https://github.com/diging/innogen-script
Python script to extract images from scanned documents using OpenCV
https://github.com/diging/innogen-script
Last synced: 17 days ago
JSON representation
Python script to extract images from scanned documents using OpenCV
- Host: GitHub
- URL: https://github.com/diging/innogen-script
- Owner: diging
- Created: 2022-10-25T18:02:46.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2022-10-25T21:34:07.000Z (over 3 years ago)
- Last Synced: 2025-02-28T18:46:40.230Z (over 1 year ago)
- Language: Jupyter Notebook
- Size: 4.88 KB
- Stars: 0
- Watchers: 2
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
## Extract images from Scans
This script uses OpenCV to find and extract images from scans. To run, clone repo, and then build and run the Docker container.
For example, if your image is in a subfolder `images`:
```
docker build -t extract_imgs .
docker run --mount type=bind,source="$(pwd)",target=/data extract_imgs -f /data/images/file.jpg -o /data/images/extracted/
```
The extracted images will be in `images/extracted/extracted`.
The build step will take quite a bit of time, while OpenCV is being built.