AKAndrey V. Kamenskiy

Andrey V. Kamenskiy

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

Andrey V. Kamenskiy has a total of 18 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Application of the YOLOv5 Neural Network for Pattern Recognition on Radiographic Images of the Human Wrist Joint

    by Alena S. Krasnoperova, Andrey V. Kamenskiy

    The possibility of using artificial intelligence in the task of recognizing objects of interest in medical radiographic images has been studied. To implement computer vision, the YOLOv5 neural network and the use of its functionality for pattern recognition on radiographic images of the human wrist joint were considered. YOLOv5 is one of the most popular neural network models due to a number of advantages and features: high learning speed, object detection accuracy, efficient use of hardware and support for various architectures. The use of an artificial neural network in medicine is a promising direction that allows one to obtain data on pathologies and anomalies on radiographs, improving the diagnostic process and providing quick results with a high percentage of reliability. To adapt the model for the task of recognizing objects of the wrist joint in radiographic images, a data set was labeled, including images for retraining the neural network model and test images. Learning key numerical properties is key to building and tuning effective neural network models. The correctness of their selection and debugging have a direct impact on achieving the desired results when retraining and using neural networks. According to the results of the neural network, all classes of objects were correctly identified in more than 70% of the images; this indicator is a worthy result of the work, which confirms the relevance of using a computer vision tool in medical diagnostics and practical application in clinical practice.

  • Open Access

    Digital three-stage recursive-separable image processing filter with variable sizes of scanning multielement aperture

    by A. V. Kamenskiy, T. M. Akaeva, D. A. Grebenshchikova

    Objectives. The main aim of digital image processing is to increase clarity while maintaining image quality and eliminate noise. However, the amount of information contained in digital image files is growing year after year. This circumstance negatively affects processing time, critical for systems with high load requirements on the computing platform. In this regard, the use of digital filters which enable a reduction to the processing time of incoming data is important. In order to resolve this issue, adaptive filters with different sizes of multielement processing aperture are being developed to improve image clarity and preserve image details. Filters with adaptive properties are able to change their parameters during data processing, and provide maximum performance as the aperture size increases. The aim of the work is to develop a type of recursively separable digital filter with variable sizes of a scanning multielement aperture which allows the number of computational operations to be reduced while maintaining the efficiency of filtering input data (images).Methods. The work used recursive-separable methods and algorithms to construct digital filters.Results. An algorithm for the recursive-separable implementation of a digital filter is described, and the final view of the processing aperture and its three-dimensional appearance are presented. In order to evaluate the performance of the filter, a comparison of the developed algorithm with the classical two-dimensional convolution algorithm was carried out. The experiment was performed using images of various sizes and consisted of determining the time spent on the process of processing the test image. The study established that the processing time of a test image using the developed filter is on average 5 times less than the time taken by the classical two-dimensional convolution algorithm. The optimal coefficients for magnifying the central element and raising the positive part of the aperture of a digital filter were determined, enabling the efficiency of its use to be enabled.Conclusions. The studies show the effectiveness of using the developed recursive-separable two-dimensional filter to improve image clarity and reduce the time spent on processing.


  • Influence of Unequilateral Apertures of the "Trunced Pyramid" and "Double Pyramid" Laplacian Digital Filters on the Accuracy of Television Measuring Systems

    by K. A. Rylov, K. S. Kupriyanova, A. V. Kamensky

    In the modern world, digital image processing requires increasing the speed of the processing methods and algorithms used. One way to improve performance is to transform spatial filters into filters with a recursively separable form of implementation. The recursion property implies the use of previous output values of a function to form the current sample. The property of separability is understood as division into processing by column and row of a matrix of digital image values. The transformation of spatial filters consists of changing the aperture of the masks into a non-orthogonal (non-equilateral) form, which reduces the number of computational operations and speeds up the processing process, while maintaining its efficiency. The paper presents a description of the non-equilateral apertures of the previously developed “truncated pyramid” and “double pyramid”Laplacian digital filters. For non-equilateral apertures, results were obtained for the first time on their use for television measuring systems. From which it can be seen that a “truncated pyramid” Laplacian filter with non-equilateral processing apertures is recommended for use in TIS, since it increases the efficiency of measuring the range to objects of interest while reducing processing time. Based on the results of processing with modified filters, sets of processed images were obtained for each of the 10 original images. For each set of processed images, measurements of the peak signal-to-noise ratio, standard deviation and selection of the optimal central coefficient of the filter mask were carried out, for subsequent assessment of the effectiveness of processing with modified filters. The assessment of the influence of recursively separable “truncated pyramid” and “double pyramid” Laplacian filters with non-equilateral aperture masks on the accuracy of television measurement systems consisted of considering their influence on measuring the distance (from the camera) to the object of interest in the image, when – control of processing time. Based on the evaluation results, we can conclude that by using pre-processing of images with modified digital filters, the accuracy of measuring the distance from the camera to the measurement object is improved, while reducing processing time.

