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.
1,433
datasets available to search
ShareScore release 0.9.0
Dataset results
1,433 results for “mask”
The Noh Mask Effect - Archive of Research Materials on Noh Masks and Facial Expression
<p>Contains materials related to research on culture and viewpoint-dependent perception of facial expressions portrayed on masks used in the Japanese Noh Theatre. The archive includes the images used in the experiments as well as various documents related to the project.</p> <p><strong>Animations</strong></p> <ul> <li>animated gif of the antique Magojiro mask tilting forwards & back</li> <li>mp4 file with a comparison of new & old masks at different tilts</li> </ul> <p><strong>Article</strong></p> <ul> <li>pdf of article on the research project</li> <li>atr99.pdf contains a short summary of the project that may be helpful</li> <li>manuscript of the article (latex source files)</li> <li>correspondence with the publisher</li> <li>final versions of the article figures</li> </ul> <p><strong>Composites</strong></p> <ul> <li>composite figures of masks and human face at varying tilts</li> </ul> <p><strong>Experimental Stimuli</strong></p> <ul> <li>folders XA, XC, XH, XT</li> <li>only XA and XH were used for experiments reported in the article</li> <li>tilt angles range from -30 to 30 degrees in 5 degree steps</li> <li>XA: antique Magojiro mask from Edo period</li> <li>XC: Magojiro mask from the current era (1980s or 90s)</li> <li>XH: female human face, images rendered from 3D scan</li> <li>XT: Ko-omote mask made by an amateur carver (collection of MJL)</li> </ul> <p><strong>Misc</strong></p> <ul> <li>'behind the scenes' photos</li> <li>view of the Noh stage at the Nara Shin Kokai Do in Nara Koen</li> <li>view of the camera and apparatus used to adjust the tilt angle</li> <li>shape images rendered from scans of the Ko-omote mask and human face</li> <li>view of the Magojiro mask from the current era (collection of the Komparu family)</li> <li>close up of mouth area of the Magojiro mask from the current era</li> <li>view of the antique Edo period Magojiro mask</li> <li>view of the reverse of the antique Magojiro mask showing inscriptions</li> </ul> <p>Thank you for your interest in the project.</p> <p>Michael Lyons, Ph.D.<br> Professor of Image Arts and Science<br> Ritsumeikan University<br> Kyoto, Japan</p>
3D Mask Attack Dataset (3DMAD)
<p><strong>The 3D Mask Attack Database (3DMAD) is a biometric (face) spoofing database.</strong> It contains 76500 frames of 17 persons, recorded using Kinect for both real-access and spoofing attacks. Each frame consists of:</p> <ul> <li>a <strong>depth image</strong> (640x480 pixels – 1x11 bits)</li> <li>the corresponding <strong>RGB image</strong> (640x480 pixels – 3x8 bits)</li> <li>manually annotated <strong>eye positions</strong> (with respect to the RGB image).</li> </ul> <p>The data is collected in 3 different sessions for all subjects and for each session 5 videos of 300 frames are captured. The recordings are done under controlled conditions, with frontal-view and neutral expression. The first two sessions are dedicated to the real access samples, in which subjects are recorded with a time delay of ~2 weeks between the acquisitions. In the third session, 3D mask attacks are captured by a single operator (attacker).</p> <p>In each video, the eye-positions are manually labelled for every 1st, 61st, 121st, 181st, 241st and 300th frames and they are linearly interpolated for the rest.</p> <p>The real-size masks are obtained using "ThatsMyFace.com". The database additionally contains the face images used to generate these masks (1 frontal and 2 profiles) and paper-cut masks that are also produced by the same service and using the same images.</p> <p>The satellite package which contains the <a href="https://www.idiap.ch/software/bob/">Bob</a> accessor methods to use this database directly from Python, with the certified protocols, is available in two different distribution formats:</p> <ol> <li>You can download it from <a href="https://pypi.org/project/xbob.db.maskattack/">PyPI</a>, or</li> <li>You can download it in its source form from its <a href="https://github.com/bioidiap/xbob.db.maskattack">git repository</a>.