A simple command-line interface for image enhancement and color balancing.
This application is being developed mainly to play with a few algorithms that I like. I am aiming at making the implementations work for 2D, 3D and 4D images. Currently implemented algorithms are:
- Multi-scale retinex [1, 3]
- Simplest color balance [2]
- Simplex color balance (based on [3, 4], not published)
Python 3 and the following packages:
| Package | Tested version |
|---|---|
| OpenCV | 3.4.4 |
| SciPy | 1.2.0 |
| NiBabel | 2.2.1 |
| NumPy | 1.15.4 |
Clone this repository or download the latest release. In your command line, change directory to folder of this package and run the following:
python setup.py install
If everything went fine, typing iphigen -h or iphigen_nifti -h in the command-line should show the help menu now.
iphigen /path/to/image.png --retinex --intensity_balance
iphigen /path/to/image.png --simplest_color_balance
iphigen /path/to/image.png --retinex --simplest_color_balance
iphigen_nifti /path/to/data.nii.gz --retinex
See script examples here.
Please use github issues to report bugs or make suggestions.
The project is licensed under BSD-3-Clause.
This application is based on the following work:
-
Jobson, D. J., Rahman, Z. U., & Woodell, G. A. (1997). A multiscale retinex for bridging the gap between color images and the human observation of scenes. IEEE Transactions on Image Processing, 6(7), 965–976. http://doi.org/10.1109/83.597272
-
Limare, N., Lisani, J., Morel, J., Petro, A. B., & Sbert, C. (2011). Simplest Color Balance. Image Processing On Line, 1(1), 125–133. http://doi.org/10.5201/ipol.2011.llmps-scb
-
Petro, A. B., Sbert, C., & Morel, J. (2014). Multiscale Retinex. Image Processing On Line, 4, 71–88. http://doi.org/10.5201/ipol.2014.107
-
Gulban, O. F. (2018). The Relation between Color Spaces and Compositional Data Analysis Demonstrated with Magnetic Resonance Image Processing Applications. Austrian Journal of Statistics, 47(5), 34–46. http://doi.org/10.17713/ajs.v47i5.743