Traditional face recognition technology is mainly based on the face recognition of visible light images, and people are more familiar with such recognition methods. However, the disadvantage of this method is actually very obvious, the limitation of light is very large, and it cannot meet the actual needs. The solutions to the lighting problem include 3D image face recognition and thermal imaging face recognition. However, these two technologies are far from mature, and the recognition effect is not satisfactory.
ToF camera solution is a multi-light source face recognition technology based on active near-infrared images. ToF cameras can overcome the effects of light changes and have achieved excellent recognition performance, with overall system performance exceeding 3D image face recognition in terms of accuracy, stability and speed. ToF camera technology has developed rapidly in the past two or three years, making face recognition technology gradually practical.
ToF camera is one of the solutions of 3D depth camera, which is similar to the use of structured light. There are two types of ToF camera ranging, single-point and multi-point, among which multi-point ranging is generally used on smartphones. The principle of multi-point ranging is similar to that of pulse single-point ranging, but the light-receiving device is CCD, that is, a photodiode array with charge retention, which has an integral characteristic of light response. The basic principle is that the laser source emits a laser with a certain viewing angle, where the laser duration is dt (from t1 to t2), and each pixel of the CCD is controlled by two synchronous trigger switches S1 (t1 to t2), S2 (t2 to t2+dt) The charge holding element of each pixel collects the period of reflected light intensity to obtain responses C1 and C2. The distance between the object and each pixel is L=0.5*c*dt*c2/(c1+c2), where c is the speed of light (this formula can remove the influence of the difference in the reflection characteristics of the reflector on the ranging). To put it simply, a processed light is emitted, and it will be reflected back when it hits an object, capturing the time of the round trip. Because the speed of light and the wavelength of the modulated light are known, the distance to the object can be quickly and accurately calculated.
Advantage of ToF camera technology is that the overall components are smaller, and it can be applied to smartphones without considering the size of the screen, the recognition distance is longer, and more applications can be expanded; no post-processing is required to calculate the depth of field after the picture is captured, and it is simple In other words, it can avoid the time delay and save the related costs caused by the use of a powerful post-processing system; it has the advantages of being less susceptible to external light interference, small size, fast response speed and high recognition accuracy.
