A basic document scanner that scans an image an produces a better readable form of it,using OpenCV and Python
- General Info
- Installing and running the project on local machine
- Libraries Used
- End Product
- References
A document scanner can be build using basic image processing techniques, inorder to achieve the result
Usually the process takes only three main process:-
- Detect the edge
- Use the edges in the image to find the contour (outline) representing the piece of paper being scanned.
- Apply a perspective transform to obtain the top-down view of the document.
Clone the project
git clone https://github.com/vipuljain-17/Document_Scanner_OpenCV.git
Go to the project directory
cd Document_Scanner_OpenCV
Run the shell script to install required packages and start the program.
./run.sh
- If you face any permission errors while running the shell script. Write the given code.
This provides you with the execution rights in order to run the script.
chmod +x run.sh
Or, Just click on the run.sh file!
- OpenCV
- Python3
- Scikit-image
- Tkinter
- PIL
I have added an scanned result.
This could have not possible without the help of pyimagesearch and Pysource