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{200708,
        author = {Minal Toley and Sankalp Ambre and Chaitanya Alande and Purushottam Kshirsagar},
        title = {Handwritten Document Digitizer (OCR + Classifier)},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {2765-2780},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=200708},
        abstract = {The increasing reliance on handwritten documents in educational institutions, government offices, healthcare systems, and financial organizations creates challenges in data storage, retrieval, and processing. Manual transcription of handwritten records into digital format is time-consuming, error-prone, and inefficient. To address these limitations, this project presents an AI-based Handwritten Document Digitizer that combines Optical Character Recognition (OCR) and Machine Learning classification techniques to convert handwritten content into structured digital text.
The proposed system captures handwritten document images and applies image preprocessing techniques such as grayscale conversion, noise reduction, thresholding, and segmentation to enhance text clarity. An OCR engine is then used to extract textual content from the processed image. To further improve accuracy and organization, a classification model is integrated to categorize recognized content into predefined classes such as letters, numbers, or document types. This dual approach ensures both accurate text recognition and intelligent categorization of documents.
The entire solution is designeddesigned in Python, incorporating OpenCV to manage image-related tasks, Tesseract OCR to convert visual text into digital format, and deep learning algorithms to categorize the processed data effectively. Data augmentation and preprocessing strategies are incorporated to improve recognition accuracy under varying handwriting styles and image conditions.
Experimental evaluation demonstrates reliable performance in digitizing handwritten content with satisfactory accuracy. The developed solution reduces manual workload, enhances data accessibility, and enables efficient digital archiving. The project highlights the practical application of artificial intelligence in document automation and demonstrates how OCR integrated with classification models can support real-world digitization systems.},
        keywords = {Optical Character Recognition, Handwritten Text Recognition, Machine Learning, Document Classification, Image Processing, Artificial Intelligence.},
        month = {May},
        }