Welcome to Pixels → Perception

This site is a computer vision course you can read in order or dip into. It starts with images as arrays of numbers and builds up to modern deep networks.

How it is organized

The Learn section has five tracks: Foundations, Image Processing, Classical Computer Vision, Machine Learning for Vision, and Deep Learning. Each tutorial lists its prerequisites, so you can always see what to read first.

Running the code

Every tutorial with code has a matching Jupyter notebook. Click Open in Colab at the top of the page to run it in your browser with no setup.

The blog, where this post lives, is for everything outside the curriculum: paper notes, tool reviews and longer essays.