Email this article Application of neural networks of Siamese architecture in problems of classifying products of various categories on supermarket shelves
- Authors: Smirnov A.V.1, Tishchenko I.P.1
-
Affiliations:
- Ailamazyan Program Systems Institute of RAS
- Issue: Vol 15, No 2 (2024)
- Pages: 113-137
- Section: Articles
- URL: https://bakhtiniada.ru/2079-3316/article/view/299201
- DOI: https://doi.org/10.25209/2079-3316-2024-15-2-113-137
- ID: 299201
Cite item
Full Text
Abstract
This paper presents a study on the application of Siamese architecture neural networks in problems of classifying various food products on the shelves of department stores. Siamese networks are a special class of neural network architectures that combine two convolutional subnets. This type of neural networks is often used in object matching problems and has an important advantage over traditional convolutional neural networks, namely the absence of the need for a large amount of training data. During the work, we generated our own data set, including five different product categories. As a result, it was possible to achieve a tonality of 97.5% during training.
Keywords
About the authors
Alexander Vladimirovich Smirnov
Ailamazyan Program Systems Institute of RAS
Email: asmirnov\_1991@mail.ru
Igor Petrovich Tishchenko
Ailamazyan Program Systems Institute of RAS
Email: igor.p.tishchenko@gmail.com
References
- Bromley J., Guyon I., LeCun Y., Säckinger E., Shah R.. “Signature verification using a ‘Siamese’ time delay neural network”, Proceedings of the 6th International Conference on Neural Information Processing Systems, NIPS'93, Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, 1993, pp. 737–744.
- Livieris I. E., Pintelas E., Kiriakidou N., Pintelas P.. “Explainable image similarity: integrating siamese networks and grad-CAM”, Journal of Imaging, 9:10 (2023).
- Valero-Mas J. J., Gallego A. J., Rico-Juan J. R.. “An overview of ensemble and feature learning in few-shot image classification using siamese networks”, Multimedia Tools and Applications, 83:7 (2024), pp. 19929–19952.
- Понамарёв В. В., Китов В. В., Китов В. А.. «Учёт иерархии классов при классификации объектов с помощью сиамских нейронных сетей», Прикладная математика и информатика, 2023, №73, с. 38–57.
- Byung-Rae C., Binod V.. “Enhancing human activity recognition with siamese networks: a comparative study of contrastive and triplet learning approaches”, Electronics, 13:9 (2024), pp. 1739.
- Qiqi Z., Sai W., Shun T., Liangbin Y., Kunlun Q., Qingfeng G.. “RockS$^2$Net: Rock image classification via a spatial localization siamese network”, Computers & Geosciences, 185 (March 2024), 105560.
- Abady L., Wang J., Tondi B., Barni M.. “A siamese-based verification system for open-set architecture attribution of synthetic images”, Pattern Recognition Letters, 180 (April 2024), pp. 75–81.
- Lingxia L., Ju-Song K., Fanju M., Miao Y.. “Non-intrusive load identification based on retrainable Siamese network”, Sensors, 24:8 (2024).
- Contreras J., Mostafapour S., Popp J., Bocklitz T.. “Siamese networks for clinically relevant bacteria classification based on Raman spectroscopy”, Molecules, 29:5 (2024).
- Zhenzhen Y., Botao H., Zhenghao S., Minghua Z., Shuangli D., Haiqin L., Xinhong H., Xiaoyong R., Yan Y.. “Vocal cord leukoplakia classification using Siamese network under small samples of white light endoscopy images”, Otolaryngology–Head and Neck Surgery, 170:4 (2024), pp. 1099–1108.
- Polsinelli M., Li H. B., Mignosi F., Zhang L., Placidi G.. “Siamese network to assess scanner-related contrast variability in MRI”, Image and Vision Computing, 145 (May 2024), 104997.
- Ranjan P., Girdhar A.. “Deep Siamese network with handcrafted feature extraction for hyperspectral image classification”, Multimedia Tools and Applications, 83:1 (2024), pp. 2501–2526.
Supplementary files
