Face recognition system and method based on distributed intelligent light supplement

Abstract

The invention discloses a face recognition system and method based on distributed intelligent light supplement, and the system comprises a camera subsystem which is used for collecting a face image in a foresight scene; a distributed lighting unit group which is used for supplementing light in a foresight scene of the camera subsystem, wherein the brightness of a single lighting unit of the distributed lighting unit group is continuously adjustable; a visual information processing subsystem which is used for calculating two-dimensional and three-dimensional face key points and a face model according to the acquired face image, and carrying out the light radiation calculation, face reflection calculation, face light shielding calculation, incident light response intensity calculation of the camera subsystem and optimal light control method calculation on each illumination unit in the distributed illumination unit group; and a lighting unit control subsystem which is used for continuously controlling the output mode of the single lighting unit according to the calculation result. The system can effectively improve the face recognition rate of the visible light camera in a complex dark field environment.

Description

technical field [0001] The invention relates to the technical field of face recognition, in particular to a face recognition system and method based on distributed intelligent light supplement. Background technique [0002] Face recognition is currently widely used in criminal investigation, entertainment consumption, personnel management and other fields. At present, face recognition is mostly applied under the condition of sufficient ambient light, but when the ambient light is weak and the facial shadow is complex, the relevant face recognition rate will drop significantly. [0003] To solve the above problems, common solutions include: 1) Use sensors that are not sensitive to ambient light to collect face data, and design and develop related face recognition algorithms on this basis. Related applications include sensing systems using near-infrared cameras and sensing systems using multispectral cameras. Obviously, in most cases, the cost of the above-mentioned systems ...

AI Technical Summary

Problems solved by technology

At present, deep learning technology has developed rapidly, but deep learning methods rely on a large number of training samples, and the adaptive computing capabilities of related algorithms for complex environmental changes are also limited by the actual situation that training data can traverse

Improve the recognition rate by continuously improving and upgrading the face recognition algorithm. The design and improvement of related algorithms are close to the upper limit of the algorithm's processing capability. difficulty

Images