DKDmitriy Kirsh

Dmitriy Kirsh

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Dmitriy Kirsh has a total of 29 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Hybrid Binarization Method for Historical Handwritten Documents

    by D. G. Asatryan, M. E. Haroutunian, G. S. Sazhumyan, A. V. Kupriyanov, R. A. Paringer, D. V. Kirsh

    Binarization of historical documents is a rather complex task that is being intensively studied by researchers all over the world. A large number of approaches, procedures, and binarization algorithms have been proposed, but methods that work equally well in all cases have not yet been proposed. The literature offers various criteria for assessing the quality of the binarization result. In the case of binarization of ancient handwritten texts, the criterion for the quality of the binarization algorithm is the degree of readability of the text using a visual method or technical means. One of the approaches proposed in the literature to improve the quality of the binarization result is pre-processing the original image using filtering methods, morphological analysis, spectral analysis, etc. This article proposes a hybrid binarization method, consisting of an arbitrary global or adaptive binarization algorithm and a special segmentation procedure for selecting segments of certain sizes. The proposed procedure makes it possible to identify objects of certain sizes in an image, in particular artifacts that exist in a binarized image. This work experimentally explores the possibility of improving the quality of a binary image by applying the proposed procedure.


  • Application of artificial intelligence in ophthalmology for solving the problem of semantic segmentation of fundus images

    by N.S. Demin, Ipsi Ras – Branch Of The Fsrc “Crystallography And Photonics” Ras, N.Y. Ilyasova, R.A. Paringer, D.V. Kirsh, Samara National Research University


  • Open Access

    Dissimilarity-based algorithms for fabric defects detection

    by David Asatryan, Mariam Haroutunian, Vardan Kurkchiyan, Armen Melkumyan, Alexander Kupriyanov, Rustam Paringer, Dmitriy Kirsh

    The paper investigates images of textures with a defect, characterized by a sufficiently prominent structure. A procedure for detecting a defect in a textured image using an intellectual procedure for assessing the similarity of different parts of the tested image scanned with a sliding window is proposed. It is assumed that an area of the image that contains a defect in whole or in part will be the least similar to the other areas considered. To assess the similarity of images in the paper, the previously proposed measures are used, built on the basis of the values of the components and the magnitude of the gradient, considered as a sample from a random variable with the Weibull distribution. The effectiveness of the proposed methods is demonstrated by experimental investigation.

  • Automatic Dominant Orientation Estimation in Texture Images Using the Scattering Ellipse of the Gradients

    by D. Asatryan, M. Haroutunian, A. Kupriyanov, G. Hakobyan, R. Paringer, D. Kirsh

    In this paper, the problem of estimating the dominant image orientation (DIO) is experimentally investigated using the characteristics of the scattering el

  • Decision-making support system for the personalization of retinal laser treatment in diabetic retinopathy

    by Samara National Research University, N.Y. Ilyasova, D.V. Kirsh, N.S. Demin, Ipsi Ras - Branch Of The Fsrc “Crystallography And Photonics” Ras

    In this work, we propose a decision-making support system for automatically mapping an effective photocoagulation pattern for the laser treatment of diabetic retinopathy. The purpose of research to create automated personalization of diabetic macular edema laser treatment. The results are based on analysis of large semi-structured data, methods and algorithms for fundus image processing. The technology improves the quality of retina laser coagulation in the treatment of diabetic macular edema, which is one of the main reasons for pronounced vision decrease. The proposed technology includes original solutions to establish an optimal localization of multitude burns by determining zones exposed to laser. It also includes the recognition of large amount of unstructured data on the anatomical and pathological locations' structures in the area of edema and data optical coherent tomography. As a result, a uniform laser application on the pigment epithelium of the affected retina is ensured. It will increase the treatment safety and its effectiveness, thus avoiding the use of more expensive treatment methods. Assessment of retinal lesions volume and quality will allow predicting the laser photocoagulation results and will contribute to the improvement of laser surgeon's skills. The architecture of a software complex comprises a number of modules, including image processing methods, algorithms for photocoagulation pattern mapping, and intelligent analysis methods.


  • Open Access

    Identification of Prognostic Factors and Predicting the Therapeutic Effect of Laser Photocoagulation for DME Treatment

    by Nataly Ilyasova, Aleksandr Shirokanev, Dmitriy Kirsh, Nikita Demin, Evgeniy Zamytskiy, Rustam Paringer, Alexey Antonov

    Diabetic retinopathy is among the most severe complications of diabetes, most often leading to rapid and irreversible vision loss. The laser coagulation procedure, which consists of applying microburns to the fundus, has proven to be an effective method for treating diabetic retinopathy. Unfortunately, modern research does not pay enough attention to the study of the arrangement of microburns in the edema area—One of the key factors affecting the quality of therapy. The aim of this study was to propose a computational decision-making support system for retina laser photocoagulation based on the analysis of photocoagulation plans. Firstly, we investigated a set of prognostic factors based on 29 features describing the geometric arrangement of coagulates. Secondly, we designed a technology for the intelligent analysis of the photocoagulation plan that allows the effectiveness of the treatment to be predicted. The studies were carried out using a large database of fundus images from 108 patients collected in clinical trials. The results demonstrated a high classification accuracy at a level of over 85% using the proposed prognostic factors. Moreover, the designed technology proved the superiority of the proposed algorithms for the automatic arrangement of coagulates, predicting a 99% chance of a positive therapeutic effect.


