An identity recognition method and device based on multi-posture facial veins
A multi-posture and vein technology, applied in the field of biometrics, can solve the problems of potential security risks, easy to be copied and misappropriated, and users with limited pass rate, and achieve the effect of improving passability, not easy to copy, and improving robustness.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0044] Refer to attached figure 1 As shown, the present invention relates to a kind of identification method based on multi-posture facial veins, comprising the following steps:
[0045] 1) Face detection and posture judgment: use RGB camera and infrared camera to take 100 face pictures and facial vein pictures of 1000 people in different postures respectively. Vein pictures such as figure 2 shown.
[0046] Use RetinaFace to detect 68 feature points of facial vein pictures, and the distribution of 68 feature points is as follows image 3 As shown, 46 marks the left eye corner of the left eye, 55 marks the left corner of the mouth, 13-17 marks the five feature points of the left face edge, 37 marks the right eye corner of the right eye, 49 marks the right mouth corner, 1-5 Mark the 5 feature points on the edge of the face on the right side;
[0047] If the midpoint of the feature points of the left corner of the left eye and the left corner of the mouth is on the right sid...
Embodiment 2
[0072] combine Image 6 As shown, the present invention relates to an identification device based on multi-position facial veins, comprising:
[0073] 1) Face detection and posture judgment module: used for face detection and posture judgment, that is, the infrared camera is used to take pictures of facial veins, and the face frame and 68 feature points are detected by the face detection algorithm RetinaFace, and judged according to the feature points Face posture, including front face and side face, the side face includes left face and right face; this module is used to realize the function of step 1) in embodiment 1.
[0074] 2) Facial vein picture collection and preprocessing module: used for facial vein picture collection and preprocessing, that is, according to the posture detected in step 1), collect the front face vein characteristic picture or the side face vein characteristic picture of the facial vein picture, And respectively expand and enhance the collected front ...
Embodiment 3
[0080] combine Figure 7 As shown, another embodiment of the present invention provides a structural diagram of an identification device based on multi-posture facial veins, the device includes at least one processor and a memory, Figure 7 Take a processor as an example. The processor and the memory are connected through a bus, and the memory stores instructions that can be executed by the processor; when the processor executes the program stored in the memory, the following methods can be implemented: 1) Face detection and posture judgment: use an infrared camera to capture the face The vein picture, the face frame and 68 feature points are detected by the face detection algorithm RetinaFace, and the face posture is judged according to the feature points, including the front face and the side face, and the side face includes the left face and the right face;
[0081] 2) Acquisition and preprocessing of facial vein feature pictures: According to the posture detected in step ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


