Practical Comparison of Computer Vision and Deep Learning Methods for the Binary Image Classification Task

Vladimir Lokhvitsky; Evgeny L. Yakovlev; Ilya Bushev

doi:10.20295/2413-2527-2025-444-89-98

UDC

656.073

VAK Russia

1.2.1 1.2.2 2.3.1

PRACTICAL COMPARISON OF COMPUTER VISION AND DEEP LEARNING METHODS FOR THE BINARY IMAGE CLASSIFICATION TASK Practical Comparison of Computer Vision and Deep Learning Methods for the Binary Image Classification Task

АА Аа

Published in Intellectual Technologies on Transport · Pages 89–98 · Rubric: MATHEMATICAL MODELLING AND SYSTEM ANALYSIS

DOI: https://doi.org/10.20295/2413-2527-2025-444-89-98 · EDN: RLQION

Received: 20.11.2025 Accepted: 25.11.2025 Published: 15.12.2025

Authors

Vladimir Lokhvitsky

Evgeny L. Yakovlev

Ilya Bushev

Vladimir Lokhvitsky

Academic degree: doctor of technical sciences

Mozhaisky Military Aerospace Academy Associate Professor · Department of Mathematics and Software for Special Space Complexes · Russian Federation · Saint Petersburg

Evgeny L. Yakovlev

Academic degree: candidate of technical sciences

Mozhaisky Military Aerospace Academy Associate Professor · Department of Mathematics and Software for Special Space Complexes · Russian Federation · Saint Petersburg

Ilya Bushev

Mozhaisky Military Aerospace Academy Russian Federation · Saint Petersburg

ABSTRACT

Binary image classification tasks are widely employed in engineering and manufacturing systems, including automated control, machine vision, and object monitoring. As the complexity of imaging conditions increases and data volumes expand, it becomes essential to evaluate classical computer vision algorithms alongside deep learning neural network methods to identify the most effective method. Purpose: to perform a practical comparison of the effectiveness of a traditional image processing algorithm and the YOLO neural network model for addressing the binary classification challenge. Methods: traditional image processing techniques, including threshold filtering, morphological operations, and geometric feature analysis, as well as the YOLO detection model trained on a labeled dataset. Results: the classical algorithm has demonstrated high processing speed and adequate accuracy under stable lighting conditions; however, it has exhibited a pronounced decline in performance when imaging conditions changed. In contrast, the YOLO model has demonstrated enhanced accuracy, resilience to both photometric and geometric variations, and consistent performance even in the presence of extraneous noise. Practical significance: the results can guide the development of computer vision systems, aid in the selection of the optimal algorithm for specific operational scenarios, and facilitate the creation of hybrid systems that combine the strengths of both traditional and neural network methods. Discussion: this study confirms that while traditional methods are effective in resource-constrained environments, they are vulnerable to external influences. Conversely, neural network approaches offer superior generalization and stability, making them more advantageous in fluctuating imaging conditions. The novelty of the research lies in the comparative analysis of these methods under identical processing parameters, with a particular focus on practical indicators. This approach facilitates an objective assessment of the applicability domain inherent to each method.

KEYWORDS

computer vision, deep learning, YOLO, binary classification, image analysis, image processing, neural network methods

Text

Text (PDF)

Read Download

1. Senichev A. V., Novikova A. I., Vasilyev P. V. Sravnenie glubokogo obucheniya s traditsionnymi metodami kompyuternogo zreniya v zadachakh identifikatsii defektov [Comparison of Deep Learning with Traditional Methods of Computer Vision in the Problems of Defects Identification], Molodoy issledovatel Dona [Young Researcher of Don], 2020, No. 4 (25), Pp. 64–67. (In Russian) EDN: https://elibrary.ru/TKXORB

2. Polkovnikova N. A. Issledovanie metodov i algoritmov kompyuternogo zreniya na osnove svertochnykh i rekurrentnykh neyronnykh setey [Research of Methods and Algorithms of Computer Vision Based on Convolutional and Recurrent Neural Networks], Ekspluatatsiya morskogo transporta [Marine Transport Operation], 2020, No. 3 (96), Pp. 154–168. DOI:https://doi.org/10.34046/aumsuomt96/21. (In Russian) EDN: https://elibrary.ru/TQLDDM

3. Saksonov P. V., Bauman A. A. Obzor metodov mashinnogo obucheniya [Overview of Machine Learning Methods], Sovremennye tendentsii i innovatsii v nauke i proizvodstve: materialy XII Mezhdunarodnoy nauchno-prakticheskoy konferentsii [Modern Trends and Innovations in Science and Production: Proceedings of the XII International Scientific and Practical Conference], Mezhdurechensk, Russia, April 26, 2023. Mezhdurechensk, T. F. Gorbachev Kuzbass State Technical University, 2023. Pp. 444-1–444-6. (In Russian) EDN: https://elibrary.ru/OVBWRJ

4. Gonzalez R. C., Woods R. E. Tsifrovaya obrabotka izobrazheniy [Digital Image Processing. Third Edition]. Moscow, Tekhnosphera Publishing House, 2012, 1104 p. (In Russian) EDN: https://elibrary.ru/TIKLUW

5. Senichev A. V., Novikov S. S. Metody kompyuternogo zreniya i ikh primenenie v analize izobrazheniy [Computer vision methods and their application in image analysis]. Moscow, Institute for the Study of Science of the RAS, 2020, 142 p. (In Russian)

6. Bradski G., Kaehler A. Learning OpenCV: Computer Vision with the OpenCV Library. Sebastopol (CA), O’Reilly Media, 2008, 575 p.

