Detection of Expiration Dates in Product Images Using YOLO

• Lucas Andreotti PUCRS
• Lucas M. Fraga PUCRS
• Rodrigo C. Barros PUCRS
• Lucas S. Kupssinskü PUCRS

DOI: https://doi.org/10.5753/eramiars.2025.16690

Resumo

Accurate identification of expiration dates on product packaging is essential to prevent the consumption of expired goods, reduce waste, and improve inventory management. This study proposes a YOLO-based neural network model for automatic detection of expiration dates in product packaging images. A dataset containing 668 images of Brazilian product packages was created, annotated, and made publicly available for training and evaluation purposes. Our fine-tuned YOLO achieved a precision of 0.804 and an F1-score of 0.812, indicating promising results for expiration date detection.

Referências

ABRAS (2022). A eficiência dos supermercados. Accessed on May 2025, available in [link].

Gong, L., Thota, M., Yu, M., Duan, W., Swainson, M., Ye, X., and Kollias, S. (2021). A novel unified deep neural networks methodology for use by date recognition in retail food package image. Signal, Image and Video Processing, 15.

Hosozawa, K., Wijaya, R., Linh, T., Seya, H., Arai, M., Maekawa, T., and Mizutani, K. (2018). Recognition of expiration dates written on food packages with open source ocr. International Journal of Computer Theory and Engineering, 10:170–174.

Rebedea, T. and Florea, V. (2020). Expiry date recognition using deep neural networks. International Joural of User-System Interaction, 13:1–17.

Scazzoli, D., Bartezzaghi, G., Uysal, D., Magarini, M., Melacini, M., and Marcon, M. (2019). Usage of hough transform for expiry date extraction via optical character recognition. In 2019 Advances in Science and Engineering Technology International Conferences (ASET), pages 1–6.

Seker, A. C. and Ahn, S. C. (2022). A generalized framework for recognition of expiration dates on product packages using fully convolutional networks. Expert Systems with Applications, 203:117310.