Skip to content
No description, website, or topics provided.
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.


Color Me Impressed


This project was an extension of the work I read in this blogpost It's a series of funcitons that batch analysze tiffs and then

note : These functions always run faster on smaller images. To save yourself someheadache scale down the images before you run them by using the sip command in bash.

Simply navigate to the image folder and execute:

sips -Z 100 *.jpg

This will generally preserve the colors but scale everything down.

Getting the data

I used instalooter to collect data but any scraping service that allows you to collect large amounts of images should work.

Analyszing one image

The function takes two arguments: the location of the image and the number of color to extract

python3 %PathToImage% n

As an example of n=5, we see this function will generate an output like this:


Batch Analysis

To find the primary colors in a series of images you can call the following function

python3 %PathToImageDirectory% n

This will save a pickled python list of lists called "storage.pkl" containing the "n" most promoinent colors for each image in the directory.


To generate unique radial plots using the extracted data you can simple run the function:


This will load "storage.pkl" and generate a smoothed radial histogram based on the hues of the scraped images. *note: * There are many ways to visulaize distributions of color, here we simply discard black and white and look at the predominance of the colors of the rainbow. girl

You can’t perform that action at this time.