The Google Developers page defines face detection as the process of automatically locating and detecting human faces in visual media (digital images or video). The detected face is reported at a position with an associated size and orientation. After the face is detected, we can search for landmarks present in the face such as the eyes and nose.

Here are some important terms to understand before we can move on to programming face detection with ML Kit:

• Face Orientation: Detects faces at a range of different angles.
• Face Recognition: Determines whether two faces can belong to the same person.
• Face Tracking: Refers to detecting faces in videos.
• Landmark: Refers to a point of interest within a face. This corresponds to the notable features on a face, such as the right eye, left eye, and nose base.
• Classification: Determines the presence of facial characteristics, such as open or closed eye or a smiling or serious face.