Face recognition method, device and equipment

Abstract

The invention discloses a face recognition method, device and equipment, and the method comprises the steps: enabling face recognition equipment to establish short-distance wireless connection with a user terminal, receiving face recognition information sent by the user terminal, and storing the face recognition information into a local sample library, wherein the face recognition information comprises a face recognition sample; identifying the first face image according to the first face image collected by the first camera and the face identification sample stored in the local sample library; after the identification is successful, executing a preset operation, and deleting face identification information corresponding to the successfully identified first face image in the local sample library. According to the invention, a small number of face samples with strong objectivity are generated in the local sample library collected on site, so that the face recognition time is greatly shortened and the face recognition efficiency is improved; and the local sample library can be dynamically updated, so that the increase and deletion of the face samples can be automatically completed, and the success rate of face recognition can be ensured under the condition of small samples.

Description

technical field [0001] The present invention relates to the technical field of face recognition, in particular to a face recognition method, device and equipment. Background technique [0002] With the improvement of image recognition algorithm and the improvement of processor computing power, the recognition rate of face recognition technology has also been greatly improved, making the application of face recognition payment system more and more extensive. The face recognition payment system identifies personal identities through facial information, and associates personal identities with mobile payment methods such as bank cards, mobile wallets, Alipay, and WeChat payments, and completes payments through face recognition. Because of its convenience, the face recognition payment system has been initially applied in fields such as subway fare collection, unmanned retail, and finance. [0003] Face recognition needs to pre-extract the face image of the target group, process ...

AI Technical Summary

Problems solved by technology

Every time a passenger passes through the gate, theoretically, the face information of the passenger collected by the gate camera on the spot needs to be matched with tens of millions of samples in the sample library, which will increase the time for face recognition and seriously affect the traffic efficiency and user experience.

Images