Add reinhard color normalization support #25
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Closed
andreped
changed the title
|
Note that I also added TF support now, as I need it for one of my studied. Will not have time for PyTorch any time soon, but at least both Numpy and TF backends work as intended. |
|
Thanks for the contribution! Merging it now |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
I have added support for reinhard color normalization, as an alternative to Macenko, as discussed in #24.
Reinhard itself was straight forward to implement, but I had a hard time getting the RGB/LAB color converters to work as intended. After looking at what OpenCV, Scikit-Image, and other projects were doing, I managed to implement numpy-equivalents. In the end, from qualitative assessment, I get the same results as another commonly used library, StainTools.
Have not had the time to benchmark it yet, hence,
experimental, but at least it runs and serves as an alternative method.UPDATE: Now both Numpy and TensorFlow backends are supported!
What's changed:
ReinhardNormalizer- currently supports both numpy and tensorflow backends.rgb2labandlab2rgbcolor conversion implementations.statsandsplit.experimental Reinhard supportwith reference to original article.result.pngtodata/directory and updated corresponding path in README.