> <p>Datasets contain 2 folders and 1 mat file.</p> <p> </p> <p><strong>(Folder 1) Stimuli</strong></p> <p><strong>(Folder 2) Psychophysics_data</strong></p> <p><strong>(Mat file) stimulusMagnitudeToMacLeodBoynton.mat</strong></p> <p> </p> <p>Details are described below.</p> <p> </p> <p>----------------------------------------------------------------------------------------------------------------------------------------</p> <p><strong>(Folder 1) Stimuli</strong></p> <p> </p> <p><strong>Overview of datasets</strong></p> <p>This Image dataset includes 57,600 images (2 gloss levels * 3 environments * 100 stimulus magnitudes * 8 hue directions * 12 camera angles from 0 to 330 degree in 30 degree step) in .mat format.</p> <p> </p> <p>The half of images were used in psychophysical experiment (camera angles: 0, 60, 120, 180, 240, 300 degrees).</p> <p>Other half images were used for testing chromatic statistics models and CNN-based models [1] (camera angles: 30, 90, 150, 210, 270, 330 degrees).</p> <p> </p> <p><strong>Each image file</strong></p> <p>Filename denotes a condition name and the camera angle as formatted in a following way.</p> <p> </p> <p>stim_”environment” _”glossiness”_”hueAngle”_”magnitude”_”cameraAngle”.mat</p> <p>e.g. “stim_en1_glossy_hue45_n45_cameraAngle90.mat”</p> <p> </p> <p>Stimulus magnitude 100 is a maximum saturation, and 1 corresponds to equal energy white (which was used as a distractor object).</p> <p> </p> <p>Each image file contains two valuables : MacLeodBoynton, XYZ</p> <p> </p> <p>Each variable contains an image of 128*128*3 pixels (height*width*channel).</p> <p> </p> <p>MacLeod-Boynton: MacLeod-Boynton chromaticity image (1st channel: L/(L+M), 2nd channel: S/(L+M), and 3rd channel L+M)</p> <p>XYZ: XYZ coordinates calculated based on 2-degree CIE 1931 xyz color matching function (1st channel: X, 2nd channel: Y, and 3rd channel Z)</p> <p> </p> <p>Luminance and L+M are both relative (normalised by the maximum luminance across all 57,600 images).</p> <p> </p> <p>----------------------------------------------------------------------------------------------------------------------------------------</p> <p><strong>(Folder 2) Psychophysics_data</strong></p> <p>Filename denotes the condition and observers formatted in a following way.</p> <p> </p> <p>data_”environment” _”specularities”_”sessionNumber”_”obsever”.mat</p> <p>e.g. data_en2_matte_session4_JH.mat or .csv</p> <p> </p> <p>Each file includes following variables:</p> <p> </p> <p>(Variable 1) threshold</p> <p>Thresholds are stored in MacLeod-Boynton (MB) chromaticity coordinates for all 8 hue directions (from 0 to 315 degree in 45 degree step).</p> <p> </p> <p>MacLeod-Boynton chromaticity coordinates were calculated in a following way. </p> <p>These scalings are in accordance with description in CVRL main site (Chromaticity coordinates tab ).</p> <p> </p> <p>First of all, L, M, and S cone signals were calculated based on Stockman & Sharpe cone fundamentals (energy in linear scale available at at http://www.cvrl.org).</p> <p>Each sensitivity curve was normalised to have 1.0 at the peak.</p> <p> </p> <p>Then, MB coordinates were calculated using equation (1-3).</p> <p> </p> <p>L/(L+M) = Lw*L/(Lw*L+Mw*M) - (1)</p> <p>S/(L+M) = Sw*S/(Lw*L+Mw*M) - (2)</p> <p>L+M = Lw*L+Mw*M - (3)</p> <p> </p> <p>where Lw = 0.689903; Mw = 0.348322;Sw = 1.93540.</p> <p> </p> <p>L, M and S denote L-cone, M-cone, S-cone excitations, respectively.</p> <p> </p> <p>Under this calculation, equal energy white becomes L/(L+M) = 0.7078 and S/(L+M) = 1.</p> <p> </p> <p>(Variable 2) staircase</p> <p> </p> <p>Since we ran 8 interleaved staircase (for 8 hue angles), information about 8 staircases are stored in this single variable.</p> <p>(staircase(1) corresponds to 0 degree, and staircase(8) corresponds to 315 degree)</p> <p> </p> <p>There are 5 fields:</p> <p>(i) groundtruth, (ii) response, (iii) correct, (iv) magnitude, (v) cameraAngle</p> <p> </p> <p>For each trial, the location of objects was defined in a following way.</p> <p>| 1 3 |</p> <p>| 2 4 |</p> <p> </p> <p>And each field stores following information for all trials in the staircase.</p> <p> </p> <p>(i) groundtruth</p> <p>Location of the target object</p> <p> </p> <p>(ii) response</p> <p>Location that the participant chose</p> <p> </p> <p>(iii) correct</p> <p>If the response was correct (1) or incorrect (0)</p> <p> </p> <p>(iv) magnitude</p> <p>Stimulus magnitude of target object in each trial from 1 to 100 (1 for equal energy white and 100 for maximum saturation).</p> <p> </p> <p>(v) Camera angle</p> <p>Camera angles assigned for four objects in each trial.</p> <p>This data and (i) groundtruth allow reconstruct of the exact image for each trial.</p> <p> </p> <p>----------------------------------------------------------------------------------------------------------------------------------------</p> <p><strong>(Mat file) stimulusMagnitudeToMacLeodBoynton.mat</strong></p> <p>This file stores a variable ‘stimulusMagnitudeToMacLeodBoynton’ (8*100*2) which describes correspondence map between stimulus magnitude and MacLeod-Boynton chromaticity.</p> <p> </p> <p>1st channel: hue direction from 0 degree to 315 degree, 45 degree step</p> <p>2nd channel: magnitude from 1 to 100</p> <p>3rd channel: MacLeod-Boynton coordinate, 1 being L/(L+M) and 2 being S/(L+M)</p> <p> </p>
Dataset related to article "Imaging the kidney with an unconventional scanning electron microscopy technique: analysis of the subpodocyte space in diabetic mice".
