The idea is to create an application that takes images then;
- Remove the noises,
- Detect edges of the papers,
- Crop as per the image and transform the image to make it flat paper,
- Apply filters or image transformations techniques,
- Convert image to the PDF,
- Enrich the PDF using OCR,
- If possible, do this for multiple images and then merge into a single file.
2025-10-13.00-51-25.mp4
- Read, display and transfrom images and videoes
read.py - Draw geometric shapes with OpenCV. Created logo using shapes.
drawing_functions.py - Optimization and measuring performance. OpenCV 12.0 Docs
- Learn about masking and color tracking
tracking-color.py