  • Increasing the Efficiency of Constructing 3D Models of Objects by Using a High-Speed Digital Filter

    by Darya A. Grebenshchikova, Andrey V. Kamenskiy

    The work is devoted to increasing the efficiency of constructing 3-dimensional models of objects, using human organs as an example, through the use of preprocessing of the initial data with a high-speed digital filter. The high-speed recursive-separable digital Laplacian filter “truncated pyramid”, previously developed by the authors, was taken as a filter. This filter, through the use of the properties of recursion and separability, reduces the amount of computational costs required for the processing process, however, there is a factor that slows down its operation, its sequential operating algorithm. In the work, the authors modified the structure of the algorithm from sequential to parallel, displaying the basic principles of operation of the parallel architecture of the recursive-separable Laplacian filter “truncated pyramid” for processing images used to build 3- dimensional models of objects. After conducting experimental studies, including testing the architecture on source images and comparing performance with an existing sequential algorithm, results were obtained that confirmed the effectiveness and applicability of the developed architecture to reduce computational costs. Test objects were constructed without processing and with processing with a modified filter, from which visually and due to the increase in the number of points used to form a dense point cloud, it is clear that the generated 3-dimensional models have increased their quality.

  • Influence of Unequilateral Apertures of Digital Filters Laplacian “Trunced Pyramid” and “Double Pyramid” on the Accuracy of Television Measuring Systems

    by K. A. Rylov, K. S. Kupriyanova, A. V. Kamensky

    In the modern world, digital image processing requires increasing the speed of the processing methods and algorithms used. One way to improve performance is to transform spatial filters into filters with a recursively separable form of implementation. The recursion property implies the use of previous output values of a function to form the current sample. The property of separability is understood as division into processing by column and row of a matrix of digital image values. The transformation of spatial filters consists of changing the aperture of the masks into a non-orthogonal (non-equilateral) form, which reduces the number of computational operations and speeds up the processing process, while maintaining its efficiency. The paper presents a description of the non-equilateral apertures of the previously developed Laplacian digital filters “truncated pyramid” and “double pyramid.” For non-equilateral apertures, results were obtained for the first time on their use for television measuring systems. From which it can be seen that a “truncated pyramid” Laplacian filter with non-equilateral processing apertures is recommended for use in TIS, since it increases the efficiency of measuring the range to objects of interest while reducing processing time. Based on the results of processing with modified filters, sets of processed images were obtained for each of the 10 original images. For each set of processed images, measurements of the peak signal-to-noise ratio, standard deviation and selection of the optimal central coefficient of the filter mask were carried out, for subsequent assessment of the effectiveness of processing with modified filters. The assessment of the influence of recursively separable Laplacian filters “truncated pyramid” and “double pyramid” with non-equilateral aperture masks on the accuracy of television measurement systems consisted of considering their influence on measuring the distance (from the camera) to the object of interest in the image, when - control of processing time. Based on the evaluation results, we can conclude that by using pre-processing of images with modified digital filters, the accuracy of measuring the distance from the camera to the measurement object is improved, while reducing processing time.


  • Increasing the contrast and accuracy of localization of objects of interest on orthophotomaps of the terrain built from distorted images from an unmanned aerial vehicle

    by Tomsk State University of Control Systems and Radioelectronics, A. S. Zakhlebin, M. I. Kuryachiy, V. V. Kapustin, A. V. Kamenskiy, A. K. Movchan

    In this article, we will consider and compare methods for eliminating distortions in the original images obtained from an unmanned aerial vehicle. The main goal of these methods is to increase the contrast and accuracy of determining the coordinates of objects of interest relative to the background. To conduct the study, aerial work is performed, during which initial images of the underlying surface with different exposure times are obtained, as well as data from the unmanned aerial vehicle navigation module. Further, cameral processing of the received materials is carried out. The exact centers for photographing each image are calculated and orthophotomaps of the area are built. Then we have evaluated the contrast and accuracy of determining the coordinates of objects of interest relative to the background on the orthophotomaps of the area built from the original and restored images using various methods.