<p><strong>Datasets:</strong></p> <p><strong>Table 1_Systemic parameters.xlsx </strong>- dataset related to the systemic parameters. These data are presented in Table 1. </p> <p><strong>Figure 6_Morphometric analysis.xlsx </strong>- dataset related to the morphometric characterization of the subpodocyte space and podocytes. These data are presented in Figure 6. </p> <p><strong>Abstract of the manuscript</strong></p> <p>Transmission electron microscopy (TEM) remains the gold standard for renal histopathological diagnoses, given its higher resolving power compared to light microscopy. However, it imposes several limitations on pathologists, including longer sample preparation time and a small observation area. To overcome these, we introduced a scanning electron microscopy (SEM) technique for imaging resin-embedded semi-thin sections of renal tissue. We developed a rapid tissue preparation protocol for experimental models and human biopsies which, alongside SEM digital imaging acquisition of secondary electrons (SE-SEM), enables fast electron microscopy examination, with a resolution similar to that achieved by TEM. We used this unconventional SEM imaging approach to investigate the subpodocyte space (SPS) in BTBR <em>ob/ob</em> mice with type 2 diabetes. Analysis of semi-thin sections with secondary electrons revealed that the SPS had expanded in volume and covered large areas of the glomerular basement membrane, forming wide spaces between the podocyte body and underlying filtering membrane. Our results show that SE-SEM is a valuable tool for imaging the kidney at the ultrastructural level, filling the magnification gap between light microscopy and TEM, and reveal that in diabetic mice the SPS is larger than in normal controls, which is associated with podocyte damage and impaired kidney function.</p>
Wheat disease images (small dataset)
<p>999 wheat disease images, including yellow rust, brown rust, septoria, mildew and healthy leaves taken in realistic growth conditions. This is a small subset of the full dataset containing 19,172 images over the five categories.</p> <p>The full dataset is available on request from James Brown, james.brown@jic.ac.uk.</p>
A phenotyping weeds image dataset for open scientific research
<p>This in-house-built image dataset consists of 10810 weed images captured through a dedicated phenotyping activity in quasi-field conditions. The targets are seven of the most widespread and hard-to-control weeds in wheat (but also in other winter cereals) in the Mediterranean environment.</p> <p>In the framework of open scientific research, our aim is to share low-cost and high-resolution images representing challenging agricultural environments where weather, lighting and other factors can change by the hour and affect the quality of images. This way the dataset could be used to train Artificial Intelligence architectures designed for weed recognition, allowing the implementation of tools directly available in the field for farmers and technicians for effective and timely weed management.</p> <p>The dataset encompasses weed images ranging from the post-emergence phase (i.e. the complete cotyledons unfolding) until the pre-flowering stage. The weed selection was made by considering (i) bottom-up information and specific requests by farmers and technicians, (ii) weed susceptibility to commercial formulations for chemical control <50%, reported at least twice by field technicians, (iii) the difficulty of control considering any methods, and (iv) the type of growing season (overlapping or not with wheat). The final weeds selection encompassed both monocots (<em>Avena sterilis</em> and <em>Lolium multiflorum</em>) and dicots (<em>Convolvulus arvensis</em>, <em>Fumaria officinalis</em>, <em>Papaver rhoeas</em>, <em>Veronica persica</em> and <em>Vicia sativa</em>).</p> <p>Image acquisition was facilitated by using a white panel as a background; this helped to (i) spread the light and thereby make the plants well-illuminated, while still avoiding strong shadows when using the flash and (ii) simplify image processing. The images were acquired with a Canon EOS 700D hand-held camera set in the macro mode with aperture, shutter speed, ISO and flash in auto mode. Photo capture timing, target distances and light conditions did not have a fixed pattern but were deliberately programmed to vary in such a way as to mimic field conditions. For image shooting at various times of the day, the only precaution was to frame the subject with homogeneous light conditions (full sunlight/full shade). The varied outdoor conditions (light, distance, timing) and camera type (RGB) with auto mode were essential features to make the images photos look similar to those that a user can take in a field, for example with a smartphone camera.</p> <p>After selection and categorization, images were cropped to select the region of interest following the 1:1 ratio but maintaining a minimum size of 512 x 512 pixels.</p> <p> </p> <p>More details on the dataset and its use for weed recognition tasks will be soon available in the proceedings of the forthcoming ECPA conference (2-6 July 2023, Bologna, Italy).</p>
