The Development of Face Recognition Dec 03, 2019

Face recognition is a kind of biometirc identity recognition based on facial feature information. Use a camera to collect images or video streaming containing human faces, and automatically detect and track the face in the image, and then carry out a series of face related technologies for the detected face. This is commonly known as human image recognition and face recognition. Now it is generally used in the company's swing gatesystem, which is convenient for punching in the company. Some communities are also using face recognition and swing brakes.

Conventional face recognition technologies mainly are based on visible light image, which is also a familiar recognition method. It has been developed for more than 30 years. However, this method has some defects that are difficult to overcome, especially when the ambient light changes, the recognition effect will decline sharply, which can hardly meet the needs of the actual system. The solutions to the illumination problem are 3D face recognition, and thermography face recognition. However, these two technologies are far from maturing with the recognition effect.

A fast-growing solution is multi light source face recognition technology based on initiative near infrared image. It can overcome the influence of light changes, and has achieved excellent recognition performance. Its overall system performance in accuracy, stability and speed is better than that of 3D face recognition. This technology has developed rapidly in the past two or three years, making face recognition technology gradually practical.

Human face is born with other biological characteristics (fingerprint, iris, etc.). Its uniqueness and nonreplication provide the necessary premise for identification. Compared with other types of biometrics, face recognition has the following characteristics:

Non-mandatory: Without users behave in conjunction with it, a face acquisition equipment can obtain face images almost when users are unconsciously. Such a method of sampling is not "mandatory";

Non contact: Users do not need to directly contact with the device to obtain face images;

Concurrency: In the actual application scenario, multiple faces can be sorted, judged and identified;

In addition, it also conforms to the visual characterized by "recognizing people by appearance". And it is also characteristered by simple operation, intuitive results and good concealment.