Face recognition is a technology that can recognize or verify the identity of the subject in the image or video. The first face recognition algorithm was born in the early 1970s. Since then, their accuracy has been greatly improved. Now people tend to prefer face recognition compared with biometric methods traditionally considered more robust, such as fingerprint or iris recognition. One big difference that makes face recognition more popular than other biometric methods is that face recognition is essentially non-invasive. For example, fingerprint recognition requires users to press their fingers on the sensor, iris recognition requires users to be close to the camera, and speech recognition requires users to speak loudly. In contrast, modern face recognition systems only require users to be in the field of view of the camera (assuming that their distance from the camera is also reasonable). This makes face recognition the most user-friendly biometric method. This also means that face recognition has a wider range of potential applications, because it can also be deployed in environments where users do not expect to cooperate with the system, such as monitoring systems. Other common applications of face recognition include access control, fraud detection, identity authentication and social media. When deployed in an unconstrained environment, face recognition is also one of the most challenging biometric methods because the presentation of face images in the real world is highly variable (this kind of face images are usually called faces in the wild). The variable parts of face image include head posture, age, occlusion, lighting conditions and facial expression. Figure 1 shows an example of these cases.