VegAnn: Vegetation Annotation of a large multi-crop RGB Dataset acquired under diverse conditions for image segmentation
<p> VegAnn - Vegetation Annotation - dataset, a collection of 3795 multi-crop RGB images acquired for different phenological stages using different systems and platforms in diverse illumination conditions. </p>
NIR-MFCO dataset: Near-infrared-based false-color images of post-consumer plastics at different material flow compositions and material flow presentations
<p>Determining mass-based material flow compositions (MFCOs) is crucial for assessing and optimizing the recycling of post-consumer plastics. Currently, MFCOs in plastic recycling are mostly determined through manual sorting analysis, but the use of inline near-infrared (NIR) sensors holds potential to automate the characterization process, paving the way for novel sensor-based material flow characterization (SBMC) applications. The NIR-MFCO dataset aims to expedite SBMC research by providing NIR-based false-color images of plastic material flows with their corresponding MFCOs. The false-color images were created through the pixel-based classification of binary material mixtures using a hyperspectral imaging camera (EVK HELIOS NIR G2-320; 990 nm – 1678 nm wavelength range) and the on-chip classification algorithm (CLASS 32). The resulting NIR-MFCO dataset includes <em>n</em> = 880 false-color images from three test series: (T1) high-density polyethylene (HDPE) and polyethylene terephthalate (PET) flakes, (T2a) post-consumer HDPE packaging and PET bottles, and (T2b) post-consumer HDPE packaging and beverage cartons for <em>n</em> = 11 different HDPE shares (0% - 50%) at four different material flow presentations (singled, monolayer, bulk height H1, bulk height H2). The dataset can be used, e.g., to train machine learning algorithms, evaluate the accuracy of inline SBMC applications, and deepen the understanding of segregation effects of anthropogenic material flows, thus further advancing SBMC research and enhancing post-consumer plastic recycling.</p>
WE3DS: An RGB-D image dataset for semantic segmentation in agriculture
<p>Here, we introduce a novel RGB-D image database (WE3DS) for semantic segmentation in crop farming. It contains 2,568 RGB-D images (color image and distance map) and hand-annotated ground-truth masks for semantic segmentation and is the first RGB-D image dataset for multi-class plant species semantic segmentation task. Images were taken under natural light conditions using an RGB-D sensor consisting of two RGB cameras in a stereo setup.</p> <p> </p> <p><strong>Please cite the original source when using this dataset.</strong></p> <p>Kitzler, F.; Barta, N.; Neugschwandtner, R.W.; Gronauer, A.; Motsch, V. WE3DS: An RGB-D Image Dataset for Semantic Segmentation in Agriculture. <em>Sensors</em> <strong>2023</strong>, <em>23</em>, 2713. <a href="https://doi.org/10.3390/s23052713">https://doi.org/10.3390/s23052713 </a></p>
Global Wetlands: Luderick Seagrass Dataset - Test Set Image Patches
<p>This dataset is a test dataset of image patches created from the 'novel-test' split of the Global Wetlands Luderick-Seagrass dataset. The original images were divided as a grid into 50 image patches. The image patches were manually labeled into 'Background', 'Fish' and 'Seagrass' sets. The images were otherwise unaltered. </p> <p>We contribute this test dataset of underwater image patches to facilitate evaluation of coarse segmentation seagrass methods.</p> <p>Original dataset description: "This dataset comprises of annotated footage of Girella tricuspidata in two estuary systems in South East Queensland, Australia. This data is suitable for a range of classification and object detection research in unconstrained underwater environments."</p> <p>Original dataset citation: Ditria, Ellen M; Connolly, Rod M; Jinks, Eric L; Lopez-Marcano, Sebastian (2021)<strong>:</strong> Annotated video footage for automated identification and counting of fish in unconstrained marine environments. <em>PANGAEA</em>, <a href="https://doi.org/10.1594/PANGAEA.926930">https://doi.org/10.1594/PANGAEA.926930</a>.</p> <p>The original dataset is available at: <br> https://github.com/globalwetlands/luderick-seagrass<br> https://download.pangaea.de/dataset/926930/files/Fish_automated_identification_and_counting.zip<br> https://globalwetlands.blob.core.windows.net/globalwetlands-public/datasets/luderick-seagrass/luderick-seagrass.zip</p>
An Occlusion and Pose Sensitive Image Dataset for Black Ear Recognition
