Персона:
Сафонов, Илья Владимирович

Организационные подразделения

Организационная единица

Институт общей профессиональной подготовки (ИОПП)

Миссией Института является: фундаментальная базовая подготовка студентов, необходимая для получения качественного образования на уровне требований международных стандартов; удовлетворение потребностей обучающихся в интеллектуальном, культурном, нравственном развитии и приобретении ими профессиональных знаний; формирование у студентов мотивации и умения учиться; профессиональная ориентация школьников и студентов в избранной области знаний, формирование способностей и навыков профессионального самоопределения и профессионального саморазвития. Основными целями и задачами Института являются: обеспечение высококачественной (фундаментальной) базовой подготовки студентов бакалавриата и специалитета; поддержка и развитие у студентов стремления к осознанному продолжению обучения в институтах (САЕ и др.) и на факультетах Университета; обеспечение преемственности образовательных программ общего среднего и высшего образования; обеспечение высокого качества довузовской подготовки учащихся Предуниверситария и школ-партнеров НИЯУ МИФИ за счет интеграции основного и дополнительного образования; учебно-методическое руководство общеобразовательными кафедрами Института, осуществляющими подготовку бакалавров и специалистов по социо-гуманитарным, общепрофессиональным и естественнонаучным дисциплинам, обеспечение единства требований к базовой подготовке студентов в рамках крупных научно-образовательных направлений (областей знаний).