</li> </ol> <p><br> <strong>Acknowledgments</strong></p> <p>If you use this database, please cite the following publication:</p> <p>Nesli Erdogmus and Sébastien Marcel, "Spoofing in 2D Face Recognition with 3D Masks and Anti-spoofing with Kinect", Biometrics: Theory, Applications and Systems, 2013.<br> <a href="https://doi.org/10.1109/BTAS.2013.6712688">10.1109/BTAS.2013.6712688</a><br> <a href="https://publications.idiap.ch/index.php/publications/show/2657">https://publications.idiap.ch/index.php/publications/show/2657</a></p>
Mobile Custom Silicone Mask Attack Dataset (CSMAD-Mobile)
<p><strong>This dataset consists of face & silicon masks images from 8 different subjects captured with 3 different smartphones.</strong></p> <p>This dataset consists of images captured from 8 different bona fide subjects using three different smartphones (iPhone X, Samsung S7 and Samsung S8). For each subject within the database, varying number of samples are collected using all the three phones. Similarly, the silicone masks of each of the subject is collected using three phones. The masks, each costing about USD 4000, have been manufactured by a professional special-effects company.</p> <p>For the bona fide presentations of the same eight subjects, each data subject is asked to pose in a manner compliant to standard portrait capture. The data is captured indoors, with adequate artificial lighting. Silicone mask presentations have been captured under similar conditions, by placing the masks on their bespoke support provided by the manufacturer, with prosthetic eyes and silicone eye sockets.</p> <p>The database is organized in three folders corresponding to three smartphones and further each subject within the database is organized in sub-folders.</p> <p>The files are named using the convention "PHONE/CLASS/SUBJECTNUMBER/PHONEIDENTIFIER-PRESENTATION-SUBJECTNUMBER-SAMPLENUMBER.jpg".</p> <ul> <li>PHONE is iPhone, SamS7 or SamS8 corresponding to iPhone, Samsung S7 and Samsung S8 respectively.</li> <li>CLASS is "Bona" or "Mask" indicating the bona fide presentation or mask presentation respectively.</li> <li>SUBJECTNUMBER is "s1" to "s8" indicating 8 subjects in the database.</li> <li>PHONEIDENTIFIER is the two letter keyword as given by "ip", "s7" and "s8" corresponding to iPhone, Samsung S7 and Samsung S7 respectively.</li> <li>PRESENTATION identifies bona-fide or mask-attack presentation using 2 letter identifier "bp" or "ap".</li> <li>SAMPLENUMBER indicates the sample number of the subject.</li> </ul> <p> </p> <p><strong>Reference</strong></p> <p>If you publish results using this dataset, please cite the following publication.</p> <p>“Custom Silicone Face Masks - Vulnerability of Commercial Face Recognition Systems & Presentation Attack Detection”, R. Raghavendra, S. Venkatesh, K. B. Raja, S. Bhattacharjee, P. Wasnik, S. Marcel, and C. Busch. IAPR/IEEE International Workshop on Biometrics and Forensics (IWBF), 2019.<br> <a href="https://doi.org/10.1109/IWBF.2019.8739236">10.1109/IWBF.2019.8739236</a><br> <a href="https://publications.idiap.ch/index.php/publications/show/4065">https://publications.idiap.ch/index.php/publications/show/4065</a></p> <p> </p>
Custom Silicone Mask Attack Dataset (CSMAD)
<p><strong>The Custom Silicone Mask Attack Dataset (CSMAD) contains presentation attacks made of six custom-made silicone masks. Each mask cost about USD 4000. The dataset is designed for face presentation attack detection experiments.</strong></p> <p>The Custom Silicone Mask Attack Dataset (CSMAD) has been collected at the Idiap Research Institute. It is intended for face presentation attack detection experiments, where the presentation attacks have been mounted using a custom-made silicone mask of the person (or identity) being attacked.</p> <p>The dataset contains videos of face-presentations, as a set of files specifying the experimental protocol corresponding the experiments presented in the corresponding publication.