Intellectualization of the process of detecting shapes of geometric objects

Purpose of research. Development of program code in the C# programming language that implements an algorithm for recognizing the shape of geometric objects in the input image while ensuring the reliability of this computational process is the main goal of the article.

Methods. The algorithm for recognizing the geometric shapes of objects is based on a combination of traditional image processing methods and intelligent rules that determine the type of geometric shape of an object depending on the characteristics of the contours, such as moments, the number of their sides, etc. To implement this method, the following sequence of mathematical operations which includes the following stages is proposed in the article. Firstly, this method includes the following operations: blur, convert the original image to grayscale, and invert. Detection of contours and determination of their characteristics, such as moments, perimeter, etc., is carried out at the second stage of the method. And at the final stage, the comparison of each found contour of a certain geometric figure is carried out depending on the number of sides included in the structure of the contour.

Results. An algorithm and instructions for creating program code have been developed for the software implementation of the process of recognizing the geometric shape of objects. It was determined that the proposed algorithm has a high reliability approximately equal 97%.

Conclusion. Traditional image processing methods such as blurring and grayscale conversion can be successfully combined with methods for identifying contours and determining their geometric characteristics. This synergy of image processing methods makes it possible to create an algorithm for recognizing geometric shapes. It is important to consider that the reliability and efficiency of such an algorithm depends on the settings of the threshold values used in the image processing functions and further study of their characteristics can lead to improved results of the algorithm presented in the article.

1. Gneushev A. N., Murynin A. B. Adaptive gradient method for selecting contour features of objects in images of real scenes. Izvestiya Rossiiskoi akademii nauk. Teoriya i sistemy upravleniya = Izvestia of the Russian Academy of Sciences. Theory and Control Systems. 2003; (6): 153-160. (In Russ.).

2. Chertov M. A., Rudensky G. E., Psakhye S. G., Skvortsov A.V. An algorithm for grouping geometric objects in automatic cutting of sheet material using local shape characteristics. Vychislitel'nye tekhnologii = Computational Technologies. 2006; 11 (2): 93-107. (In Russ.).

3. Chukanov S. N. Comparison of images of objects by methods of computational topology. Trudy SPIIRAN = Proceedings of SPIIRAN. 2019; 18(5): 1043-1065. (In Russ.). https://doi.org/10.15622/sp.2019.18.5.1043-1065.

4. Chukanov S. N. Comparison of diffeomorphic images based on the formation of persistent homologies. Modelirovanie i analiz informatsionnykh sistem = Modeling and Analysis of Information Systems. 2019; 26 (3): 450-468. (In Russ.). https://doi.org/10.18255/1818-1015-2019-3-450-468.

5. Shabalin A. S., Rakhmatullov I. I., Polyanin N. A. Comparison of two methods of pattern recognition of geometric shapes. Uchenye zapiski UlGU. Seriya: Ma-tematika i informatsionnye tekhnologii = Scientific Notes of UlSU. Series: Mathematics and Information Technology. 2021: (2): 82-89. (In Russ.).

6. Voronova L. V., Panisheva E. V. On the issue of choosing a method for determining boundaries and recognizing a graphic object in relation to the problem of identifying a car number. Tekhnologii i kachestvo = Technology and Quality. 2022; (2): 46-50. (In Russ.). https://doi.org/10.34216/2587-6147-2022-2-56-46-50.

7. Bobyr M. V., Emelyanov S. G., Milostnaya N. A. Algorithm for Creating 3d Scenes of Recognized Objects from Depth Maps. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta = Proceedings of the Southwest State University. 2023; 27(2): 90-104 (In Russ.). https://doi.org/10.21869/2223-1560-2023-27-2-90-104.

8. Bobyr M., Arkhipov A., Emelyanov S., Milostnaya N. A method for creating a depth map based on a three-level fuzzy model. Engineering Applications of Artificial Intelligence. 2023; 117 (Part B): 105629. https://doi.org/10.1016/j.engappai.2022.105629.

9. Bobyr M. V., Arkhipov A. E., Yakushev A. S., Cao Ts. Building a depth map using an upgraded Canny filter. Pt. 1. Promyshlennye ASU i kontrollery = Industrial automated control systems and controllers. 2021; (4): 12-20. (In Russ.). https://doi.org/10.25791/asu.4.2021.1271.

