2025
doi: 10.12720/jait.16.6.777-785
A YOLOv10-Based System for Automated FPT University Student Card Information Extraction
Toan Quy Nguyen*
,
Tuan Minh Le ,
Linh Van Nguyen ,
Phuc Hoang Minh Lai ,
Khang Vo Hoang Nguyen ,
Thuan Van Tran ,
Thu Vo Minh Le
- Department of Information Technology, Faculty of Computer Science and Engineering, FPT University, Ho Chi Minh City, Vietnam
- Manuscript receivedNovember 17, 2024
- revisedDecember 25, 2024
- acceptedMarch 12, 2025
- publishedJune 5, 2025
Abstract
This paper presents a model for automated recognition and information extraction from student Identification cards (ID card). The model utilizes the You Only Look Once Version 10 (YOLOv10) model to identify student ID cards. Subsequently, the detected card is rotated to its correct orientation, and any unwanted black regions are removed using Tesseract. Precise cropping of the student ID card is then achieved by identifying the intersection points on its four edges. The cropped card is subsequently standardized to a resolution of 640440 pixels, and the region containing crucial information (name, student ID, and photo) is extracted and processed using Optical Character Recognition (OCR). This enables the efficient extraction and recognition of the necessary data from the student ID card. Following the research and model training process, the model’s accuracy reached 94.6%, leaving us highly satisfied with the research outcomes. In the future, this model holds the potential for widespread adoption by numerous schools to facilitate easier student management within the institution.
Keywords
- detect student ID card
- YOLOv10
- computer vision
- Optical Character Recognition (OCR)
- Tesseract
How to Cite
Toan Quy Nguyen, Tuan Minh Le, Linh Van Nguyen, Phuc Hoang Minh Lai, Khang Vo Hoang Nguyen, Thuan Van Tran, and Thu Vo Minh Le, "A YOLOv10-Based System for Automated FPT University Student Card Information Extraction," Journal of Advances in Information Technology, vol. 16, no. 6, pp. 777-785, 2025. https://doi.org/10.12720/jait.16.6.777-785
Copyright & License
Copyright © 2025 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