<p><strong>RESEARCH APPROACH</strong></p> <p>The research approach adopted for the study consists of seven phases which includes as shown in Figure 1:</p> <ol> <li>Pre-acquisition</li> <li>data pre-processing</li> <li>Raw images collection</li> <li>Image pre-processing</li> <li>Naming of images</li> <li>Dataset Repository</li> <li>Performance Evaluation</li> </ol> <p>The different phases in the study are discussed in the sections below.</p> <p> </p> <p><strong>PRE-ACQUISITION</strong></p> <p>The volunteers are given brief orientation on how their data will be managed and used for research purposes only. After the volunteers agrees, a consent form is given to be read and signed. The sample of the consent form filled by the volunteers is shown in Figure 1.</p> <p>The capturing of images was started with the setup of the imaging device. The camera is set up on a tripod stand in stationary position at the height 90 from the floor and distance 20cm from the subject.</p> <p> </p> <p><strong>EAR </strong><strong>IMAGE ACQUISITION</strong></p> <p>Image acquisition is an action of retrieving image from an external source for further processing. The image acquisition is purely a hardware dependent process by capturing unprocessed images of the volunteers using a professional camera. This was acquired through a subject posing in front of the camera. It is also a process through which digital representation of a scene can be obtained. This representation is known as an image and its elements are called pixels (picture elements). The imaging sensor/camera used in this study is a Canon E0S 60D professional camera which is placed at a distance of 3 feet form the subject and 20m from the ground. </p> <p>This is the first step in this project to achieve the project’s aim of developing an occlusion and pose sensitive image dataset for black ear recognition. (OPIB ear dataset). To achieve the objectives of this study, a set of black ear images were collected mostly from undergraduate students at a public University in Nigeria.</p> <p> </p> <p>The image dataset required is captured in two scenarios:</p> <p>1. uncontrolled environment with a surveillance camera</p> <ol> </ol> <p>The image dataset captured is purely black ear with partial occlusion in a constrained and unconstrained environment.</p> <p> </p> <p>2. controlled environment with professional cameras</p> <p>The ear images captured were from black subjects in controlled environment. To make the OPIB dataset pose invariant, the volunteers stand on a marked positions on the floor indicating the angles at which the imaging sensor was captured the volunteers’ ear. The capturing of the images in this category requires that the subject stand and rotates in the following angles 60<sup>o</sup>, 30<sup>o</sup> and 0<sup>o</sup> towards their right side to capture the left ear and then towards the left to capture the right ear (Fernando <em>et al.,</em> 2017) as shown in Figure 4. Six (6) images were captured per subject at angles 60<sup>o</sup>, 30<sup>o</sup> and 0<sup>o</sup> for the left and right ears of 152 volunteers making a total of 907 images <strong><em>(five volunteers had 5 images instead of 6, hence f</em></strong><strong><em>olders 34, 22, 51, 99 and 102 contain 5 images).</em></strong></p> <p>To make the OPIB dataset occlusion and pose sensitive, partial occlusion of the subject’s ears were simulated using rings, hearing aid, scarf, earphone/ear pods, etc. before the images are captured.</p> <p> </p> <table> <tbody> <tr> <td> <p><strong>CONSENT FORM</strong></p> <p>This form was designed to obtain participant’s consent on the project titled: <strong>An Occlusion and Pose Sensitive Image Dataset for Black Ear Recognition</strong><strong> (OPIB)</strong>. The information is purely needed for academic research purposes and the ear images collected will curated anonymously and the identity of the volunteers will not be shared with anyone. The images will be uploaded on online repository to aid research in ear biometrics.</p> <p>The participation is voluntary, and the participant can withdraw from the project any time before the final dataset is curated and warehoused.</p> <p>Kindly sign the form to signify your consent.</p> <p><strong><em>I consent to my image being recorded in form of still images or video surveillance as part of the OPIB ear images project.</em></strong></p> <p><strong>Tick as appropriate:</strong></p> <p><strong>GENDER</strong> Male Female</p> <p><strong>AGE</strong> (18-25) (26-35) (36-50)</p> <p> </p> <p>………………………………..</p> <p>SIGNED</p> </td> </tr> </tbody> </table> <p> </p> <p><strong>Figure 1</strong>: Sample of Subject’s Consent Form for the OPIB ear dataset</p> <p> </p> <p><strong>RAW IMAGE COLLECTION</strong></p> <p>The ear images were captured using a digital camera which was set to JPEG because if the camera format is set to raw, no processing will be applied, hence the stored file will contain more tonal and colour data. However, if set to JPEG, the image data will be processed, compressed and stored in the appropriate folders.