A Deep Learning-Based Multi QR Code Detection System for Logistics Applications
Main Article Content
Abstract
The rapid growth of e-commerce has significantly increased parcel volumes in logistics operations, creating a demand for accurate and automated QR-code detection systems. Conventional QR-code scanning methods are often limited to single-code detection and may exhibit reduced performance in complex warehouse environments containing multiple parcels and cluttered backgrounds. This study proposes a deep learning–based multi-QR-code detection framework for logistics applications using a Region-based Convolutional Neural Network (R-CNN) integrated with VGG16 for feature extraction and a Support Vector Machine (SVM) for classification. The model was developed using a balanced dataset and enhanced through data augmentation techniques to improve learning capability and robustness under diverse operating conditions. For performance evaluation, the proposed framework was tested using real parcel images containing between one and ten QR codes per image, representing practical logistics scenarios. Experimental results demonstrated that the proposed framework achieved a QR-code detection accuracy of 95.82%, with a precision of 94.11%, a recall of 95.82%, and an F1-score of 94.96%. The framework maintained high detection performance even in images containing multiple parcels and complex backgrounds. These results indicate that the proposed framework is effective for multi-QR-code detection and can support automated parcel identification and tracking in warehouse and parcel management systems.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
The articles published are the opinion of the author only. The author is responsible for any legal consequences. That may arise from that article.
References
[1] Z. Zou, K. Chen, Z. Shi, Y. Guo, and J. Ye, “Object detection in 20 years: A survey,” Proceedings of the IEEE, vol. 111, no. 3, pp. 257–276, Mar. 2023, doi: 10.1109/JPR OC.2023.3238524.
[2] D. A. Noever and F. G. McKee, “Dueling QR codes: The hyding of Dr. Jeckyl,” arXiv:2503.13458, Feb. 2025, doi: 10.48550 /arXiv.2503.13458.
[3] M.-J. Tsai, Y.-C. Lee, and T.-M. Chen, “Implementing deep convolutional neural networks for QR code-based printed source identification,”Algorithms, vol. 16, no. 3, Mar. 2023, Art. no. 160, doi: 10.3390/ a16030160.
[4] L. Huo, J. Zhu, P. K. Singh, and P. A. Pavlovich, “Research on QR image code recognition system based on artificial intelligence algorithm,” Journal of Intelligent Systems, vol. 30, no. 1, pp. 855–867, Jan. 2021, doi: 10.1515/jisys-2020-0143.
[5] G. H. Girisha, A. D. Kumar, A. Singh, B. K. P., and Deepak, “QR Code detection," International Journal of Advanced Research in Science, Communication and Technology, pp. 357–360, Jun. 2022, doi: 10.48175/ijarsct-5353.
[6] V. Jain, Y. Jain, H. Dhingra, D. Saini, M. C. Taplamacioglu, and M. Saka, “A systematic literature review on QR code detection and pre-processing,”International Journal on Technical and Physical Problems of Engineering, vol. 13, no. 1, pp. 111–119, Mar. 2021.
[7] D. J. Corpuz, L. V. D. Rosario, J. P. Cempron, P. L. Lozano, and J. Ilao, “QR code detection with perspective correction and decoding in real-world conditions using deep learning and enhanced image processing,” in Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP), vol. 3, 2025, pp. 685–690, doi: 10.5220/00 13287200003912.
[8] C.-Q. Cao, B. Wang, W. Zhang, X. Zeng, X. Yan, Z.-J. Feng, Y. Liu, and Z. Wu, “An improved faster R-CNN for small object detection,” IEEE Access, vol. 7, pp. 106838–106846, 2019, doi: 10.1109/ACCESS.2019. 2932731.
[9] A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, “YOLOv4: Optimal speed and accuracy of object detection,” arXiv:2004.10934, 2020, doi: 10.48550/arXi v.2004.10934
[10] M. Rostan, “A comparative study on QR code and bar code detection techniques in modern systems,”International Journal of Synergy in Engineering and Technology, vol. 6, no. 1, pp. 14–22, 2025.
[11] M. Rostan and S. Safei, “Enhance efficiency of QR code detection on movement object: Performance analysis of algorithms and environmental factors,” International Journal of Synergy in Engineering and Technology, vol. 6, no. 1, pp. 51–62, 2025.
[12] F. Alsulami and N. Z. Jhanjhi, “Deep learning framework for barcode localization and decoding using simulated UAV imagery,” Scientific Reports, vol. 16, 2026, Art. no. 399, doi: 10.1038/s41598-025-29720-w.
[13] S.-Y. Yang, H.-C. Jan, C.-Y. Chen, and M.-S. Wang, “CNN-based QR code reading of package for unmanned aerial vehicle,” Sensors, vol. 23, no. 10, 2023, Art. no. 4707, doi: 10.3390/s23104707.
[14] A. A. Alsulami, Q. A. Al-Haija, B. Alturki, A. Yafoz, A. Alqahtani, R. Alsini, and S. S. Binyamin, "Efficient malicious QR code detection system using an advanced deep learning approach," Computer Modeling in Engineering & Sciences, vol. 145, no. 1, pp. 1117–1140, 2025, doi: 10.32604/cmes. 2025.070745.
[15] R. Chen, H. Huang, Y. Yu, J. Ren, P. Wang, H. Zhao, and X. Lu, "Rapid detection of multi-QR codes based on multistage stepwise discrimination and a compressed MobileNet," IEEE Internet of Things Journal, vol. 10, no. 18, pp. 15966–15979, Sep. 2023, doi: 10.1109/JIOT.2023.3268636.
[16] A. Sharif, G.-T. Zhai, X.-K. Min, J. Jia, and K. Munir, “Enhancing decoding rate of barcode decoders in complex scenes for IoT systems,” IEEE Internet of Things Journal, vol. 8, no. 24, pp. 17495–17507, Dec. 2021, doi: 10.1109/JIOT.2021.3081555.
[17] J. Li, D. Zhang, M. Zhou, and Z. Cao, “A motion blur QR code identification algorithm based on feature extracting and improved adaptive thresholding,” Neurocomputing, vol. 493, pp. 351–361, 2022, doi: 10.1016/j.neucom.2022.04.041.