Orclever Proceedings of Research and Development

Development of a Price Tag Detection System on Mobile Devices using Deep Learning

Melek Turan

Özdilek Özveri R&D Center

https://orcid.org/0000-0002-1873-4980

Musa Peker

Özdilek Özveri R&D Center

https://orcid.org/0000-0002-1445-7410

Hüseyin Özkan

Özdilek Özveri R&D Center

https://orcid.org/0000-0003-4169-4259

Cevat Balaban

Özdilek Özveri R&D Center

https://orcid.org/0000-0002-5165-3082

Nadir Kocakır

Özdilek Özveri R&D Center

https://orcid.org/0000-0001-7421-0631

Önder Karademir

Özdilek Özveri R&D Center

https://orcid.org/0000-0001-5757-7335

DOI: https://doi.org/10.56038/oprd.v1i1.174

Keywords: Price tag detection, Deep learning, Object detection, Intelligence applications

---

Abstract

Ensuring customer satisfaction is an important issue in the retail industry. The way to achieve this satisfaction is to provide a quality service. The data on the price tags on the product shelves are frequently updated. These data should be included on the price tags in their current form. Customers may encounter inaccurate information on price tags in shopping places, which causes negative results in terms of customer loyalty and satisfaction. The data on the price tags is mostly checked manually, which can cause human errors. In this study, a deep learning-based solution is proposed for fast and high accuracy detection of price tag area. One of the first and important stages of a deep learning-based price recognition system is the correct detection of the price tag area. The successful execution of this stage is important for the successful execution of the next processes (barcode reading, price reading). The proposed method has been tested on mobile phones. It is envisaged that the proposed method is applicable in its current form and can be a technical reference for similar problems in the retail industry.

---

References

Allegro Logistics (2022), Are digital price tags worth the hype ?, https://www.allegrologistics.co.uk/, Erişim Tarihi: 15.10.2022

Fomenko, V., Botov, D., & Klenin, J. (2018). Text scene detection with transfer learning in price detection task. in 7th International Conference on. Analysis of Images, Social Networks, and Texts (AIST), pp. 173-178, Moscow, Russia.

Hussin, M.N.A., Ahmad, A.H., & Razak, M.A. (2017). Price tag recognition using HSV color space. Journal of Telecommunication, Electronic and Computer Engineering, 9(3-9), 77-84.

Kovtunenko, A., Yakovleva, O., Liubchenko, V., & Yanholenko, O. (2020). Research of the joint use of mathematical morphology and convolutional neural networks for the solution of the price tag recognition problem. Bulletin of National Technical University KhPI Series System Analysis Control and Information Technologies. 1, 24–31. DOI: https://doi.org/10.20998/2079-0023.2020.01.05

Laptev, P., Litovkin, S., Davydenko, S., Konev, A., Kostyuchenko, & E., Shelupanov, A. (2022). Neural network-based price tag data analysis. Future Internet, 14(3), 1-14. DOI: https://doi.org/10.3390/fi14030088

Qian, Y., Miao, Y., Huang, S., Qiao, X., Wang, M., Li, Y., ... & Cao, L. (2022). Real-Time Detection of Eichhornia crassipes Based on Efficient YOLOV5. Machines, 10(9), 754. DOI: https://doi.org/10.3390/machines10090754

Tan, M., & Le, Q. (2019). Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning pp. 6105-6114, PMLR.

TensorFlow, Tensorflow Object Detection API, https://github.com/tensorflow/models/tree/master/research/object_detection, Erişim Tarihi: 15.10.2022.