</p> <p> </p> <p><strong>IMAGE PRE-PROCESSING </strong></p> <p>The aim of pre-processing is to improve the quality of the images with regards to contrast, brightness and other metrics. It also includes operations such as: cropping, resizing, rescaling, etc. which are important aspect of image analysis aimed at dimensionality reduction. The images are downloaded on a laptop for processing using MATLAB.</p> <p> </p> <p><strong>Image Cropping</strong></p> <p>The first step in image pre-processing is image cropping. Some irrelevant parts of the image can be removed, and the image Region of Interest (ROI) is focused. This tool provides a user with the size information of the cropped image. MATLAB function for image cropping realizes this operation interactively by waiting for a user to specify the crop rectangle with the mouse and operate on the current axes. The output images of the cropping process are of the same class as the input image.</p> <p><strong>Naming of OPIB Ear Images</strong></p> <p>The OPIB ear images were labelled based on the naming convention formulated from this study as shown in Figure 5. The images are given unique names that specifies the subject, the side of the ear (left or right) and the angle of capture. The first and second letters (SU) in the image names is block letter simply representing subject for subject 1-to-n in the dataset, while the left and right ears is distinguished using L1, L2, L3 and R1, R2, R3 for angles 60<sup>0</sup>, 30<sup>0</sup> and 0<sup>0</sup><sub>, </sub>respectively as shown in Table 1.</p> <p> </p> <p><strong>Table 1: Naming Convention for OPIB ear images</strong></p> <table align="center"> <tbody> <tr> <td> <p>NAMING CONVENTION</p> </td> </tr> <tr> <td> <p>Label</p> <p>Degrees 60<sup>0</sup> 30<sup>0</sup> 0<sup>0</sup></p> </td> </tr> <tr> <td> <p>No of the degree 1 2 3</p> </td> </tr> <tr> <td> <p>Subject 1 indicates (first image in dataset) SU<sub>1</sub></p> </td> </tr> <tr> <td> <p>Subject n indicates (last image in dataset) SU<sub>n</sub></p> </td> </tr> <tr> <td> <p>Left Image 1 L 1</p> <p>Left image n L n</p> <p>Right Image 1 R 1</p> <p>Right Image n R n</p> </td> </tr> <tr> <td> <p>SU1L<sub>1</sub> SU1R<sub>I</sub></p> <p>SU1L<sub>2</sub> SU1R<sub>2</sub> </p> <p>SU1L<sub>3</sub> SU1R<sub>3</sub></p> </td> </tr> </tbody> </table> <p> </p> <p><strong>OPIB EAR DATASET EVALUATION</strong></p> <p>The prominent challenges with the current evaluation practices in the field of ear biometrics are the use of different databases, different evaluation matrices, different classifiers that mask the feature extraction performance and the time spent developing framework (Abaza <em>et al.</em>, 2013; Emeršič <em>et al.,</em> 2017).</p> <p>The toolbox provides environment in which the evaluation of methods for person recognition based on ear biometric data is simplified. It executes all the dataset reads and classification based on ear descriptors.</p> <p> </p> <p><strong>DESCRIPTION OF OPIB EAR DATASET</strong></p> <p>OPIB ear dataset was organised into a structure with each folder containing 6 images of the same person. The images were captured with both left and right ear at angle 0, 30 and 60 degrees. The images were occluded with earing, scarves and headphone etc. The collection of the dataset was done both indoor and outdoor. The dataset was gathered through the student at a public university in Nigeria. The percentage of female (40.35%) while Male (59.65%). The ear dataset was captured through a profession camera Nikon D 350. It was set-up with a camera stand where an individual captured in a process order. A total number of 907 images was gathered.</p> <p>The challenges encountered in term of gathering students for capturing, processing of the images and annotations. The volunteers were given a brief orientation on what their ear could be used for before, it was captured, for processing. It was a great task in arranging the ear (dataset) into folders and naming accordingly.</p> <p> </p> <p><strong>Table 2</strong>: Overview of the OPIB Ear Dataset</p> <table align="left"> <tbody> <tr> <td> <p>Location</p> </td> <td> <p>Both Indoor and outdoor environment</p> </td> </tr> <tr> <td> <p>Information about Volunteers</p> </td> <td> <p>Students</p> </td> </tr> <tr> <td> <p>Gender</p> </td> <td> <p>Female (40.35%) and male (59.65%)</p> </td> </tr> <tr> <td> <p>Head Side Left and Right</p> </td> <td> <p>Side Left and Right</p> </td> </tr> <tr> <td> <p>Total number of volunteers</p> </td> <td> <p>152</p> </td> </tr> <tr> <td> <p>Per Subject images</p> </td> <td> <p>3 images of left ear and 3 images of right ear</p> </td> </tr> <tr> <td> <p>Total Images</p> </td> <td> <p>907</p> </td> </tr> <tr> <td> <p>Age group</p> </td> <td> <p>18 to 35 years</p> </td> </tr> <tr> <td> <p>Colour Representation</p> </td> <td> <p>RGB</p> </td> </tr> <tr> <td> <p>Image Resolution</p> </td> <td> <p>224x224</p> </td> </tr> </tbody> </table> <p> </p> <p> </p> <p> </p> <p> </p> <p> </p> <p> </p> <p> </p> <p> </p> <p> </p> <p> </p> <p> </p> <p> </p> <p> </p> <p> </p>
