In a previous post I showed some of the beautiful new images of Pluto from New Horizon’s mission, coloured using the new Matplotlib perceptual colormaps:
More recently I was experimenting with Principal Component Analysis in scikit-learn, and one of the things I used it for was compression of some of these Pluto images. Below is an example of the first two components from the False Color Pluto image:
You can take a look at the Python code available on this Jupyter Notebook. There are of course better ways of compressing images, but this was a fun way to play around with PCA.
In a follow-up post I will use image registration and image processing techniques to reproduce from the raw channels NASA’s Psychedelic Pluto Image.
Pingback: Machine learning in geoscience and planetary science with scikit-learn: series outline | MyCarta