</p> <p> </p> <p><strong>Reference</strong></p> <p>If you publish results using this dataset, please cite the following publication.</p> <p>Sushil Bhattacharjee, Amir Mohammadi and Sebastien Marcel: "Spoofing Deep Face Recognition With Custom Silicone Masks." in Proceedings of International Conference on Biometrics: Theory, Applications, and Systems (BTAS), 2018.<br> <a href="https://doi.org/10.1109/BTAS.2018.8698550">10.1109/BTAS.2018.8698550</a><br> <a href="https://publications.idiap.ch/index.php/publications/show/3887">http://publications.idiap.ch/index.php/publications/show/3887</a></p> <p> </p> <p><strong>Data Collection</strong></p> <p>Face-biometric data has been collected from 14 subjects to create this dataset. Subjects participating in this data-collection have played three roles: targets, attackers, and bona-fide clients. The subjects represented in the dataset are referred to here with letter-codes: A .. N. The subjects A..F have also been targets. That is, face-data for these six subjects has been used to construct their corresponding flexible masks (made of silicone). These masks have been made by Nimba Creations Ltd., a special effects company.</p> <p>Bona fide presentations have been recorded for all subjects A..N. Attack presentations (presentations where the subject wears one of 6 masks) have been recorded for all six targets, made by different subjects. That is, each target has been attacked several times, each time by a different attacker wearing the mask in question. This is one way of increasing the variability in the dataset. Another way we have augmented the variability of the dataset is by capturing presentations under different illumination conditions. Presentations have been captured in four different lighting conditions:</p> <ul> <li>flourescent ceiling light only</li> <li>halogen lamp illuminating from the left of the subject only</li> <li>halogen lamp illuminating from the right only</li> <li>both halogen lamps illuminating from both sides simultaneously</li> </ul> <p>All presentations have been captured with a green uniform background. See the paper mentioned above for more details of the data-collection process.</p> <p> </p> <p><strong>Dataset Structure</strong></p> <p>The dataset is organized in three subdirectories: ‘attack’, ‘bonafide’, ‘protocols’. The two directories: ‘attack’ and ‘bonafide’ contain presentation-videos and still images for attacks and bona fide presentations, respectively. The folder ‘protocols’ contains text files specifying the experimental protocol for vulnerability analysis of face-recognition (FR) systems.</p> <p>The number of data-files per category are as follows:</p> <ul> <li>‘bonafide’: 87 videos, and 17 still images (in .JPG format). The still images are frontal face images captured using a Nikon Coolpix digital camera.</li> <li>‘attack’: 159, organized in two sub-folders – ‘WEAR’ (108 videos), and ‘STAND’ (51 videos)</li> </ul> <p>The folder ‘attack/WEAR’ contains videos where the attack has been made by a person (attacker) wearing the mask of the target being attacked. The ‘attack/STAND’ folder contains videos where the attack has been made using a the target’s mask mounted on an appropriate stand.</p> <p> </p> <p><strong>Video File Format</strong></p> <p>The video files for the face-presentations are in ‘hdf5’ format (with file-extensions ‘.h5’. The folder structure of the hdf5 file is shown in Figure 1. Each file contains data collected using two cameras:</p> <ul> <li>RealSense SR300 (from Intel): collects images/videos in visible-light (RGB color) , near infrared (NIR) @ 860nm wavelength, and depth maps</li> <li>Compact Pro (from Seek Thermal): collects thermal (long-wave infrared (LWIR)) images.</li> </ul> <p>As shown in Figure 1, frames from the different channels (color, infrared, depth, thermal) from he two cameras are stored in separate directory-hierarchies in the hdf5 file. Each file respresents a video of approximately 10 seconds, or roughly, 300 frames.</p> <p>In the hdf5 file, the directory for SR300 also contains a subdirectory named ‘aligned_color_to_depth’. This folder contains post-processed data, where the frames of depth channel have been aligned with those of the color channel based on the time-stamps of the frames.</p> <p> </p> <p><strong>Experimental Protocol</strong></p> <p>The ‘protocols’ folder contains text files that specify the protocols for vulnerability analysis experiments reported in the paper mentioned above. Please see the README file in the protocols folder for details.</p>