Фамилия

Сафонов

Имя

Илья Владимирович

Полная страница элемента

Результаты поиска

Теперь показываю 1 - 10 из 13

Только метаданные
Inpainting of Ring Artifacts on Microtomographic Images by 3D CNN
(2020) Yakimchuk, I.; Kornilov, A.; Safonov, I.; Корнилов, Антон Сергеевич; Сафонов, Илья Владимирович
© 2020 FRUCT.Ring artifacts are inevitable in microtomographic images. In a Digital Rock workflow, such defects might affect the subsequent segmentation and flow simulation. We propose a correction of ring artifacts in reconstructed microtomographic images by inpainting. Our blind inpainting method uses a 3D convolutional network U-net. For the creation of training and validation datasets, we suggest an algorithm for transferring real ring artifacts to an arbitrary place in the undistorted slices of 8 big images of sandstones and sand. The parameters of the deep neural network and loss functions are analyzed. A loss function based on the multi-scale structural similarity index (MS-SSIM) allows to achieve the best performance. The developed solution corrects ring artifacts perfectly from a point of view of visual assessment and outperforms existing inpainting methods according to quality metrics based on MS-SSIM and mean absolute error (MAE).
Только метаданные
An Animated Graphical Abstract for an Image
(2021) Reimers, I. A.; Safonov, I. V.; Kornilov, A. S.; Сафонов, Илья Владимирович; Корнилов, Антон Сергеевич
© 2021, Springer Nature Switzerland AG.The conventional approach used in modern user interfaces for browsing of a big collection of images by viewing their downsampled versions often does not allow to recognise the content and to assess the quality of the images. To cope with this problem, we propose a method for the creation of an animated graphical abstract. Our approach comprises detection of attention zones, selection of the region for visual quality estimation, and generation of animation that simulates the camera tracking-in, tracking-out, and panning between detected zones and the whole scene. The short looped animation shows the whole image, main objects of the scene one by one, as well as an enlarged fragment for estimation quality of the image. We demonstrate our concept for consumer photographs, scanned images of documents, and slices of tomographic images. The attention zones vary by the type of image. Face detection and salient regions are used for photos. The title, subheaders, and pictures are attention zones for document images. The attention zones in slices of tomographic images in the investigation of rock samples are enlarged regions of a material having different characteristics according to visual similarity. We conducted five user studies to prove the effectiveness of the proposed animated graphical abstract in comparison with conventional thumbnails and icons.
Только метаданные
Blind quality assessment for slice of microtomographic image
(2019) Yakimchuk, I.; Kornilov, A.; Safonov, I.; Корнилов, Антон Сергеевич; Сафонов, Илья Владимирович
© 2019 FRUCT.The paper considers a new algorithm for blind quality assessment of a slice of X-ray microtomographic image. We selected the following factors impacting on micro-CT image quality with respect to Digital Rock technology: Smoothness, sharpness, contrast, absence of high-density regions and ring artifacts. We propose algorithms for estimation of partial quality measures for named factors inside Region-of-Interest, that is in area associated with a sample of rock or granular material. Total quality metrics is calculated as a product of these partial measures. Our method for quality assessment provides reasonable outcomes for synthetic and real slices of micro-CT images. We collected experts' judgments about quality of slices. Proposed solution has a high correlation with scores of experts and outperforms existing blind quality metrics. An application of developed method to all slices allows to obtain quality estimation for 3D micro-CT image.
Только метаданные
The regression model for the procedure of correction of photos damaged by backlighting
(2019) Goncharova, A. V.; Safonov, I. V.; Romanov, I. A.; Сафонов, Илья Владимирович
© 2019 CEUR-WS. All rights reserved.In the paper, we propose an approach for selection a correction parameter for images damaged by backlighting. We consider the photos containing underexposed areas due to backlit conditions. Such areas are dark and have poorly discernible details. The correction parameter controls the level of amplification of local contrast in shadow tones. Besides, the correction parameter can be considered as a quality estimation factor for such photos. For an automatic selection of the correction parameter, we apply regression by supervised machine learning. We propose new features calculated from the co-occurrence matrix for the training of the regression model. We compare the performance of the following techniques: the least square method, support vector machine, random forest, CART, random forest, two shallow neural networks as well as blending and staking of several models. We apply two-stage approach for the collection of a big dataset for training: initial model is trained on a manually labeled dataset containing about two hundred of photos, after that we use the initial model for searching for photos damaged by backlit in social networks having public API. Such approach allowed to collect about 1000 photos in conjunction with their preliminary quality assessments that were corrected by experts if it was necessary. In addition, we investigate an application of several well-known blind quality metrics for the estimation of photos affected by backlit.
Открытый доступ
From Iris Image to Embedded Code: System of Methods
(2023) Matveev, I.; Safonov, I.; Сафонов, Илья Владимирович
Passwords are ubiquitous in todayвЂ™s world, as are forgetting and stealing them. Biometric signs are harder to steal and impossible to forget. This paper presents a complete system of methods that takes a secret key and the iris image of the owner as input and generates a public key, suitable for storing insecurely. It is impossible to obtain source data (i.e., secret key or biometric traits) from the public key without the iris image of the owner, the irises of other persons will not help. At the same time, when the iris image of the same person is presented the secret key is restored. The system has been tested on several iris image databases from public sources. It allows storing 65 bits of the secret key, with zero possibility to unlock it with the impostorвЂ™s iris and 10.4% probability to reject the owner in one attempt.
Открытый доступ
An Approach for Matrix Multiplication of 32-Bit Fixed Point Numbers by Means of 16-Bit SIMD Instructions on DSP
(2023) Safonov, I.; Kornilov, A.; Makienko, D.; Сафонов, Илья Владимирович; Корнилов, Антон Сергеевич; Макиенко, Дарья Олеговна
Открытый доступ
Analysis of Open Well Datasets
(НИЯУ МИФИ, 2024) Makienko, D. O.; Safonov, I. V.; Сафонов, Илья Владимирович
Recently, the number of studies devoted to the use of machine learning methods in geophysics has been increasing significantly. Examples of such investigations include the prediction of rock properties and separation of rock types according to quantitative characteristics. Annotated datasets are required to build and evaluate the quality of machine learning based models. This paper analyzes open labeled well datasets and related research. We consider data containing well logs, rock images, laboratory results, labeled zonation by lithotypes. Methods for visualizing well data are presented. We provide recommendations for oil and gas companies on the preferable format for making well data publicly available
Только метаданные
Deep neural networks for ring artifacts segmentation and corrections in fragments of CT images
(2021) Reimers, I.; Yakimchuk, I.; Kornilov, A.; Safonov, I.; Корнилов, Антон Сергеевич; Сафонов, Илья Владимирович
© 2021 IEEE Computer Society. All rights reserved.Ring artifacts are typical defects of computed tomography (CT) that degrade the quality of a 3D reconstructed image. Existing techniques for a ring reduction have various shortcomings and limitations, in particular, a lot of them are unable to process arbitrary fragments of the image and blur artifact-free regions. We propose an algorithm for ring artifacts segmentation and reduction by deep convolutional neural networks that correct 3D fragments of the CT image by inpainting. We compare 2D and 3D architectures of networks. For the creation of a dataset with a big number of ring artifacts, we propose a procedure that is able to transfer an artifact from one image to an arbitrary place of another image. The appearance of the transferred artifact changes. For ring artifact segmentation and correction in images of sandstones and sand, the proposed networks demonstrate good visual results and outperform existing methods. The proposed technique concentrates on the Digital Rock workflow, but the networks can be adjusted for the processing of other CT images as well.
Только метаданные
Analysis of Open Well Datasets
(2024) Makienko, D. O.; Safonov, I. V.; Сафонов, Илья Владимирович
Только метаданные
Rendering semisynthetic FIB-SEM images of rock samples
(2021) Reimers, I.; Safonov, I.; Kornilov, A.; Сафонов, Илья Владимирович; Корнилов, Антон Сергеевич
© 2021 Copyright for this paper by its authors.Digital rock analysis is a prospective approach to estimate properties of oil and gas reservoirs. This concept implies constructing a 3D digital twin of a rock sample. Focused Ion Beam - Scanning Electron Microscope (FIB-SEM) allows to obtain a 3D image of a sample at nanoscale. One of the main specific features of FIB-SEM images in case of porous media is pore-back (or shine-through) effect. Since pores are transparent, their back side is visible in the current slice, whereas, in fact, it locates in the following ones. A precise segmentation of pores is a challenging problem. Absence of annotated ground truth complicates fine-tuning the algorithms for processing of FIB-SEM data and prevents successful application of machine-learning-based methods, which require a huge training set. Recently, several synthetic FIB-SEM images based on stochastic structures were created. However, those images strongly differ from images of real samples. We propose fast approaches to render semisynthetic FIB-SEM images, which imply that intensities of voxels of mineral matrix in a milling plane, as well as geometry of pore space, are borrowed from an image of rock sample saturated by epoxy. Intensities of voxels in pores depend on the distance from milling plane to the given voxel along a ray directed at an angle equal to the angle between FIB and SEM columns. The proposed method allows to create very realistic FIB-SEM images of rock samples with precise ground truth. Also, it opens the door for numerical estimation of plenty of algorithms for processing FIB-SEM data.