ScoreSync: Automated Mark Entry App using Image Capture with Computer Vision and Optical Character Recognition
DOI:
https://doi.org/10.11113/ijic.v16n1-2.703Keywords:
Automated score transfer, Computer vision, Optical Character Recognition (OCR), YOLOv8, Mobile Application, Machine LearningAbstract
Traditional score recording, whereby educators manually key in scores in their respective education hubs, is time-consuming and susceptible to error when the volume of papers is high. To address this, ScoreSync, an automated mark entry app, was developed to streamline the grading and recording process by leveraging computer vision and machine learning. The primary objective is to develop an application capable of capturing images of exam papers using a lens or phone camera, ensuring a clear and accurate representation of score sheets. This would not only reduce an educator’s administrative burdens but also improve data accuracy and efficiency. Created to be applied by Android devices, ScoreSync captures images of graded papers and extracts scores through Optical Character Recognition (OCR) guided by YOLOv8, a Convolutional Neural Network (CNN) model optimised for bounding box detection. Developed through a Rapid Development Model, the app has been through multiple refines when it comes to the Artificial Intelligence (AI) model, transitioning from TensorFlow to PyTorch for greater flexibility and accuracy. The initial build of the ScoreSync is solely for the purpose of extracting graded papers of any kind, with results ranging from 80% to 90% in terms of detecting the scores in the exam sheets. Future improvements include expanding compatibility across platforms, refining the model adaptability towards different exam paper styles, and a setup that would aid the software when a live-capture solution is implemented, which would minimise more time spent rather than having the educators snap each exam sheet.
References
Revolutionizing data entry: An in-depth study of optical character recognition technology and its future potential. International Journal for Research in Applied Science and Engineering Technology, 11(2), 645–653. https://doi.org/10.22214/ijraset.2023.49108
Koushik, K. S., Sourav, C., & Chendan, R. P. (2022). Automated marks entry processing in handwritten answer scripts using character recognition techniques. In Proceedings of the International Conference (pp. 728–733). Retrieved from https://ieeexplore.ieee.org/document/9885493
Logeshvar, L., Premnath, A. B., Geethan, R., & Suganya, R. (2021). AI-based examination assessment mark management system. In International Conference on Secure Cyber Computing and Communications (pp. 144–149). Retrieved from https://ieeexplore.ieee.org/document/9478091
Sun, M., Song, Z., Jiang, X., Pan, J., & Pang, Y. (2017). Learning pooling for convolutional neural network. Neurocomputing, 224, 96–104. Retrieved from https://www.sciencedirect.com/science/article/abs/pii/S0925231216312905
Subasri, R., & Meenakumari, R. (2023). AI-based automatic mark entry system. Retrieved from https://openreview.net/forum?id=-eCgVcWbnzE
Jayoma, J. M., Moyon, E. S., & Morales, E. M. O. (2021). OCR-based document archiving and indexing using PyTesseract: A record management system for DSWD Caraga, Philippines. In 2020 IEEE 12th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM). https://doi.org/10.1109/HNICEM51456.2020.9400000
Salehudin, M. A. M., Basah, S. N., Yazid, H., Basaruddin, K. S., Safar, M. J. A., Mat Som, M. H., & Sidek, K. A. (2023). Analysis of optical character recognition using EasyOCR under image degradation. In 8th International Conference on Man Machine Systems 2023. Journal of Physics: Conference Series, 2641(1), 012001. https://doi.org/10.1088/1742-6596/2641/1/012001
Levchenko, M. (2025). Evaluating LLMs for historical document OCR: A methodological framework for digital humanities (arXiv Preprint). Retrieved from https://arxiv.org/abs/2510.06743
Mansoor, K., & Olson, C. F. (2019). Recognizing text with a CNN. In International Conference on Image and Vision Computing New Zealand (pp. 1–6). Retrieved from https://ieeexplore.ieee.org/document/8961031
Lim, L. G., Suhaila, B. H., & Norashikin, Y. (2014). Automatic assessment mark entry system using local binary pattern (LBP). In IEEE International Conference on Control System, Computing and Engineering (pp. 372–377). Retrieved from https://ieeexplore.ieee.org/document/7072747
Zafar, A., Aamir, M., Mohd Nawi, N., Arshad, A., Riaz, S., Alruban, A., Dutta, A. K., & Almotairi, S. (2022). A comparison of pooling methods for convolutional neural networks. Applied Sciences, 12(17), 8643. https://doi.org/10.3390/app12178643
Reis, D., Kupec, J., Hong, J., & Daoudi, A. (2023). Real-time flying object detection with YOLOv8 (arXiv Preprint). https://doi.org/10.48550/arXiv.2305.09972
Downloads
Published
Issue
Section
License
Copyright (c) 2026 International Journal of Innovative Computing
This work is licensed under a Creative Commons Attribution 4.0 International License.
