Infrared face recognition algorithm

Supported platforms: Android, Windows, Linux, bare OS or other platforms

Hardware requirements: processor frequency > 300MHz; Memory more than 16M;

Face recognition: to detect the ideal distance between the eyes of the face in more than 40 pixels, the ideal distance between the eyes of the recognition in more than 50 pixels; Can recognize the face image, the correct recognition rate of more than 99%;

Image specifications: the distance between the eyes of the photo face is more than 40 pixels;

Camera resolution: no less than 300,000 pixels;

Head Angle: positioning up and down plus or minus 30 degrees, about plus or minus 45 degrees, identify up and down plus or minus 20 degrees, about plus or minus 30 degrees; (Parameters vary according to different hardware platforms)

Identification distance: The identification distance is related to the camera resolution and lens focal length. The following data is for reference only, please refer to the actual test of the camera. The furthest detection distance of the 30W camera is 0.3-0.8m.

Rejection rate: 0.01%

Error rate: 0.00001%

Method of technology authorization:

Core SDK Authorization:

At present, core authorization is our main authorization method, which provides users with core dynamic library of recognition. Customers can realize face detection and face recognition according to our interface

Supported platforms: Android (Java), Windows (C ++/ C #/ Java), Linux(C), ARM-Linux (C).

Documents provided:

Documentation: SDK development interface documentation and DEMO

encryption

PC (Windows /Linux) : Dongle encryption/network authentication;

Android: Network authentication/encryption chip;

Linux: Encryption chip/dongle;