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 640440 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


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).