RECOGNITION MODELS AND THEIR CLASSIFICATION USING MACHINE LEARNING

The article is devoted to the study of various models of image recognition and classification using machine learning methods. The work considers both classical algorithms, such as support vector methods and decision trees, and more complex and modern approaches, including convolutional neural networks (CNN) and deep learning. These methods are actively used for efficient processing and analysis of visual data in various fields. The article analyzes in detail the features of each approach, their advantages and disadvantages, and provides specific examples of application in real tasks. The article considers various kinds of tasks such as object classification, face recognition, medical image analysis, as well as more complex tasks, such as segmentation and detection of objects in images. Particular attention is paid to the application of machine learning technologies in such areas as security, healthcare, industry and robotics. The article provides a comparative analysis of various models in terms of their accuracy, speed and computational costs, discusses the prospects for further development of image recognition technologies, possible directions for improving accuracy and performance, as well as their future application to create more intelligent and autonomous systems.

image recognition, classification, machine learning models, neural networks, convolutional neural networks, deep learning, classification algorithms.

1. Andreev K. V., Smirnov A. P. Modern Approaches to Image Classification Using Neural Networks. Bulletin of Moscow State University. Series: Applied Mathematics and Information Science, 35(2), p. 105-118.

2. Belyaev D. S., Timofeeva O. V. Application of GANs to Improve Data Quality in Image Recognition Problems. Bulletin of Moscow Institute of Electronics and Mathematics, 13(4), p.61-74.

3. Grigoriev N. A., Sidorova L. V. Application of Convolutional Neural Networks for Image Analysis in Medicine and Industry. Computer Research and Modeling, 12(4), p. 67-79.

4. Danilov O. E., Koroleva L. S. Application of Pre-trained Deep Learning Models for Image Recognition. Modern Information Technology and Engineering Research, 15(1), p. 98-112.

5. Zakharov A. V., Smirnova T. A. Image Classification Based on Ensemble Machine Learning Methods. Intelligent Systems and Machine Learning, 18(2), p. 177-190.

6. Kuznetsov V. P., Sokolova T. G. Image Classification Using Deep Learning Algorithms. Information Technology and Computing Systems, 24(3), p. 88-99.

7. Orlov E. P., Zakharova M. A. Image Recognition and Segmentation Using Transformers. Journal of Machine Learning and Computer Vision, 10(1), p. 132-145.

8. Petrov A. I., Bobrov K. S. Optimization of Neural Network Image Recognition Models. Automation and Digital Technologies in Science and Production, 9(2), p. 121-133.

9. Romanov D. V., Klimova E. N. Using Deep Learning Methods for Handwritten Character Recognition. Kazan University Bulletin. Series: Physical and Mathematical Sciences, 48(1), p. 52-64.

10. Fedorov I. G., Kiselev M. V. Automatic Object Recognition Using Machine Learning Methods. Journal of Digital Technologies and Artificial Intelligence, 7(3), p. 145-157.

2026-03-25