How can we use k-Means to understand and/or manipulate photographic images? Here’s a classic example from the print world: choosing a few perfect inks for poster printing.
In this example, we reduce the mean calculation to just one dimension: the grayscale histogram from a specific photo.
“Photos have no narrative content. They only describe light on surface.” - GW
A follow-on to the last post on k-Means — this time, we use different criteria to determine “closeness” and to adjust where we move things around.
“Photography is about finding out what can happen in the frame. When you put four edges around some facts, you change those facts.” - Garry Winogrand
This is the first post in a brief series on simple algorithms I like, either becasue of their simplicty or novelty or usefullness or all three. Each with a live demo. To begin, I introduce a method that more programmers and artists should know about: k-Means Clustering .