DOI: 10.18503/1995-2732-2026-24-1-133-141
Abstract
Problem Statement (Relevance). At the moment, computer vision tools and neural networks are becoming increasingly widespread in all fields and spheres of human activity. They are already used in technology, medicine, education, the creation of various art objects and in other activity areas. The mechanical engineering industry is also actively implementing them. As one of the possible applications of neural networks for mechanical engineering, it is proposed to use models for recognizing objects in images and videos for working with drawings. This approach will significantly reduce labor costs when preparing documentation for launching the product into production. This applies to enterprises that have rotational parts in their production range, which is relevant, new and promising in modern production conditions. Objectives. The work is aimed at creating a model based on a neural network capable of efficiently detecting an area in a drawing containing the length of rotational parts with the further creation of a computer program using this model and increasing its efficiency and practical applicability. Methods Applied. In the course of the work, several basic methods have been used: learning and working with a model for recognizing objects in images and videos; writing computer programs in the Python programming language; optical text recognition. Result. The paper presents a computer program that is capable of efficiently detecting an area in a drawing containing the length of a part, reading text from this area, which is the length value, and entering the results into a table in an editable format. Practical Relevance. This program has significant prospects for practical application because it can help automate the planning of the production of rotational parts, for example, when determining the consumption rate of materials per part or when checking the dimensions when assigning equipment used for their manufacture and grouping.
Keywords
YOLOv5, EasyOCR, drawings, turning, rotational parts, object detection, neural networks, object recognition, computer vision
For citation
Kuznetsov S.V., Rogovik A.A. Automated Detection and Recognition of Lengths of Rotational Parts in Technical Drawings Using Computer Vision Tools. Vestnik Magnitogorskogo Gosudarstvennogo Tekhnicheskogo Universiteta im. G.I. Nosova [Vestnik of Nosov Magnitogorsk State Technical University]. 2026, vol. 24, no. 1, pp. 133-141. https://doi.org/10.18503/1995-2732-2026-24-1-133-141
1. Suzdaleva N.N. The potential of using neural networks by industrial enterprises in the context of Russian reality. Regionalnaya i otraslevaya ekonomika [Regional and sectoral economics]. 2022;(11(173)):91-94. (in Russ.)
2. Altunina K.A., Sokolova M.V. Application of neural networks for modeling the turning process. Vestnik TGTU [Bulletin of TSTU]. 2016;22(1):122-133. (in Russ.)
3. Stepanov D.V., Makarov A.V., Molotov A.M., Bolotov E.N. Convolutional neural networks for detecting defects and damage to structures. Promyshlennoye i grazhdanskoye stroitelstvo [Industrial and civil engineering]. 2024;(9):52-58. (in Russ.)
4. Veretelnikov A.S., Gavlitsky A.I. Application of artificial intelligence in the metalworking industry. Elektronniy nauchniy zhurnal «Dnevnik nauki» [Electronic scientific journal "Diary of Science"]. 2022;(12(72)). (in Russ.)
5. Alkhanov A.A. Machine learning and its application in the modern world. Problemy nauki [Problems of Science]. 2021;(7(66)):25-27. (in Russ.)
6. Redmon J., Farhadi A. YOLO9000: Better, Faster, Stronger. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017;7263-7271.
7. Redman J., Shoji F., Farhadi A. YOLOv5 Training and Improving Object Detector and Segmentation Models with One Click. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2022;962-972.
8. Sin T.-Y., Dollar P., Girshick R., He K., Hariharan B., Belongie S. Feature Pyramid Networks for Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017;936-944.
9. Bochkovsky A., Wang C. Yellow 5: Creating State-of-the-Art Object Detector in Real Time. S. l. ArXiv. 2021;214-219.
10. Bochkovsky A. YOLOv7: Trainable Boosted Data-Driven Layer for Real-Time Object Detection. S. 1. ArXiv. 2023;5147-5155.
11. Davletov A.R. Modern machine learning methods and OCR technology for document processing automation. Vestnik nauki [Bulletin of Science]. 2023;(10):676-698. (in Russ.)
12. Hamdi A. OCR with Tesseract, Amazon Textract, and Google Document AI: a benchmarking experiment. Journal of Computational Social Science. 2022;(5(1)):861-882.
13. Patel D. Improving the Accuracy of Tesseract 4.0 OCR Engine Using Convolution-Based Preprocessing. Symmetry. 2020;(12(5)):715.
14. Kuznetsov S.V., Rogovik A.A. The prospect of using neural networks to plan the loading of a machining site. International Journal of Humanities and Natural Sciences. 2024;(9):115-117. (in Russ.)
15. Kuznetsov S.V., Rogovik A.A. Grouping rotation bodies of “disс” and similar type when planning their manufacture to increase the serial production. Vestnik IzhGTU imeni M.T. Kalashnikova [Bulletin of Kalashnikov Izhevsk State Technical University]. 2025;28(1):24-32. (in Russ.) DOI: 10.22213/2413-1172-2025-1-24-32
16. Mitrofanov S.P. Nauchnaya organizatsiya mashinostroitelnogo proizvodstva [Scientific organization of machine-building production]. Leningrad. Mashinostroenie, 1976, 712 p. (in Russ.)
17. Kuznetsov S.V., Anosov M.S., Rogovik A.A., Murugov Yu.S. Determination of the unit time coefficients of “shaft” type parts based on their similarity. Nauchno-tekhnicheskiy vestnik Povolzhya [Scientific and Technical Bulletin of the Volga region]. 2024;(6):72-75. (in Russ.)