Mask on the Grass
A metal mask scanned on a lawn. Created with Polycam. Source: Objaverse 1.0 / Sketchfab
Storm Anvil Mask Files
<p>This folder contains the storm anvil masks used in the research titled: "Characterization of Reflectance Signatures Within Above Anvil Cirrus Plumes in GOES-16 Infrared and Visible Imagery" by Murphy et al. 2024 (publication in progress in the AGU JGR:Atmospheres journal). It provides 5 storm masks via .npy files that enabled extraction of storm-specific satellite reflectance and brightness temperature values.</p>
Storm Anvil Masks
<p>This folder contains the storm anvil masks used in the research titled: "Characterization of Reflectance Signatures Within Above Anvil Cirrus Plumes in GOES-16 Infrared and Visible Imagery" by Murphy et al. 2024 (publication in progress in the AGU JGR:Atmospheres journal). It provides 5 storm masks via .npy files that enabled extraction of storm-specific satellite reflectance and brightness temperature values.</p>
OCTA image dataset with pixel-level mask annotation for FAZ segmentation
<p>This dataset is publish by the research "<em>A Deep Learning-based Quality Assessment and Segmentation System with a Large-scale Benchmark Dataset for Optical Coherence Tomographic Angiography Image</em>"</p> <p>Detail:</p> <p>This dataset is the pixel-level mask annotation for FAZ segmentation. 1,101 3 × 3 mm<sup>2</sup> sOCTA images chosen from gradable and best OCTA images randomly in subset sOCTA-3x3-10k, and 1,143 6 × 6 mm<sup>2</sup>dOCTA images were annotated by an experienced ophthalmologist.</p> <p>GitHub: <a href="https://github.com/shanzha09/COIPS">https://github.com/shanzha09/COIPS</a></p> <p>These datasets are public available, if you use the dataset or our system in your research, please <strong>cite</strong> our paper: <em><code>A Deep Learning-based Quality Assessment and Segmentation System with a Large-scale Benchmark Dataset for Optical Coherence Tomographic Angiography Image</code></em>.</p> <p>arXiv:<a href="https://arxiv.org/abs/2107.10476v1">https://arxiv.org/abs/2107.10476v1</a></p>
Narrowband Nolise Masking of High-Pass-Noise Derived ABR: Wave V amplitudes and latencies.
<p>Study investigated effect of narrowband noise maskers on click-evoked high-pass noise/derived ABR responses. Amplitudes and Latencies are raw (uV and ms), NOT %amp or Lat-shift.</p>
PHyMAtt (Personalised Hygienic Mask Attacks)
<p>This dataset was used to perform the experiments reported in the IJCB2023 paper "Can personalised hygienic masks be used to attack face recognition systems?".</p> <p>The dataset consists of face videos captured using the ‘selfie’ cameras of five different smartphones : Apple iPhone 12, Apple iPhone 6s, Xiaomi Redmi 6 Pro, Xiaomi Redmi 9A and Samsung Galaxy S9. The dataset contains :</p> <ul> <li><strong>B</strong><strong>ona-fide </strong><strong>face videos</strong><strong>:</strong> 1400 videos of bona-fide (real, non-attack) faces. In total, there are 70 identities (data subjects). Each video is 10 seconds long, where for the first 5 seconds the data subject was required to stay still and look at the camera, then for the last 5 seconds the subject was asked to turn their head from one side to the other (such that profile views could be captured). The videos were acquired indoors, under normal office lighting conditions. The data subjects were volunteers, who were required to be present during two recording sessions, which on average were separated by about three weeks. In each recording session, the volunteers were asked to record a video of their own face using the front (i.e., selfie) camera of each of the five smartphones mentioned earlier. The face data was additionally captured while the data subjects wore plain (not personalised) hygienic masks, to simulate the scenario where face recognition might need to be performed on a masked face (e.g., during a pandemic like COVID-19).