  • Open Access

    Modeling of Fundus Laser Exposure for Estimating Safe Laser Coagulation Parameters in the Treatment of Diabetic Retinopathy

    by Aleksandr Shirokanev, Nataly Ilyasova, Nikita Andriyanov, Evgeniy Zamytskiy, Andrey Zolotarev, Dmitriy Kirsh

    A personalized medical approach can make diabetic retinopathy treatment more effective. To select effective methods of treatment, deep analysis and diagnostic data of a patient’s fundus are required. For this purpose, flat optical coherence tomography images are used to restore the three-dimensional structure of the fundus. Heat propagation through this structure is simulated via numerical methods. The article proposes algorithms for smooth segmentation of the retina for 3D model reconstruction and mathematical modeling of laser exposure while considering various parameters. The experiment was based on a two-fold improvement in the number of intervals and the calculation of the root mean square deviation between the modeled temperature values and the corresponding coordinates shown for the convergence of the integro-interpolation method (balance method). By doubling the number of intervals for a specific spatial or temporal coordinate, a decrease in the root mean square deviation takes place between the simulated temperature values by a factor of 1.7–5.9. This modeling allows us to estimate the basic parameters required for the actual practice of diabetic retinopathy treatment while optimizing for efficiency and safety. Mathematical modeling is used to estimate retina heating caused by the spread of heat from the vascular layer, where the temperature rose to 45 °C in 0.2 ms. It was identified that the formation of two coagulates is possible when they are located at least 180 μm from each other. Moreover, the distance can be reduced to 160 μm with a 15 ms delay between imaging.


  • Open Access

    The study of effectiveness of a high-performance crystal lattice parametric identification algorithm based on CUDA technology

    by A S Shirokanev, D V Kirsh, A V Kupriyanov

    The study of substances with a crystal structure is a complex multi-step process. The key step in the crystalline substance analysis is the unit cell parameter estimation. The estimation of the crystal lattice unit cell parameters is a particular problem that involves the search of the crystal lattice model’s parameters according to the information which can be extracted from the substance. In these recent times, the most accurate information about the substance structure can be obtained with the electron microscope whose linear resolution is high enough to observe the atomic structure of a substance. The problem of parameter estimation in this case means the reconstruction of the three-dimensional crystal lattice with 2-dimentional images received by an electron microscope, and the estimation of the crystal lattice unit cell parameters by reconstructed lattice. In the previous papers the crystal lattice parametric identification algorithms based on solving the local optimization problem were presented. However, the analysis of a large crystal lattice database requires a lot of computations. In this paper, a high-performance crystal lattices parametric identification algorithm using the CUDA technology is proposed. The investigation of the algorithm effectiveness is carried out on the GPU GeForce NVidia GTX 1070 Ti. With data dimension more than 32 translations the acceleration is higher than 70. The algorithm runs more efficiently at the use of a large number of CUDA-blocks.

  • Algorithm of reconstruction of a three-dimensional crystal structure from two-dimensional projections

    by Ipsi Ras – Branch Of The Fsrc “Crystallography And Photonics” Ras, D.V. Kirsh, Samara National Research University, A.S. Shirokanev, A.V. Kupriyanov

    The article deals with a problem of three-dimensional crystal lattice reconstruction, which is an important stage in the X-ray structural analysis. The accuracy of parametric and structural identification of crystals directly depends on the quality of crystal lattice reconstruction. The proposed algorithm of reconstruction of a three-dimensional crystal lattice is based on minimizing the distances from each node to a line projected onto a specified plane. Three sets of two-dimensional node coordinates, obtained from three two-dimensional projections, are used as input data. We performed an analytical calculation of the reconstruction error, allowing the total reconstruction accuracy to be estimated. The results of computational experiments confirmed the high quality of the proposed reconstruction algorithms and its stability against the distortion of node coordinates. In addition, we revealed a problem of lattice system separability, with the identification accuracy for monoclinic, rhombic and tetragonal systems found to be 34%, 53% and 10%, respectively.


  • Open Access

    Clustering of media content from social networks using bigdata technology

    by Samara National Research University, I. Rycarev, D. Kirsh, Ipsi Ras – Branch Of The Fsrc “Crystallography And Photonics” Ras, A. Kupriyanov

    The article deals with one of the key problems of the social network analysis – the problem of classifying accounts based on media content uploaded by users. The main difficulties are the content heterogeneity (both in format and subject) and the large volumes of data, which leads to excessive computational complexity of its processing and often to the complete inefficiency of traditional analysis methods. In the article, we discuss an approach to the clustering of media content from social networks based on textual annotation using BigData technology – a modern and efficient tool that allows to solve the problem of large data volume processing. To carry out computational experiments, a large sample of heterogeneous images (photographs, paintings, postcards, etc.) was collected from real Twitter accounts. The results confirmed the high quality of media content clustering, the average error was around 5 %.