  • Digital anti-aliasing trapezoidal recursively separable image processing filter with resizable scanning multi-element aperture

    by Tomsk State University of Control Systems and Radioelectronics, A. V. Kamenskiy, K. A. Rylov, N. Borodina

    The development of television systems is an important factor for many industries involved in the acquisition, processing, storage and transmission of images. Today, an urgent task in the use of such systems is to improve the quality of images obtained using digital photo and video cameras. To solve this problem, digital recursive-separable smoothing filters can be used. The paper describes the process of operation of the algorithm for changing the size of the scanning multi-element aperture of a smoothing trapezoidal recursive-separable filter for digital image processing. The results of evaluating its performance relative to the same algorithm implemented through classical two-dimensional convolution for various sizes of test images are presented. The influence of the aperture size of the developed filter on the change in the signal-to-noise ratio is assessed. The algorithm is implemented in the MATLAB computing environment.


  • High-speed recursive-separable image processing filters with variable scanning aperture sizes

    by FSBEO HE «Tomsk State University of Control Systems and Radioelectronics», A.V. Kamenskiy, M.I. Kuryachiy, A.S. Krasnoperova, Yu.V. Ilyin, T.M. Akaeva, S.E. Boyarkin

    In the process of development of computer technologies, the number of areas of their application naturally grows and, along with it, the complexity of the tasks to be solved, which entails the need for new research. Similar tasks include digital filtering of images in the field of medical technologies and active-pulse television measuring systems. There are many methods and algorithms of digital filtering designed to solve the problem of improving the quality; algorithms that can improve the quality of images while reducing computational costs are widely used. High demands, which are made due to the constant growth in the size of the generated images, as well as the requirement for modern television systems, is real-time operation. When solving practical problems, it is required to use different filter aperture sizes, which provide an increase in quality and preservation of image details. The solution of these problems was the reason for the emergence of adaptive filters that are able to change the parameters in the process of processing the received data, while not spending additional time on processing with an increase in the size of the aperture. The paper presents the principles of constructing adaptive image processing filters, which, by obtaining an input parameter indicating the required dimension of a multi-element aperture, are able to implement the construction of the required aperture. The Laplacian “Truncated Pyramid” filter and the “double pyramid” Laplacian were modified. A feature of these filters is the oddness of the multi-element aperture, so the coefficient used to build the mask is always set to odd. When using these filters, it is possible to use two coefficients that are responsible for increasing the filtration efficiency, since, in their original form, the Laplacian filters have a sum of coefficients equal to zero. The experiment shows a comparison with high-dimensional filters that work when using classical two-dimensional convolution. The next stage of the presented research will be the application of parallel computing techniques, which will increase the speed of the developed filters.


  • Assessment of the Quality of Color Reproduction of 3D Medical Images

    by R.E. Makazhanov, M.I. Kuryachij, A.V. Kamenskiy

    This article discusses the problem of assessing the quality of color reproduction in 3D medical images. In the context of medical images, accurate and appropriate color reproduction plays an important role in correct interpretation and diagnosis. The article provides an overview of existing standards and metrics used to evaluate color reproduction in the field of medical imaging. Aspects such as the choice of color space, the accuracy of color transmission, and consistency between different display devices, human perception of color and other factors affecting the quality of color reproduction are considered. Testing and improvement of the qualitative characteristics of the color reproduction of the monitor using software and hardware to standardize its color parameters has been performed. The color distance of the monitor in the CIE L*a*b* color space before calibration was 14.84, and after calibration 1.23.

  • Influence of Non-Equilateral Apertures on the Characteristics of Digital Filters "Truncated Pyramid" Laplacian and "Double Pyramid" Laplacian

    by K.S. Kupriyanova, K.A. Rylov, A.V. Kamenskiy

    In the process of processing digital images, an important role is played by increasing the efficiency of the applied methods and processing algorithms. One way to improve efficiency is to convert spatial filters into recursively separable digital filters. The use of such filters makes it possible to reduce the number of computational operations. This article presents digital recursively-separable Laplacian filters "truncated pyramid" and "double pyramid" converted into non-equilateral form. This transformation allows to further reduce the number of computational operations and speed up the processing. Also, the article discusses the principle of operation of these filters, their structure and operation algorithm. Based on the results of image processing by a digital recursively separable filter Laplacian "double pyramid", the quality of processing by a filter with a base mask of 7x7 elements and non-equilateral apertures is evaluated and compared.