10. Bobyr M. V., Arkhipov A. E., Yakushev A. S., Bhattacharya S. Building a depth map using an upgraded Canny filter. Pt. 2. Promyshlennye ASU i kontrollery = Industrial automated control systems and controllers, 2021; (5): 3-15. (In Russ.). https://doi.org/10.25791/asu.5.2021.1277.

11. Godunov A. I., Balanyan S. T., Egorov P. S. Image segmentation and object recognition based on convolutional neural network technology. Nadezhnost' i kachestvo slozhnykh sistem = Reliability and quality of complex systems. 2021; (3): 62-73. (In Russ.). https://doi.org/10.21685/2307-4205-2021-3-8.

12. Lobanov M. G., Sholomov D. L. On accelerating the architecture of a convolutional neural network based on ResNet in the task of recognizing objects of the road scene. Informatsionnye tekhnologii i vychislitel'nye sistemy = Information Technologies and Computing Systems. 2019; (3): 57-65. (In Russ.).https://doi.org/10.14357/20718632190305.

13. Kadukov E. P. Recognition of control objects on radar images using the method of reference vectors. Voprosy oboronnoi tekhniki. Seriya 16: Tekhnicheskie sredstva protivodeistviya terrorizmu = Questions of defense technology. Series 16: Technical means of countering terrorism. 2022; (9-10): 96-105. (In Russ.).

14. Polivanov A. Yu., Ivanov Yu. V. Human recognition in the technical vision system of a mobile robot based on the method of support vectors. Vestnik MGTU "Stankin" = Bulletin of the Moscow State Technical University "Stankin". 2023; (3): 17-27. (In Russ.).

15. Pugin E. V., Zhiznyakov A. L. Image processing algorithms for detecting objects using fuzzy features. Radiotekhnicheskie i telekommunikatsionnye sistemy = Radio Engineering and Telecommunication Systems. 2020; (2): 59-65. (In Russ.)

16. Bobyr M. V., Arkhipov A. E., Gorbachev S. V., Cao Ts., Bhattacharya S. Fuzzy logic methods in the problem of detecting object boundaries. Informatika i avtomatizatsiya = Computer Science and Automation. 2022; (21): 376-404. (In Russ.). https://doi.org/10.15622/ia.21.2.6

17. Bobyr M. V., Yemelyanov S. G., Arkhipov A. E., Milostnaya N. A. Applied neurofuzzy computing systems and devices. Moscow: Infra-M; 2023. 263 p. (In Russ.). https://doi.org/10.12737/1900641.

18. Bobyr M. V., Milostnaya N. A., Bulatnikov V. A. The fuzzy filter based on the method of areas' ratio. Applied Soft Computing. 2022; 117: 108449. https://doi.org/10.1016/j.asoc.2022.108449.

19. Bobyr M. V., Milostnaya N. A. Analysis of the use of soft arithmetic operations in the structure of fuzzy logical inference. Vestnik komp'yuternykh i informatsionnykh tekhnologii = Bulletin of Computer and Information Technologies. 2015; (7): 7-15. (In Russ.). https://doi.org/10.14489/vkit.2015.07.pp.007-015.

20. Bobyr M. V., Arkhipov A. E., Yakushev A. S. [Recognition of the shade of a color label based on fuzzy clustering]. Informatika i avtomatizatsiya = Informatics and Automation, 2021; 20 (2): 407-434. (In Russ.). https://doi.org/10.15622/ia.2021.20.2.6.

21. Emgu CV Library Documentation. VectorOfVectorOfPoint Class. Available at: www.emgu.com/wiki/files/3.0.0/document/html/b29e1d11-e75c-6bbe-4b3b7d8e6395a733.htm (Доступ свободный).

22. Emgu CV Library Documentation. CvInvoke.FindContours Method. Available at: www.emgu.com/wiki/files/4.5.5/document/html/M_Emgu_CV_CvInvoke_FindContours.ht m (Доступ свободный). 23. Balun V. N., Drozdov N. A., Doroshenko E. V. Software implementation of the Douglas-Pecker algorithm for reducing the number of polyline points. Sovremennye tendentsii razvitiya i perspektivy vnedreniya innovatsionnykh tekhnologii v mashinostroenii, obrazovanii i ekonomike = Modern development trends and prospects for the introduction of innovative technologies in mechanical engineering, education and economics. 2019; 5 (1): 157-163. (In Russ.).