Unlock instant, AI-driven research and patent intelligence for your innovation.

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.

Active Publication Date: 2022-05-17
北京圣点云信息技术有限公司
View PDF17 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the face is a body surface feature, which is easy to be copied and misused, and there are security risks; and for ordinary face recognition, since the characteristics of the RGB image of the side face at a large angle have little difference, the recognition pass rate is limited by the cooperation of the user
[0003] In view of the above-mentioned technical problems, it is an urgent problem for those skilled in the art to find a method that can improve security and avoid the difficulty of live detection; and can improve the face recognition pass rate of human faces at large angles.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • An identity recognition method and device based on multi-posture facial veins
  • An identity recognition method and device based on multi-posture facial veins
  • An identity recognition method and device based on multi-posture facial veins

Examples

Experimental program
Comparison scheme
Effect test

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 ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an identification method and device based on multi-posture facial veins. Firstly, face detection and posture judgment are carried out, facial vein image acquisition and preprocessing are carried out according to the judged posture, then a convolutional neural network is constructed and trained, and finally user registration and recognition are performed. The application of the above technical solution mainly extracts facial vein pictures as the features of identity recognition, which is different from the traditional face recognition that uses ordinary face RGB pictures as features. Facial veins are internal features of the human body, which are not easy to copy, and can avoid the problem of living body detection. ; and between different people, the distribution of facial veins on the side faces is also very different. In different postures, facial veins can also be used to effectively identify identities. It is not limited to the cooperation of users and can effectively make up for the lack of common face recognition. The problem of low pass rate of recognition at large angles.

Description

technical field [0001] The invention belongs to the biological identification technology in the field of information security, and in particular relates to an identification method based on multi-posture facial veins. Background technique [0002] Face recognition is a biometric technology for identification based on human facial feature information. A series of related technologies that use a video camera or camera to collect images or video streams containing human faces, automatically detect and track human faces in the images, and then perform facial recognition on the detected faces, usually also called portrait recognition and facial recognition. . At present, due to the popularization of video surveillance technology, the face recognition industry has developed rapidly, and it has been widely used in various industries such as finance, justice, education, and medical care. However, the face is a body surface feature, which is easy to be copied and misused, and there...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06V40/16G06V10/34G06V10/82G06K9/62
CPCG06V40/161G06V40/172G06V40/171G06V40/10G06V40/14G06V10/34G06F18/22
Inventor 胡振寰李学双赵国栋张烜
Owner 北京圣点云信息技术有限公司