Computer Vision Technologies
Face detection is a type of computer vision technology that is able to identify people’s faces within digital images. This is very easy for humans, but computers need precise instructions. The images might contain many objects that aren’t human faces, like buildings, cars, animals, and so on.
It is distinct from other computer vision technologies that involve human faces, like facial recognition, analysis, and tracking.
Facial recognition involves identifying the face in the image as belonging to person X and not person Y. It is often used for biometric purposes, like unlocking your smartphone.
Facial analysis tries to understand something about people from their facial features, like determining their age, gender, or the emotion they are displaying.
Facial tracking is mostly present in video analysis and tries to follow a face and its features (eyes, nose, and lips) from frame to frame. The most popular applications are various filters available in mobile apps like Snapchat.
All of these problems have different technological solutions. This course will focus on a traditional solution for the first challenge: face detection.
00:00 As we learned in the introduction, face detection is a type of computer vision technology used to identify faces in an image. It’s important to note that it finds only the presence of faces—meaning whether or not faces are actually there—and where they are.
00:18 It doesn’t actually look at facial features to draw any conclusions like age or gender. In this picture here, face detection would tell us that there are four faces.
00:29 The program doesn’t know if they are male or female or what age they are, but it can tell us the location of each of these four faces.
00:38 Facial recognition is another computer vision technology. This takes things a step further. Facial recognition involves identifying the face in the image to be a certain person. This is most commonly used in biometrics, such as Apple’s Face ID to unlock your iPhone. Face detection determines that there is a face, and facial recognition tells us who that face belongs to.
01:04 Then, we have facial analysis. Facial analysis tries to understand something about people from their facial features, like their age, gender, or emotions.
01:15 A facial analysis algorithm might process this image on the right and guess that the face pictured belongs to a girl in her twenties who is happy, and it would be correct. Before we talk about the last major technology, we have to understand how a video works.
01:33 A video is composed of individual images called frames. When you play these images back quickly—say, at 24 or 30 frames per second—you get the illusion of a motion picture, also known as a video.
01:49 That’s part of how face tracking works. Facial tracking tries to follow a face and its features from frame to frame. It’s very common in video analysis, and it’s often used in consumer apps like Snapchat or Instagram to provide fun little filters.
02:07 In this image on the right, facial tracking algorithms track the position of my head and facial features in real time and then superimpose bunny ears and a nose onto the image.
02:19 The frames taken from my phone’s camera are rapidly fed through the algorithm in real time, which means that I can move my head and see the bunny ears and nose move with me.
02:30 As cool as some of these technologies are, this course will focus purely on face detection, or detecting the presence and location of faces within still images.
02:41 But before we can start coding, we have to briefly talk about how computers process individual images.
Become a Member to join the conversation.