7. Redmon J., Farhadi A. YOLOv3: An Incremental Improvement, ArXiv, 2018, Vol. 1804.02767, 6 p. DOI:https://doi.org/10.48550/arXiv.1804.02767.

8. Caballar R. D., Stryker C. What is Computer Vision? Available at: http://www.ibm.com/think/topics/computer-vision (accessed: November 07, 2025).

9. Patel M. The Complete Guide to Image Preprocessing Techniques in Python. Available at: http://readmedium.com/the-complete-guide-to-image-preprocessing-techniques-in-python-dca30804550c (accessed: November 07, 2025).

10. Thresholding (Image Processing), Wikipedia. Last update November 12, 2025. Available at: http://en.wikipedia.org/wiki/Thresholding_(image_processing) (accessed: November 16, 2025).

11. Mathematical Morphology, Wikipedia. Last update November 08, 2025. Available at: http://en.wikipedia.org/wiki/Mathematical_morphology (accessed: November 16, 2025).

12. Bradski G. The OpenCV Library, Dr. Dobb’s Journal Software Tools, 2000, Vol. 25, Iss. 11, Pp. 120–125. EDN: https://elibrary.ru/EOYXGL

13. Paszke A., Gross S., Massa F., et al. PyTorch: An Imperative Style, High-Performance Deep Learning Library, Advances in Neural Information Processing Systems 32: Proceeding of the 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada, December 08–14, 2019. NeurIPS Foundation, 2019. Pp. 8024–8035.

14. Hunter J. D. Matplotlib: A 2D Graphics Environment, Computing in Science and Engineering, 2007, Vol. 9, Iss. 3, Pp. 90–95. DOI:https://doi.org/10.1109/MCSE.2007.55.

15. 15. Turay T., Vladimirova T. Toward Performing Image Classification and Object Detection with Convolutional Neural Networks in Autonomous Driving Systems: A Survey, IEEE Access, 2022, Vol. 10, Pp. 14076–14119. DOI:https://doi.org/10.1109/ACCESS.2022.3147495. EDN: https://elibrary.ru/NWOBGS

16. Powers D. M. W. Evaluation: From Precision, Recall and F-measure to ROC, Informedness, Markedness and Correlation, Journal of Machine Learning Technologies, 2011, Vol. 2, Iss.1, Pp. 37–63.

17. Klette R. Kompyuternoe zrenie. Teoriya i algoritmy [Concise Computer Vision. An Introduction into Theory and Algorithms]. Moscow, DMK Press Publishing House, 2019, 506 p. (In Russian)

PDF Text JATS XML

Editor-in-Chief

Anatoly Khomonenko

khomon@mail.ru

Deputy Editor-in-Chief

Lesya Bozhko

Principal Contact

Maksim Orzhevsky

206@it-pgups.ru

Editorial Staff

Staff Editorial

itt-pgups@yandex.ru +7(812)457-86-06

1531

downloads

GOST

Lokhvitsky V. A., Yakovlev E. L., Bushev I. V. Practical Comparison of Computer Vision and Deep Learning Methods for the Binary Image Classification Task // Intellectual Technologies on Transport. 2025. no. 4. pp. 89-98. DOI: https://doi.org/10.20295/2413-2527-2025-444-89-98. EDN: RLQION. (Date of access 08.09.2026).

MLA

Vladimir Lokhvitsky, Yakovlev E. L., Bushev I. V.. "Practical Comparison of Computer Vision and Deep Learning Methods for the Binary Image Classification Task." Intellectual Technologies on Transport.4 (2025): 89-98. DOI: https://doi.org/10.20295/2413-2527-2025-444-89-98. EDN: RLQION.

APA

Lokhvitsky V. A., Yakovlev E. L., Bushev I. V. (2025). Practical Comparison of Computer Vision and Deep Learning Methods for the Binary Image Classification Task. Intellectual Technologies on Transport(4), 89-98. https://doi.org/10.20295/2413-2527-2025-444-89-98 EDN: RLQION.

Chicago

Vladimir Lokhvitsky, Yakovlev E. L., Bushev I. V.. "Practical Comparison of Computer Vision and Deep Learning Methods for the Binary Image Classification Task." Intellectual Technologies on Transport, no. 4 (2025): 89-98. https://doi.org/10.20295/2413-2527-2025-444-89-98. EDN: RLQION.

WIKI

{{cite journal | author = Lokhvitsky V. A., Yakovlev E. L., Bushev I. V. | title = Practical Comparison of Computer Vision and Deep Learning Methods for the Binary Image Classification Task | journal = Intellectual Technologies on Transport | year = 2025 | issue = 4 | pages = 89-98 | doi = 10.20295/2413-2527-2025-444-89-98 }} EDN: RLQION

Copy

Export: BibTeX EndNote RefMan RusMARC

PRACTICAL COMPARISON OF COMPUTER VISION AND DEEP LEARNING METHODS FOR THE BINARY IMAGE CLASSIFICATION TASK Practical Comparison of Computer Vision and Deep Learning Methods for the Binary Image Classification Task

Confirmation