Retinex algorithms for image enhancement
Project description
Retinex
Retinex algorithms for image enhancement. They are specially useful to process images with uneven illumination.
Still a work in progress. Next, I want to implement other techniques for color correction.
Installation
You may use pip to install retinex.
pip install retinex
Usage
Here is an example of how to use MSRCR (multi-scale retinex with color correction).
import skimage
from retinex import msrcr
img_original = skimage.io.imread("leaves.jpg")
img_msrcr = msrcr(img, sigmas=(25., 50., 100.,))
Check the examples
folder for some more samples:
Image credits
Images in the sample_images
folder were made freely available online by talented photographers. My big thanks to them:
- leaves.jpg: Photo by Rodion Kutsaiev on Unsplash
- man.jpg: Photo by Michael McAuliffe on Unsplash
- park.jpg: Photo by Oleg Lukin on Unsplash
- street.jpg: Photo by Ron Douglas on flickr
References
- Rahman, Z. U., Jobson, D. J., & Woodell, G. A. (2004). Retinex processing for automatic image enhancement. Journal of Electronic imaging, 13(1), 100-110.
Contributing
Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.
Please make sure to update tests as appropriate.
License
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.