IMAGE RECOGNITION BASED ON MACHINE LEARNING IN CORPORATE INFORMATION SYSTEMS: OVERVIEW OF METHODS AND CHOICE OF APPROACH

Image recognition plays a critical role in corporate information systems (CIS), finding widespread application in areas such as security, monitoring, asset management, and business process automation. This technology enables companies to efficiently process visual data, improve decision-making processes, and reduce processing time. Modern image processing methods include both traditional computer vision algorithms and advanced approaches based on machine learning, such as Convolutional Neural Networks (CNN) and Transformers. This article analyzes existing methods, their strengths, and weaknesses. Particular attention is paid to contemporary machine learning models, which showcase high accuracy in classification tasks. A methodology based on Transfer Learning using ResNet architecture is proposed, which significantly enhances image classification accuracy even with a limited amount of training data. The research results demonstrate that the application of neural networks substantially improves the performance of image recognition systems by reducing errors and increasing processing speed. The article also discusses potential improvements to current models and future research directions, including the integration of computer vision technologies into corporate systems.

image recognition, machine learning, information systems, neural networks, computer vision, transformers, image analysis, authentication.

1. Andreev, D. “Application of Machine Learning for Image Recognition Problems.” Moscow University Bulletin. Series 15: Computational Mathematics and Cybernetics, 2020, pp.45–58.

2. Kirillov, S. A., Petrov, V. V. “Deep Learning Methods in Image Classification.” Information Technologies and Computing Systems, 2021, no. 3, pp. 12–23.

3. Smirnov, D. I. “Automated Face Recognition Based on Convolutional Neural Networks.” Artificial Intelligence and Decision Making, 2020, no. 4, pp. 78–92.

4. Vlasov, I. M., Rogov, A. A. “Deep Neural Network Models in Image Processing Problems.” Scientific and Technical Bulletin of Information Technologies, 2022, no. 5, pp. 34–47.

5. He K., Zhang X., Ren S., Sun J. Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770-778.

6. Dosovitskiy A., Beyer L., Kolesnikov A., et al. An Image is Worth 16×16 Words: Transformers for Image Recognition at Scale. International Conference on Learning Representations (ICLR), 2021, pp. 1-15.

7. Krizhevsky A., Sutskever I., Hinton G. ImageNet Classification with Deep Convolutional Neural Networks. Advances in Neural Information Processing Systems, 2012, vol. 25, pp.1097-1105.

8. Simonyan K., Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv preprint arXiv:1409.1556, 2014, pp. 1-14.

9. Goodfellow I., Bengio Y., Courville A. Deep Learning. MIT Press, 2016, pp. 1-775.

10. Redmon J., Farhadi A. YOLOv3: An Incremental Improvement. arXiv preprintarXiv:1804.02767, 2018, pp. 1-6.

11. Chen, X., Zhang, Y. “Artificial intelligence applications in logistics: A focus on inventory tracking and quality control.” Logistics and Transportation Review, 2022 15(4), 287-295.

12. Tan, L., Zhou, Q. “Using image recognition for product defect detection in manufacturing.” Journal of Industrial and Production Engineering, 2020 42(6), 321-330.

2026-03-30