Enhancing Container Number Recognition Accuracy through Multi-Model OCR Comparison and Post-Processing

Anakorn Roumpattana; Chalothon Chootong; Boonchoo Jitnupong; Sarut Serarom; Jirawan Charoensuk

doi:10.46604/aiti.2026.15750

Authors

Anakorn Roumpattana Department of Computer Science and Information, Faculty of Science at Sriracha, Kasetsart University, Chonburi, Thailand
Chalothon Chootong Department of Computer Science and Information, Faculty of Science at Sriracha, Kasetsart University, Chonburi, Thailand
Boonchoo Jitnupong Department of Computer Science and Information, Faculty of Science at Sriracha, Kasetsart University, Chonburi, Thailand
Sarut Serarom KLN Seaport Limited, Chonburi, Thailand
Jirawan Charoensuk Department of Computer Science and Information, Faculty of Science at Sriracha, Kasetsart University, Chonburi, Thailand

DOI:

https://doi.org/10.46604/aiti.2026.15750

Keywords:

optical character recognition, PaddleOCR, container number recognition, horizontal text alignment

Abstract

Extracting container numbers from moving trucks in seaports remains challenging. This study aims to evaluate and compare the performance of optical character recognition (OCR) technologies, including EasyOCR, PaddleOCR, TesseractOCR, and TrOCR, for container number recognition in CCTV-based surveillance systems. The evaluation considers both horizontal and vertical text orientations with three-character categories: alphanumeric, alphabetic, and numeric. The results indicate that horizontal text recognition significantly outperforms vertical text recognition across all models and character categories. In experiments with alphanumeric container number formats, PaddleOCR and TrOCR achieve initial character error rates (CER) of 3.82% and 1.64% within 5.19 and 12.32 seconds, respectively. After applying post-processing rules, the CER is reduced to 0.36% for both models. PaddleOCR obtains comparable accuracy to TrOCR while offering a faster processing speed (7.78 seconds). Considering both recognition accuracy and processing time, PaddleOCR demonstrates an efficient performance for horizontal container number detection in seaport environments.

References

M. Yu, S. Zhu, B. Lu, Q. Chen, and T. Wang, “A Two-Stage Automatic Container Code Recognition Method Considering Environmental Interference,” Applied Sciences, vol. 14, no. 11, article no. 4779, 2024.

R. Shetty, R. Cáceres, J. Pastrana, and L. Rabelo, “Optical Container Code Recognition and Its Impact on the Maritime Supply Chain,” Proceedings of the Industrial and Systems Engineering Research Conference, Orlando, Florida, USA, pp. 1535-1544, 2012.

C. Tang and P. Chen, “Container Number Recognition Method Based on SSD_MobileNet and SVM,” American Scientific Research Journal for Engineering, Technology, and Sciences, vol. 74, no. 1, pp. 200-211, 2020.

JaidedAI, “EasyOCR,” https://github.com/JaidedAI/EasyOCR, accessed in 2024.

J. K. Coching, A. J. L. Pe, S. G. D. Yeung, C. M. L. Ang, R. S. Concepcion, and R. K. C. Billones, “License Plate Recognition System for Improved Logistics Delivery in a Supply Chain with Solution Validation through Digital Twin Modeling,” IEEE 15th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM), Coron, Palawan, Philippines, 2023.

D.-D. Ngo, V.-H.-A. Phan, H.-T. Pham, T.-T. Be, V.-B. Nguyen, and M.-H. Le, “A Vision-Based Container-Code Checking System: Case Study at International Terminal,” 2023 International Workshop on Intelligent Systems (IWIS), Ulsan, Republic of Korea, 2023.

Y. Du, C. Li, R. Guo, X. Yin, W. Liu, J. Zhou, et al., “PP-OCR: A Practical Ultra Lightweight OCR System,” arXiv preprint, arXiv:2009.09941, 2020.

Y. Du, Z. Chen, C. Jia, X. Yin, T. Zheng, C. Li, et al., “SVTR: Scene Text Recognition with a Single Visual Model,” arXiv preprint, arXiv:2205.00159, 2022.

R. K. Prajapati, T. Nagar, S. Dangi, Y. Bhardwaj, P. R. S. Rao, and R. K. Jain, “Automatic Number Plate Recognition Using YOLOv7 and PaddleOCR,” International Journal of Advanced Research in Science, Engineering and Technology, vol. 10, Special Issue 2, pp. 26-32, 2023.

M. Fabijanić, M. Magdalenić, J. Obradović, N. Kapetanović, F. Ferreira, and N. Mišković, “Vessel Registration Number Detection and Recognition System,” Proceedings of IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW), IEEE Press, pp. 1450-1456, 2025.

R. Smith, “An Overview of the Tesseract OCR Engine,” Proceedings of the 9th International Conference on Document Analysis and Recognition (ICDAR), IEEE Press, pp. 629-633, 2007.

I. N. T. Lestari and D. I. Mulyana, “Implementation of OCR (Optical Character Recognition) Using Tesseract in Detecting Character in Quotes Text Images,” Journal of Applied Engineering in Technological and Science (JAETS), vol. 4, no. 1, pp. 58-63, 2022.

S. M. Shithil, A. R. M. Kamil, S. Tasnim, and A. A. M. Faudzi, “Container ISO Code Recognition System Using Multiple View Based on Google LSTM Tesseract,” Proceedings of Computational Intelligence in Machine Learning, Springer, pp. 433-440, 2022.

M. Li, T. Lv, J. Chen, L. Cui, Y. Lu, D. Florencio, C. Zhang, et al., “TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models,” Proceedings of the AAAI Conference on Artificial Intelligence, pp. 13094-13102, 2023.

H. Zhang, E. Whittaker, and I. Kitagishi, “Extending TrOCR for Text Localization-Free OCR of Full-Page Scanned Receipt Images,” Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), IEEE Press, pp. 1471-1477, 2023.

R. L. Zhang, “A Comprehensive Evaluation of TrOCR with Varying Image Effects,” National High School Journal of Science, pp. 1-10, 2024.

R. Khanam and M. Hussain, “YoLov11: An Overview of the Key Architectural Enhancements,” arXiv preprint, arXiv:2410.17725, 2024.