Applied Machine Learning and AI for Engineers

Chapter 11. Face Detection and Recognition

Not long ago, I boarded a flight to Europe and was surprised that I didn’t have to show my passport. I passed in front of a camera and was promptly welcomed aboard the flight. It was part of an early pilot for Delta Air Lines’ effort to push forward with facial recognition and offer a touchless curb-to-gate travel experience.

Facial recognition is everywhere. It’s one of the most common, and sometimes controversial, applications for AI. Meta, formerly known as Facebook, uses it to tag friends in photos—at least it did until it killed the feature due to privacy concerns. Apple uses it to allow users to unlock their iPhones, while Microsoft uses it to unlock Windows PCs. Uber uses it to confirm the identity of its drivers. Used properly, facial recognition has vast potential to make the world a better, safer, and more secure place.

Suppose you want to build a system that identifies people in photos or video frames. Perhaps it’s part of a security system that restricts access to college dorms to students and staff who are authorized to enter. Or perhaps you’re writing an app that searches your hard disk for photos of people you know. (“Show me all the photos of me and my daughter.”) Building systems such as these requires algorithms or models capable of:

• Finding faces in photos or video frames, a process known as face detection

• Identifying the faces detected, a process known as facial recognition or face identification

Numerous well-known ...