Izvestiya of Saratov University.

Mathematics. Mechanics. Informatics

ISSN 1816-9791 (Print)
ISSN 2541-9005 (Online)

For citation:

Klyachin A. A. Extraction of features in images based on integral transformations in solving problems of classification of fragments of photographs. Izvestiya of Saratov University. Mathematics. Mechanics. Informatics, 2024, vol. 24, iss. 3, pp. 432-441. DOI: 10.18500/1816-9791-2024-24-3-432-441, EDN: NIUIGP

This is an open access article distributed under the terms of Creative Commons Attribution 4.0 International License (CC-BY 4.0).
Published online: 
30.08.2024
Full text:
download
(downloads: 154)
Language: 
Russian
Heading: 
Computer Sciences
Article type: 
Article
UDC: 
004.932.2
DOI: 
10.18500/1816-9791-2024-24-3-432-441
EDN: 
NIUIGP

Extraction of features in images based on integral transformations in solving problems of classification of fragments of photographs

Autors: 
Klyachin Alexey A., Volgograd State University
Abstract: 

The article proposes a method for calculating features in an image to form a training data set for solving various problems of video image classification. This method involves the use of well-known integral transformations — the Radon transform and the Steklov function. The proposed method is compared with convolutional neural networks both in terms of the percentage of correct prediction and in terms of its execution time. As a test task, the problem of finding a fragment of a photograph containing an image of a car is considered.

Key words: 
Radon transform
Steklov functions
convolutional neural network
machine learning methods
References: 
  1. Gonzalez R., Woods R. Digital Image Processing. Pearson/Prentice Hall, 2008. 954 p. (Russ. ed.: Moscow, Tekhnosfera, 2005. 1072 p.).
  2. Borzov S. M., Potaturkin A. O., Potaturkin O. I., Fedotov A. M. Analysis of the efficiency of classification of hyperspectral satellite images of natural and man-made areas. Optoelectronics, Instrumentation and Data Processing, 2016, vol. 52, iss. 1, pp. 1–10. https://doi.org/10.3103/S8756699016010015, EDN: WWFRIF
  3. Dorogov A. Yu., Kurbanov R. G., Razin V. V. Quick classification of JPEG images. Internet Mathematics 2005. Automatic Processing of Web Data. Moscow, 2005, pp. 147–172 (in Russian).
  4. Osokin V. V., Aipov T. D., Niyazova Z. A. About the classification of images and music files. Intelligent Systems. Theory and Applications, 2015, vol. 19, iss. 1, pp. 49–70 (in Russian). EDN: UWLELY
  5. Kupenova E. M., Kashnitskiy A. V. The method of random forests in the classification tasks of satellite images. Herald of Tver State University. Series: Geography and Geoecology, 2018, iss. 3, pp. 99–107 (in Russian). EDN: VRYRGY
  6. Goncharova E. F., Gaidel A. V. Methods of feature selection for problems of classification of images of the Earth’s surface. Informatsionnye tekhnologii i nanotekhnologii (ITBT-2017) [Information Technologies and Nanotechnology (ITNT-2017): Proceedings of the III International Conference and Youth school]. Samara, Novaya Tekhnika, 2017, pp. 535–540 (in Russian). EDN: YQLPDZ
  7. Turkova M. A., Gaidel A. V. Correlation features for classification of texture images. Informatsionnye tekhnologii i nanotekhnologii [Information Technologies and Nanotechnology: Proceedings of the IV International Conference and Youth School]. Samara, Novaya Tekhnika, 2018, pp. 595–599 (in Russian). EDN: XMWXVZ
  8. Chulichkov A. I., Morozova I. V. Classification of blurred images and estimation of registration system parameters by morphological analysis methods. Intelligent Systems, 2005, vol. 9, iss. 1–4, pp. 321–344 (in Russian). EDN: LZDWRV
  9. Borzov S. M., Potaturkin O. I. Vegetative cover type classification using hyperspectral remote sensing. Vestnik NSU. Series: Information Technology, 2014, vol. 12, iss. 4, pp. 13–22 (in Russian). EDN: TMFZOJ
  10. Pestunov I. A., Rylov S. A., Melnikov P. V. Classification of hyperspectral images with high spatial resolution. Journal of Siberian Federal University. Engineering & Technologies, 2018, vol. 11, iss. 1, pp. 69–76 (in Russian). https://doi.org/10.17516/1999-494X-0010, EDN: YPSWQC
  11. Kitaev D. N. Comparison of a convolutional neural network and the principal component method in the problem of classification of texture images. In: Prokofiev A. B. (ed.) Abstracts of LXVIII Youth Scientific Conference Dedicated to the 20th Anniversary of the Start of Operation of the International Space Station. Samara, Samara State University Publ., 2018, pp. 88–89 (in Russian). EDN: FNYNOI
  12. Golubkov A. M. Binary classification of images using the example of the face recognition problem. Izvestiya SPbGETU "LETI", 2018, iss. 7, pp. 26–30 (in Russian). EDN: VJYUBZ
  13. Nezhevenko E. S., Feoktistov A. S., Dashevsky O. Yu. Neural network classification of hyperspectral images of the basis of the Hilbert – Huang transform. Optoelectronics, Instrumentation and Data Processing, 2017, vol. 53, iss. 2, pp. 165–170. https://doi.org/10.3103/S8756699017020091, EDN: XNIJBJ
  14. Vaskan V. D. Overview of convolutional neural network architectures for the image classification problem. IT Standard, 2021, iss. 3 (28), pp. 34–39 (in Russian). EDN: WQQUFN
  15. Soldatova O. P., Garshin A. A. The use of a convolutional neural network for recognizing handwritten numbers. Computer Optics, 2010, vol. 34, iss. 2, pp. 252–260 (in Russian). EDN: MOTHJX
  16. Le Man Ha. Convolutional neural network for solving the classification problem. Proceedings of Moscow Institute of Physics and Technology, 2016, vol. 8, iss. 3, pp. 91–97 (in Russian). EDN: WWMDBT
  17. Azarov I. S., Prokopenya A. S. Overview of convolutional neural networks for image recognition. Big Data and Advanced Analytics, 2020, iss. 6–1, pp. 271–280 (in Russian). EDN: HBCHXL
  18. Sikorsky O. S. Overview of convolutional neural networks for the problem of image classification. New Information Technologies in Automated Systems, 2017, iss. 20, pp. 37–42 (in Russian). EDN: YNADUJ
  19. Deans S. R., Roderick S. The Radon Transform and Some of its Applications. New York, John Wiley & Sons, 1983. 289 p.
  20. Zhuk V. V., Kuzyutin V. F. Approksimatsiya funktsiy i chislennoye integrirovaniye [Approximation of Functions and Numerical Integration]. St. Petersburg, St. Petersburg University Publ., 1995. 352 p. (in Russian).
  21. Voronina V. V., Mikheev A. V., Yarushkina N. G., Svyatov K. V. Teoriya i praktika mashinnogo obucheniya [Theory and Practice of Machine Learning]. Ulyanovsk, Ulyanovsk State Technical University Publ., 2017. 290 p. (in Russian). EDN: QNQXJP
  22. Chollet F. Deep Learning with Python. New York, Manning Publications Co., 2018. 374 p. (Russ. ed.: St. Petersburg, Piter, 2018. 400 p.).
Received: 
27.02.2023
Accepted: 
08.04.2023
Published: 
30.08.2024
  • 368 reads