Image Classification using Convolutional Neural Networks

Main Article Content

Abstract

Nowadays, many different tools can be used to classify images, each of which is aimed at solving a certain range of tasks. This article provides a brief overview of libraries and technologies for image classification. The architecture of a simple convolutional neural network for image classification is built. Image recognition experiments have been conducted with popular neural networks such as VGG 16 and ResNet 50. Both neural networks have shown good results. However, ResNet 50 overfitted due to the fact that the dataset contained the same type of images for training, since this neural network has more layers that allow reading the attributes of objects in the images. A comparative analysis of image recognition specially prepared for this experiment was carried out with the trained models.

Article Details

References

1. Фисько Д.В. Обзор методов условной генерации изображений нейросетевыми моделями // Актуальные вопросы современной науки и технологий. 2021. С. 57–62.
2. Мосин Е.Д., Белов Ю.С. Генерация музыки с использованием двунаправленной рекуррентной нейронной сети // Научное обозрение. Технические науки. 2023. № 1. С. 10–14. https://doi.org/10.17513/srts.1419
3. Козар Б.А., Кугуракова В.В., Сахибгареева Г.Ф. Структуризация сущностей естественного текста с использованием нейронных сетей для генерации трехмерных сцен // Программные продукты и системы. 2022. Т. 35. № 3. С. 329–339. https://doi.org/10.15827/0236-235X.139.329-339.
4. Пантюхин Д.В. Нейронные сети синтеза речи голосовых помощников и поющих автоматов // Речевые технологии/Speech Technologies. 2021. № 3-4. С. 3–16. https://doi.org/10.58633/2305-8129_2021_3-4_3
5. Шамансуров Ш. Влияние искусственного интеллекта на развитие области синхронного перевода // Oriental renaissance: Innovative, educational, natural and social sciences. 2023. Т. 3. № 23. С. 305–309. https://doi.org/10.5281/zenodo.10365801
6. Pang B., Nijkamp E., Wu Y.N. Deep learning with tensorflow: a review // Journal of Educational and Behavioral Statistics. 2020. Vol. 45. No. 2. P. 227–248. https://doi.org/10.3102/1076998619872761
7. Ketkar N., Ketkar N. Introduction to Keras // Deep learning with python: a hands-on introduction. 2017. P. 97–111. https://doi.org/10.1007/978-1-4842-2766-4_7
8. Convolutional Neural Networks. URL: https://www.ibm.com/topics/convolutional-neural-networks
9. Sapijaszko G., Mikhael W.B. An overview of recent convolutional neural network algorithms for image recognition // 2018 IEEE 61st International midwest symposium on circuits and systems (MWSCAS). IEEE, 2018. P. 743–746. https://doi.org/10.1109/MWSCAS.2018.8623911
10. He K. et al. Deep residual learning for image recognition // Proceedings of the IEEE conference on computer vision and pattern recognition. 2016. P. 770–778. https://doi.org/10.48550/arXiv.1512.03385
11. Nguyen V. Bayesian optimization for accelerating hyper-parameter tuning // 2019 IEEE second international conference on artificial intelligence and knowledge engineering (AIKE). IEEE. 2019. P. 302–305. https://doi.org/10.1109/AIKE.2019.00060
12. Poojary R., Raina R., Mondal A.K. Effect of data-augmentation on fine-tuned CNN model performance // IAES International Journal of Artificial Intelligence. 2021. Vol. 10. No. 1. P. 84. https://doi.org/10.11591/ijai.v10.i1.pp84-92
13. Tian Y., Zhang Y. A comprehensive survey on regularization strategies in machine learning // Information Fusion. 2022. Vol. 80. P. 146–166. https://doi.org/10.1016/j.inffus.2021.11.005
14. Fruits 360. URL: https://www.kaggle.com/datasets/moltean/fruits
15. PyCharm, Quick start guide. URL: https://www.jetbrains.com/help/pycharm/quick-start-guide.html
16. MacOS. URL: https://www.apple.com/za/macos/what-is/
17. Zhang Z. Analysis of the Advantages of the M1 CPU and Its Impact on the Future Development of Apple // 2021 2nd International Conference on Big Data & Artificial Intelligence & Software Engineering (ICBASE). IEEE, 2021. P. 732–735. https://doi.org/10.1109/ICBASE53849.2021.00143
18. Tensorflow Macos. URL: https://developer.apple.com/metal/tensorflow-plugin/
19. Conv2D layer. URL: https://keras.io/api/layers/convolution_layers/convolution2d/
20. MaxPooling2D layer. URL: https://keras.io/api/layers/pooling_layers/max_pooling2d/
21. Flatten layer. URL: https://keras.io/api/layers/reshaping_layers/flatten/
22. Dense layer. URL: https://keras.io/api/layers/core_layers/dense/
23. Dropout layer. URL: https://keras.io/api/layers/regularization_layers/dropout/
24. Layer activation functions, Softmax function. URL: https://keras.io/api/layers/activations/#softmax-function