Edge-Native Digitization of Handwritten Marksheets: A Hybrid Heuristic-Deep Learning Framework
Published in 2026 IEEE 2nd International Conference on Quantum Photonics, Artificial Intelligence & Networking (QPAIN), 2026
This paper introduces a resource-efficient hybrid framework for digitizing structured handwritten documents, combining a heuristic OpenCV-based pipeline for table detection with a modified lightweight YOLOv8 for handwritten character recognition.
Recommended citation: Md. Irtiza Hossain, Junaid Ahmed Sifat, Abir Chowdhury, and Md. Imran Bin Azad. (2026). "Edge-Native Digitization of Handwritten Marksheets: A Hybrid Heuristic-Deep Learning Framework." 2026 IEEE 2nd International Conference on Quantum Photonics, Artificial Intelligence & Networking (QPAIN), Chittagong, Bangladesh, pp. 1-6, doi: 10.1109/QPAIN69676.2026.11546582.
Download Paper
