1. КК
  2. All Volumes and Issues
  3. № 2 (48) / 2025
  4. Overview of Computer Vision Technologies for Product Labeling

Overview of Computer Vision Technologies for Product Labeling

КК.
2025;
Volume 48, Number 2
: pp. 55 - 61
https://doi.org/10.32403/2411-3611-2025-2-48-55-61
Authors:
  1. R. S. Zatserkovna
  2. R. H. Zatserkovnyi
  3. V. O. Stepanets
1
Lviv Polytechnic National University
2
Lviv University of Trade and Economics
3
Lviv Polytechnic National University

In today’s world of globalized trade and e­commerce, product labeling is becoming increasingly important. It ensures product traceability throughout the supply chain, provides information and protection, and influences consumer confidence. Traditional methods of checking and reading labels are based on manual control or the use of simple barcode scanners, which often prove ineffective in conditions of increasing data processing volumes.
The issue of marking automation is particularly relevant for the food and phar­maceutical industries, where inaccuracies in data reading can lead to serious risks to consumer health. The use of computer vision technologies can significantly improve the accuracy and speed of information processing, reduce the negative impact of the human factor, and integrate labeling with digital quality control systems.
In this context, there is a need for a comprehensive analysis of modern tools and approaches that automate the processes of reading and verifying product labeling using computer vision algorithms.
In this paper, computer vision technologies used for automated product labeling are discussed. The essence of optical character recognition (OCR) technologies, barcode and QR code reading, and print quality control systems are outlined. An overview of open libraries (Tesseract, EasyOCR, OpenCV), cloud services (Google Vision API, AWS Textract), and tools for mobile applications is provided. The advantages and di­sadvantages of using these solutions in logistics, retail, and manufacturing are described.

product labeling
computer vision
OCR
QR codes
  1. Smith, R. “An Overview of the Tesseract OCR Engine.” ICDAR, 2007. https://research. google.com/pubs/archive/33418.pdf.
  2. JaidedAI. “EasyOCR (GitHub repository).” https://github.com/JaidedAI/EasyOCR.
  3. ZXing Project. “ZXing: Multi-format 1D/2D barcode image processing library (GitHub).” https://github.com/zxing/zxing.
  4. OpenCV Team. “Image Processing (imgproc module) — OpenCV Docs.” https://docs.opencv. org/4.x/d7/dbd/group    imgproc.html.
  5. Meta AI Research. “Detectron2 — A platform for object detection and segmentation.” https:// ai.meta.com/tools/detectron2/.
  6. AIA / Automate.org. “Machine Vision on Packaging Lines.” https://www.automate.org/ vision/industry-insights/machine-vision-on-packaging-lines.
  7. EPIC Systems. “Would High Speed OCR Label Inspection Work For Your Products?” https:// epicsysinc.com/blog/high-speed-label-inspection/.
  8. Oucheikh, R., et al. “Product verification using OCR classification and Mondrian conformal prediction.” Expert Systems with Applications, 2022. https://www.sciencedirect.com/science/ article/pii/S0957417421012963.
  9. Pettersson, T.; Riveiro, M.; Löfström, T. “Multimodal fine-grained grocery product recognition using image and extracted OCR text.” Machine Vision and Applications, 2024. https://link. springer.com/article/10.1007/s00138-024-01549-9.
  10. GS1. “GS1 Digital Link — Standardised web-enabled identifiers.” https://www.gs1.org/ standards/gs1-digital-link.