</li> <li> <p><strong>A</strong><strong>ttacks:</strong></p> <ul> <li> <p><em>Personalised </em><em>hygienic mask attack</em><em>s</em><em>:</em> Video recordings of an impostor wearing personalised hygienic masks (one at a time), on which the bottom part of each data subject’s face is printed. Please note that the dataset contains 350 personalised hygienic mask attack videos, whereas the IJCB2023 paper mentioned 345 videos. This is because, for the experiments reported in the paper, we excluded the videos of the attacker wearing their own hygienic mask (since the "attacker" was one of the 70 data subjects).</p> </li> <li> <p><em>P</em><em>rint attacks:</em> 1400 video recordings of the data subjects’ face photos printed on A4 matte paper, which was held up to the smartphone’s camera.</p> </li> <li> <p><em>R</em><em>eplay attacks:</em> 2800 video recordings of bona-fide face videos that were replayed to the target smartphone’s camera. Different phones were paired, such that one of the pair was used to replay the bona-fide videos while the second (attacked) phone recorded the videos using its front camera.</p> </li> </ul> </li> </ul> <p> </p> <p><strong>Reference</strong></p> <p>If you use the data for your research or publication, please cite the following paper :</p> <p><a href="https://publications.idiap.ch/authors/show/1883">Komaty, Alain</a>, <a href="https://publications.idiap.ch/authors/show/1934">Krivokuca Hahn, Vedrana</a>, <a href="https://publications.idiap.ch/authors/show/3114">Ecabert, Christophe</a> and <a href="https://publications.idiap.ch/authors/show/65">Marcel, Sébastien</a>, <a href="https://publications.idiap.ch/publications/show/5093">Can personalised hygienic masks be used to attack face recognition systems?</a>, in: Proceedings of IEEE International Joint Conference on Biometrics (IJCB2023), 2023</p>
In situ synthesis of peptide microarrays - shadow mask design [2]
GEO Series GSE50044. synthetic construct; Mus musculus. 8 samples. Type: Protein profiling by protein array.
In situ synthesis of peptide microarrays - shadow mask design
GEO Series GSE50045. synthetic construct; Mus musculus. 113 samples. Type: Protein profiling by protein array.
eXtended Custom Silicone Mask Attack Dataset (XCSMAD)
<p><strong>Description</strong></p> <p>The eXtended Custom Silicone Mask Attack Dataset (XCSMAD) consists of 535 short video recordings of both bona fide and presentation attacks (PA) from 72 subjects. The attacks have been created from custom silicone masks. Videos have been recorded in RGB (visual spectra), near infrared (NIR), and thermal (LWIR) channels.</p> <p>A complete preprocessed data for the aforementioned videos and bona fide images (as a part of experiments related to vulnerability assessment) have been provided to facilitate reproducing experiments from the reference publication, as well as to conduct new experiments. The details of preprocessing can be found in the reference publication.</p> <p>The implementation of all experiments described in the reference publication is available at <a href="https://gitlab.idiap.ch/bob/bob.paper.xcsmad_facepad">https://gitlab.idiap.ch/bob/bob.paper.xcsmad_facepad</a></p> <p> </p> <p><strong>Experimental protocols</strong></p> <p>The reference publication considers two experimental protocols: grandtest and cross-validation (cv). For a frame-level evaluation, 50 frames from each video have been used in both protocols. For the grandtest protocol, videos were divided into train, dev, and eval groups. Each group consists of unique subset of clients. (The videos corresponding to any specific subjects in one group are a part of single group).</p> <p>For cross-validation (cv) experiments, a 5-fold protocol has been devised. Videos from XCSMAD have been split into 5 folds with non-overlapping clients. Using these five partitions, 5 testprotocols (cv0, · · · , cv4) have been created such that in each protocol, four of the partitions are used for training, and the remaining one is used for evaluation.