Method, device, equipment and storage medium for binocular living body recognition of the same face frame
A technology of the same face and face frame, applied in the computer field, can solve the problems of low accuracy and low security of binocular living body recognition, and achieve the effect of improving security and accuracy.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0037] figure 1 It shows the implementation flow of the method for recognizing the same human face frame provided by the binocular living body provided by the first embodiment of the present invention. For the convenience of explanation, only the parts related to the embodiment of the present invention are shown, and the details are as follows:
[0038] In step S101, the RGB image and the NIR image for binocular living body recognition are sampled to obtain a first face frame and a second face frame, the first face frame is a face frame in the RGB image, and the second face frame is obtained. The face frame is the face frame in the NIR image.
[0039] Embodiments of the present invention are suitable for binocular living body recognition equipment, which should have a first camera and a second camera, and the first camera is used to obtain RGB (R (red, red), G (green, green) , B (blue, blue), color mode) images, the second camera is used to acquire NIR (Near Infrared, near in...
Embodiment 2
[0051] figure 2 It shows the implementation flow of the training method of the face frame prediction model for binocular living body recognition of the same face frame provided by the second embodiment of the present invention. For the convenience of explanation, only the parts related to the embodiment of the present invention are shown, and the detailed description as follows:
[0052] S201: Obtain a working distance range for binocular living body recognition, and divide the working distance range into several equidistant distance scales.
[0053] In the embodiment of the present invention, the minimum working distance d of binocular living body recognition can be set according to the requirements of the application scene min , and the maximum working distance of binocular live recognition is d max , divide the working distance interval into n equal parts, and get n+1 distance scales
[0054] S202: In the overlapping area between the RGB image and the NIR image corres...
Embodiment 3
[0066] Figure 4 The structure of the device for binocular living body recognition of the same human face frame provided by Embodiment 3 of the present invention is shown. For the convenience of description, only the parts related to the embodiment of the present invention are shown, including:
[0067] Face frame acquisition unit 41, used to sample the RGB image and the NIR image of binocular living body recognition, obtain the first face frame and the second face frame, the first face frame is the face frame in the RGB image , the second face frame is a face frame in the NIR image;
[0068] The face frame prediction unit 42 is used to predict the third face frame corresponding to the first face frame by the trained face frame prediction model, and the third face frame is the face frame in the predicted NIR image ;as well as
[0069] A human face determination unit 43, configured to calculate the overlapping pixel area ratio of the third human face frame and the second huma...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