Oxy-fuel Cutting Task State Image Dataset
<p><strong>Associated Paper: </strong>CNN-based Task State Estimation for Safer Automation of Oxy-fuel Metal Cutting<br><strong>Paper Status:</strong> Published (IEEE CASE 2023, doi: <a href="https://doi.org/10.1109/CASE56687.2023.10260647" target="_blank" rel="noopener">10.1109/CASE56687.2023.10260647</a>)</p> <p><strong>PAPER ABSTRACT:</strong></p> <p>The industrial operation of oxy-fuel metal cutting via gas torches involves tasks such as ignition, preheating, and combustion along the target surface. Automated oxy-fuel cutting systems are exposed to risks and anomalies that can lead to incorrect actions and safety hazards. In this paper, we develop a classifier for online task state estimation to assess the cutting robot’s actions, detect anomalies, and reduce the risk of hazards. Using representative footage from our robotic cutting experiments, we curate an image dataset labeled with four types of cutting task states. Using deep learning methods, we design and train a convolutional neural network model for classifying the cutting task state from input images. The classifier architecture is optimized for rapid inferences during online estimation. After evaluation, our classifier achieves an overall accuracy of 93.8% with high inference speeds on two types of representative hardware. Our ‘Oxy-fuel Cutting Task State’ (OCTS) dataset is available at <a href="https://doi.org/10.5281/zenodo.7734951">doi.org/10.5281/zenodo.7734951</a>.</p> <p><strong>DATASET DESCRIPTION:</strong></p> <p>The Oxy-fuel Cutting Task State (OCTS) dataset contains image data from footage recorded during a series of robotic oxy-fuel metal cutting experiments labeled with one of four cutting task states, identified using their prominent feature:</p> <ul> <li>Torch flame (<strong>TF</strong>): Associated with the vision system calibration task.</li> <li>Preheating pool (<strong>PP</strong>): Associated with the surface conditioning task.</li> <li>Combustion pool (<strong>CP</strong>): Associated with the combustion control task.</li> <li>Not applicable (<strong>NA</strong>): Associated with halting operations since none of the previous elements are identified; this is an anomaly.</li> </ul> <p>The dataset files consist of:</p> <ul> <li><strong>Data: </strong>Available as a ZIP archive split into 5 volumes (~2.8 GB each).</li> <li><strong>Labels:</strong> Available in JSON format.</li> <li><strong>Metadata:</strong> Available in CSV and PDF formats, contains the individual experiment set IDs, their dates and times, their total frame counts, and their label-wise frame counts.</li> </ul> <p><strong>DATASET LICENSE:</strong></p> <p>This work is licensed under a <a href="http://creativecommons.org/licenses/by-nc/4.0/">Creative Commons Attribution-NonCommercial 4.0 International License</a> (CC BY-NC 4.0).</p> <p><strong>DATA INSTRUCTIONS:</strong></p> <p>To extract the ZIP archive, download all five ZIP volumes into a common directory and extract the file <strong>dataset.zip.001</strong>. After extraction, 50 directories are obtained ('S01', 'S02', …, 'S50'). These contains the raw data (image frames) of each of the 50 individual cutting experiments. The image filenames are their frame number ('000000.jpeg', '000001.jpeg', …). All images are in JPEG format. All image filenames are their 6-digit frame number (includes leading zeroes such as in '004021.jpeg') for a particular experiment. Essentially, this is the sequential image data from the footage of each experiment.</p> <p><strong>JSON INSTRUCTIONS:</strong></p> <p>The JSON file partitions the images of each experiment set into the four labels. The first JSON level contains the experiment set ID as a string ('S01', 'S02', …, 'S50'). The second JSON level contains the four labels ('TF', 'PP', 'CP', 'NA') for each set ID. The third JSON level contains arrays of strings containing the frame number (filename without extension) of each image (e.g., ['000000', '000001', , …]). Usage of the JSON file is illustrated in the following Python code snippet:</p> <pre><code>import json with open ("labels.json") as json_file: labels = json.load(json_file) # `labels` is a dictionary. # Get all image filenames (frame numbers) from experiment `S01` in the `NA` label. labels['S01']['NA'] # returns list of image filenames (strings) #output: ['003843', '003844', …, '003978', '003979']</code></pre> <p>Thus, the labels are retrieved for each of the images in each of the set IDs.</p> <p><strong>METADATA INSTRUCTIONS:</strong></p> <p>The metadata associates the set ID of each experiment to its recording date and time. In addition, it lists the total frames of each experiment and the frame count in each of the four labels ('TF', 'PP', 'CP', 'NA'). This is available in PDF format for convenient viewing but also in CSV format.</p>
HeiPorSPECTRAL - the Heidelberg Porcine HyperSPECTRAL Imaging Dataset of 20 Physiological Organs
