It is mainly confirmed by the part outside the mask. Because wearing a mask can collect less facial information, it is necessary to add more key points to the eyes, such as bone information and the distance from eyebrow bone to ear. And through the key point algorithm to improve the accuracy of recognition, to achieve accurate recognition.
Features of face recognition:
The human face is born with other biological characteristics of the human body (fingerprint, iris, etc. ), its uniqueness and good characteristics of not being easily copied provide the necessary premise for identity authentication. Compared with other types of biometric identification, face recognition has the following characteristics:
Non-mandatory: users can unconsciously collect face images without special cooperation with face collection equipment, so this sampling method is not "mandatory".
Non-contact: users can get face images without direct contact with equipment.
Concurrency: In practical application scenarios, multiple faces can be sorted, judged and recognized.
In addition, it also conforms to the visual characteristics: the characteristics of "judging people by their appearances" and the characteristics of simple operation, intuitive results and good concealment.