A Python-based computer vision project that detects and extracts text from images using OpenCV. This project converts scanned or photographed documents into readable, editable digital text.
- Samruddhi Lakare
- Bhaktee Kalekar
- Spandan Kumkar
- Guided by: Mr. Solanke V. S.
Department of Computer Engineering, Marathwada Mitra Mandal’s Polytechnic, Pune, India
- Detects printed and handwritten text
- Can be used for reading out loud (TTS)
- Generates a short image description
- Uses OpenCV for image preprocessing
- Extracts text into readable formats (TXT, PDF etc.)
- Simple GUI for user interaction
- Can process multiple image formats (.jpg, .png, .jpeg)
- Python
- OpenCV
- Flask
- Tesseract OCR
- Numpy, Matplotlib
- Clone the repo
- Install dependencies
- Run the script
This project is copyright-protected under Indian copyright law.
© Samruddhi Lakare, Spandan Kumkar, Bhaktee Kalekar | All rights reserved
For collaborations or queries, contact via GitHub or lakaresamruddhi1@gmail.com