<p>Hyperspectral Imaging (HSI) is a relatively new medical imaging modality that exploits an area of diagnostic potential formerly untouched. Although exploratory translational and clinical studies exist, no surgical HSI datasets are openly accessible to the general scientific community. To address this bottleneck, this publication releases HeiPorSPECTRAL (<a href="https://www.heiporspectral.org">https://www.heiporspectral.org</a>), the first annotated high-quality standardized HSI dataset. It comprises 5,758 spectral images acquired with the TIVITA Tissue and annotated with 20 physiological porcine organs in a total number of 11 pigs. Each HSI image features a resolution of 480 x 640 pixels acquired over the 500-1000 nm wavelength range. The acquisition protocol has been designed such that the variability of organ spectra as a function of several parameters including the camera pose and the individual can be assessed. A comprehensive technical validation confirmed both the quality of the raw data and the annotations. We envision potential reuse within this dataset, but also its reuse as baseline data for future research questions outside this dataset, such as the detection of pathologies.</p>
Dataset: CODEX highly multiplexed tissue imaging in pancreas
<p><strong>Human pancreas</strong></p> <p>This dataset was acquired using CODEX, multiplexed single-cell imaging technology for spatial profiling, where all image data is in .tif format and it includes an associated imaging metadata .csv file. The combination of the targets present in this experiment define some of the main cell types and anatomical structures in human pancreas tissue.</p> <p>This dataset is a 12-highly multiplexed experiment performed on a human pancreas 5 μm section including the nuclear marker Hoechst and antibodies conjugated with oligo-sequences directed against the individual markers. Images were acquired using a Leica DMi8 widefield microscope, a digital CMOS camera (Hamamatsu, ORCA-Flash4.0 V3), and a 20x (0.75) NA dry objective. The light source was a SOLA-SM-II. All images were captured at a 16-bit depth with the following dimensions: x (0.325 μm), y (0.325 μm), and z (1.5 μm). In addition, images were processed, tiled and merged using the CODEX® Processor application (CODEX Processor 1.7.0.6).</p>
FIOLA: an accelerated pipeline for Fluorescence Imaging OnLine Analysis calcium dataset
<p>The dataset was used in paper FIOLA: an accelerated pipeline for Fluorescence Imaging OnLine Analysis named as 1MP. The dataset was only used to test FIOLA motion correction performance.<br> The dataset was collected for the paper Sensory-driven enhancement of calcium signals in individual Purkinje cell dendrites of awake mice (link: https://pubmed.ncbi.nlm.nih.gov/24582958/) but never published before. Data was recorded in the left lobule of the cerebellum of an awake mouse using the calcium indicator GCaMP6f. GCaMP6f was selectively expressed in Purkinje cells via a combinatorial virus strategy (as explained in the paper).</p> <p>For other datasets used in paper FIOLA, check the original paper and sources they were published.</p> <p> </p> <p> </p>
Active Region Magnetograms for Solar Flare Prediction: Reduced Resolution Dataset Images
<p>This dataset is the images associated with Dryad dataset https://doi.org/10.5061/dryad.jq2bvq898. These images are consistently sized images of active region magnetograms from the National Aeronautics and Space Administration's (NASA's) Solar Dynamics Observatory (SDO). These data are the reduced resolution (224x224 pixels) images in .png format.</p>
Yoga for all: A Comprehensive Collection of Yoga Images and Videos dataset
<p>The dataset comprises both images and videos depicting right and wrong postures for a variety of Yoga asanas. The focus of the dataset is on 10 specific Yoga postures, namely Anantasana, Ardhakati Chakrasana, Bhujangasana, Kati Chakrasana, Marjariasana, Parvatasana, Sarvangasana, Tadasana, Vajrasana, and Viparita Karani.</p> <p>The Image dataset comprises a total of 11,344 images and is organized into 10 subfolders, each corresponding to a specific Yoga asana. Within each subfolder, there are two additional folders labeled "Right Steps" and "Wrong Steps". The "Right Steps" folder contains several subfolders, each representing a specific step in the right sequence of the Yoga asana and displaying the corresponding images. On the other hand, the "Wrong Steps" folder includes multiple subfolders, each showing images of an wrong steps in the sequence of the Yoga asana.</p> <p>The Yoga asana video dataset consists of 8 videos for each posture, comprising 4 videos demonstrating the right posture from 4 different angles and 4 videos exhibiting the wrong posture from 4 different angles. This dataset includes a total of 80 videos for 10 Yoga asanas, with 40 videos demonstrating the right postures captured from 4 different angles, and 40 videos illustrating the wrong postures from 4 different angles.</p> <p>The dataset has advantages for various groups, such as app developers, machine learning researchers, Yoga instructors, and Yoga practitioners. Machine learning researchers can utilize this dataset to train computer vision algorithms in recognizing and categorizing various yoga postures automatically. App developers can use the dataset to generate yoga apps that present users with visual guidance on executing each posture and keeping track of their progress.</p>
