Copyright © 2026 Authors retain the copyright of this article. This article 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.

@article{184242,
        author = {Dr.Sunith GP and Preethi R and santhosh SG},
        title = {Handwritten Content Recognition and Text Transformation Using Machine Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {4},
        pages = {728-735},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=184242},
        abstract = {The manual evaluation of mixed-format response sheets is inefficient and lacks consistency when conducted on a large scale. This study introduces a CPU-efficient system that integrates OpenCV-based optical mark recognition for multiple-choice questions, EasyOCR with SymSpell correction for text extraction, and a rubric-aligned big language model to allocate numeric scores to descriptive responses. The tool, developed in Flask with role-based access, generates annotated overlays and downloadable reports, facilitating transparent audits without the need for GPUs. Pilot tests on diverse scan characteristics demonstrate dependable MCQ detection and substantial concordance with teacher evaluations, resulting in expedited turnaround and enhanced scoring uniformity.},
        keywords = {OpenCV, Optical Mark Recognition, OCR, EasyOCR, SymSpell, Flask, Large Language Model, Automated Grading, Educational Technology, Image Processing, Contour-based Detection, Spell Correction.},
        month = {September},
        }