Computer vision seeks to acquire, process, and analyze digital images based on dimensional data to produce numerical decisions. Machine learning applies convolutional neural networks to classify, identify, and detect symbolic information from image data. The easiest way to decipher all of this and understand when to apply which technique to your application, is to attend this session.
Set against the backdrop of the capabilities of the browser, this interactive session compares and contrasts both approaches through two different applications. In the first, you will learn image processing and feature detection techniques to track, and solve, a Rubik’s Cube. In the second, you will learn to apply those techniques to build an object classifier for facial recognition. Sit in the front row at your own risk!