Image dataset for the creation of an automatic system for meteor fall detection
<p>Image dataset with sky photos showing the occurrence or non-occurrence of falling meteors. The database comprises 7,000 images in JPEG format -- 3,850 (55%) images show the event of falling meteors, and 3,150 (45%) images show no meteors. Different instruments captured the photos from 2014 to 2023. We used the images to train a deep-learning neural network for an automatic falling meteor detector.</p> <p>The primary image data sources were the Brazilian Meteor Observation Network (BRAMON -- <a href="http://www.bramonmeteor.org">http://www.bramonmeteor.org</a>), UK Meteor Network (UKMON -- <a href="https://ukmeteornetwork.co.uk">https://ukmeteornetwork.co.uk</a>), and <em>Base des Observateurs Amateurs de Météores</em> (BOAM -- <a href="http://boam.fr">http://boam.fr</a>) repositories.</p> <p><strong>Folders Structure</strong></p> <p>We divided the folder structure into two levels. In the first level, we have two folders: RawImages, which holds images with captions stored in the repositories; and CroppedImages, which contains images without the captions (we cropped a band of 24 pixels in the lower part of the image).</p> <p>In the second level, in each of the previous folders, we have another two folders: meteor, which has images with meteors; and non-meteors, with images without occurrences of meteors.</p> <p><strong>Naming pattern for the files</strong></p> <p>The naming pattern in the meteor folder follows the format <source>_<date>_<id>.jpg where:</p> <ul> <li><source> is one of the 3 data sources: bramon, ukmon, or boam.</li> <li><date> is the date-time the instrument captured the image in the format yyyymmdd_hhnnss (y:year, m:month, d:day, h:hours, n:minutes, s:seconds).</li> <li><id> is an identifier from a specific source to avoid date-time conflicts: <ul> <li>BRAMON: radiant identifier.</li> <li>UKMON: station identifier.</li> <li>BOAM: station identifier.</li> </ul> </li> </ul> <p>For the non-meteor folder, the naming pattern is <source>_<date>_nonmeteor.jpg to avoid homonyms (with the same date-time) and to identify that they are images of non-meteors.</p>
SCA-2023: A two-part dataset for benchmarking the methods of image precompensation for users with refractive errors
<p>The recent practices of demonstrating various static and video images to users by means of digital, processor-controlled, often self-luminous devices (computer monitors, smartphone and tablet screens, etc.) have spurred the development of various methods for improving the perception of such images through their computer processing. In particular, this applies to the task of precompensating images shown to users with various anomalies of refraction of the eyes (e.g. myopia or astigmatism) in situations where they are not equipped with glasses or other corrective devices. Researchers have proposed a considerable number of such precompensation methods, but to this day there has been no way to accurately compare their quality. We propose an original dataset, which we called “SCA-2023”, of images specially designed for this purpose. Its most important feature is the fact that it includes not only a set of ground-truth images for implementing the precompensation transform, but also a separate set of images characterizing specific types and degrees of manifestation of the refractive errors. The benchmarking procedure itself includes applying the precompensation transformation to a certain image from the first part of the dataset, computer simulation of the so-called retinal image (distribution of light on the retina of an imaginary observer) based on the selection of the “distorting eye” from the second part of the dataset, and evaluating the similarity of this image to the ground-truth image, using any of the commonly used similarity metrics for this purpose.</p>
Active Region Magnetograms for Solar Flare Prediction: Full Resolution Dataset Images for ARs 1307 through 1505
<p>This dataset is the images associated with Dryad dataset https://doi.org/10.5061/dryad.dv41ns23n. These images are consistently sized images of active region magnetograms from the National Aeronautics and Space Administration's (NASA's) Solar Dynamics Observatory (SDO). These data are the full sized images (600x600 pixels) for active regions (ARs) 1307 through 1505 in .fits format.</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.