A face recognition system and method based on video multi-frame face feature fusion

Abstract

The invention belongs to the technical field of face recognition, and discloses a face recognition system and method based on video multi-frame face feature fusion, and the method comprises the steps:employing a camera of a specific bilateral filter to collect face video data; enhancing the face video data by using video processing software; extracting multiple frames of face feature elements from a face video by utilizing an extraction program, carrying out fusion operation on the multiple frames of face features by using a SMART-PN fusion algorithm; utilizing an identification program to identify the face features by adopting an ultrahigh frequency radio frequency identification technology; storing the acquired face video data by using a memory; and displaying the acquired face video data by using a display. The accuracy of face recognition can be improved; through data comparison processing of the three features of the face mouth, the eyes and the eyebrows, the recognition processing speed is increased.

Description

technical field [0001] The invention belongs to the technical field of face recognition, and in particular relates to a face recognition system and method based on multi-frame face feature fusion of videos. Background technique [0002] Face recognition technology is mainly based on face recognition of visible light images, which is also a familiar recognition method and has a research and development history of more than 30 years. However, this method has insurmountable defects, especially when the ambient light changes, the recognition effect will drop sharply, which cannot meet the needs of the actual system. Solutions to lighting problems include 3D image face recognition and thermal imaging face recognition. But these two technologies are still far from mature, and the recognition effect is not satisfactory. One solution that is rapidly developing is the multi-light source face recognition technology based on active near-infrared images. It can overcome the influence...

AI Technical Summary

Problems solved by technology

[0004] The video quality collected by existing face recognition is poor; at the same time, the face recognition rate is low and the accuracy rate is low

[0005] In the prior art, the clarity of the collected face video cannot be guaranteed, and the face image does not have the effect of smoothing and edge protection during the collection process, which is not conducive to the accurate and real collection of the collected face video data; The fusion operation of the frame face features will reduce the accuracy and fusion efficiency due to the loss caused by the collision; the reading and recognition efficiency of information data in the prior art is low, and the work efficiency is low

Images