Identity documents recognition is an important sub-field of document analysis, which deals with tasks of robust document detection, type identification, text fields recognition, as well as identity fraud prevention and document authenticity validation given photos, scans, or video frames of an identity document capture. Significant amount of research has been published on this topic in recent years, however a chief difficulty for such research is scarcity of datasets, due to the subject matter being protected by security requirements. A few datasets of identity documents which are available lack diversity of document types, capturing conditions, or variability of document field values. In this paper, we present a dataset MIDV-2020 which consists of 1000 video clips, 2000 scanned images, and 1000 photos of 1000 unique mock identity documents, each with unique text field values and unique artificially generated faces, with rich annotation. The dataset contains 72409 annotated images in total, making it the largest publicly available identity document dataset to the date of publication. We describe the structure of the dataset, its content and annotations, and present baseline experimental results to serve as a basis for future research. For the task of document location and identification content-independent, feature-based, and semantic segmentation-based methods were evaluated. For the task of document text field recognition, the Tesseract system was evaluated on field and character levels with grouping by field alphabets and document types. For the task of face detection, the performance of Multi Task Cascaded Convolutional Neural Networks-based method was evaluated separately for different types of image input modes. The baseline evaluations show that the existing methods of identity document analysis have a lot of room for improvement given modern challenges. We believe that the proposed dataset will prove invaluable for advancement of the field of document analysis and recognition.
The effects of anomalous weather conditions (such as extreme temperatures and precipitation) on CO2 flux variability in different tropical ecosystems were assessed using available reanalysis data, as well as information about daily net CO2 fluxes from the global FLUXNET database. A working hypothesis of the study suggests that the response of tropical vegetation can differ depending on local geographical conditions and intensity of temperature and precipitation anomalies. The results highlighted the large diversity of CO2 flux responses to the fluctuations of temperature and precipitation in tropical ecosystems that may differ significantly from some previously documented relationships (e.g., higher CO2 emission under the drier and hotter weather, higher CO2 uptake under colder and wetter weather conditions). They showed that heavy precipitation mainly leads to the strong intensification of mean daily CO2 release into the atmosphere at almost all stations and in all types of study biomes. For the majority of considered tropical ecosystems, the intensification of daily CO2 emission during cold and wet weather was found, whereas the ecosystems were predominantly served as CO2 sinks from the atmosphere under hot/dry conditions. Such disparate responses suggested that positive and negative temperature and precipitation anomalies influence Gross Primary Production (GPP) and Ecosystem Respiration (ER) rates differently that may result in various responses of Net Ecosystem Exchanges (NEE) of CO2 to external impacts. Their responses may also depend on various local biotic and abiotic factors, including plant canopy age and structure, plant biodiversity and plasticity, soil organic carbon and water availability, surface topography, solar radiation fluctuation, etc.
The theory of global illumination and computer programs based on it allows calculating the light field accurately in an arbitrary three-dimensional lighting scene. However, the output of the visualization of the light field spatial-angular distribution to the display screen in the form of an image is inevitably associated with scaling the luminance and color of the image pixels to the computer display dynamic range. To date, a color appearance model was created in colorimetry. This model allows recalculating the image pixels' color for viewing conditions other than the original ones preserving the image's visual perception. This model is approved by the CIE (International Commission on Illumination) as a standard model under the name CIECAM02. In this paper, the CIECAM02 algorithm model is implemented, and a study of designing a lighting system for lighting a theater stage to create an atmosphere of sunset is carried out. Modeling the lighting system is performed in the DIALux evo program, which is the de facto standard of design in lighting engineering. The correspondence of the visualization of the stage lighting to the feeling of sunset is analyzed based on expert assessments. The research allows us to recommend the inclusion of the CIECAM02 model in the algorithms for visualizing the image of three-dimensional lighting scenes.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.