</p> <p> </p> <p><strong>Reference</strong></p> <p>If you use this dataset, please cite the following publication:</p> <pre>@article{Kotwal_TBIOM_2019, author = {Kotwal, Ketan and Bhattacharjee, Sushil and Marcel, S\'{e}bastien}, title = {<a href="https://publications.idiap.ch/index.php/publications/show/4145">Multispectral Deep Embeddings As a Countermeasure To Custom Silicone Mask Presentation Attacks</a>}, journal = {IEEE Transactions on Biometrics, Behavior, and Identity Science}, publisher = {{IEEE}}, year = {2019}, } </pre>
LST CDR Cloud Mask Stability Dataset
<p>These data are the Bayesian and operational cloud masks for matches to cloudy-sky in-situ ceilometer data, used to assess the cloud masking stability for a LST CDR. They cover overlap periods between the ATSR-2 and AATSR, AATSR and MODIS Terra, and MODIS Terra and SLSTR-A sensors.</p>
The Berlin Dataset of Lombard and Masked Speech (BELMASK)
<p>The Berlin Dataset of Lombard and Masked Speech (BELMASK) is a phonetically controlled audiovisual dataset of speech produced in adverse speaking conditions. The dataset contains in total 128 min of audio and video recordings of 10 German native speakers (4 female, 6 male) with a mean age of 30.2 years (SD: 6.3 years), uttering matrix sentences in cued, uninstructed speech in four conditions: (i) with a Filtering Facepiece P2 (FFP2), (ii) without an FFP2 mask in silence, (iii) with an FFP2 mask while exposed to noise, iv) without an FFP2 mask while exposed to noise. Noise consisted of mixed-gender six-talker babble played over headphones to the speakers, triggering the Lombard effect. All conditions are readily available in face-and-voice and voice-only formats. The speech material is annotated, employing a multi-layer architecture, and was originally conceptualized to be used for the administration of a working memory task. The dataset is available for academic research in the area of speech communication, acoustics, psychology and related disciplines upon request, <strong>after signing an End User License Agreement (EULA)</strong>.</p>
Face Mask Detection Dataset
<p>The dataset contains real images of people with face mask and without face mask. Each class contains 150 images.</p> <p>Cite us:</p> <p>Ferdib-Al-Islam, Suprio Sarkar, Nusrat Jahan and Farjana Yeasmin Rupa, “Face Mask Detection Dataset”. Zenodo, Jul. 15, 2021. doi: 10.5281/zenodo.5305989</p>
Masks for hands in X-Ray images
<p>Semantic segmentation masks for hands on scanned X-Rays from the RSNA Bone Age dataset.</p> <p>Mask were obtained manually using thresholding and edge detection and all masks were quality checked.</p> <p>Based on this two models (Tensormask and Efficient-UNet) were trained to obtain the masks on the full RSNA Bone Age dataset.</p> <p> </p>
Shadow mask assisted 193 nm Excimer laser processing of commercial Cyclo-Olefin-Copolymer (COC) substrates for low-cost micro-fluidic biosensing devices.
<p>An Abstract submitted to The 24th International Symposium on Laser Precision Microfabrication (LPM2023)</p>
Chronic cigarette smoke exposure masks pathological features of Helicobacter pylori infection while promoting tumor initiation
GEO Series GSE274834. Mus musculus. 6 samples. Type: Expression profiling by high throughput sequencing.
CALIPSO Lidar L2 Vertical Feature Mask Data V3-01
Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observations (CALIPSO) was launched on April 28, 2006 to study the impact of clouds and aerosols on the Earth’s radiation budget and climate. It flies in formation with five other satellites in the international “A-Train” (PDF) constellation for coincident Earth observations. The CALIPSO satellite comprises three instruments, the Cloud-Aerosol LIdar with Orthogonal Polarization (CALIOP), the Imaging Infrared Radiometer (IIR), and the Wide Field Camera (WFC). CALIPSO is a joint satellite mission between NASA and the French Agency, CNES. These data consist 5 km aerosol layer data.
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.