Computer Vision with JavaScript and p5.js

Kyle McDonald

“Computer Vision” refers to a broad collection of techniques that allow computers to make intelligent assertions about what’s going on in digital images and video. Sometimes this means understanding the difference between an image of someone smiling and frowning, or something as low level as whether there is motion in front of a camera. Participants will be introduced to a brief history of computer vision and its relationship to media arts, but most of the time will be spent learning how to work with computer vision frameworks for JavaScript: jsfeat for pixel manipulation, optical flow and object detection, and clmtrackr for understanding faces. Both computer vision classes will cover similar material with different toolkits, and students are welcome to take one or both. Before taking this class, students should have written JavaScript for at least one semester.