In the previous chapter, we learned about object classification and how machine learning can be used to achieve it. In this chapter, we will learn how to detect and track different face parts. We will start the discussion by understanding the face detection pipeline and how it's built from the ground up. We will then use this framework to detect face parts, such as eyes, ears, mouth, and nose. We will then learn how to overlay funny masks on these face parts in a live video.
In this chapter, we will cover the following topics:
Working with Haar cascades
Integral images and why we need them
Building a generic face detection pipeline
Detecting and tracking face parts, such as eyes, ears, nose, and mouth in a live video stream from the webcam
Automatically overlaying facemasks, sunglasses, and a funny nose on a person's face in a video