A simple project to convert Devanagri text from hard copies into digital editable text
I developed an optical character recognition (OCR) project specifically designed to convert Devanagari script from hard copies into editable digital text. The project seamlessly integrates MATLAB for robust image processing capabilities, crucial for extracting text from scanned documents with varying quality and formats. Python was employed for training machine learning models and character recognition. This dual-language approach ensures accurate identification and translation of printed Devanagari characters into editable text, maintaining fidelity to the original document's format and layout. Ultimately, this project aims to advance the digitization of traditional texts, enhancing accessibility and preserving cultural and linguistic heritage effectively.
