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

A method and device for face recognition

A face recognition and face image technology, applied in the field of face recognition, can solve the problems of inability to achieve the recognition effect, regardless of the actual age of the person being recognized, and inaccurate recognition.

Active Publication Date: 2022-07-12
SENSCAPE TECH BEIJING CO LTD
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] It should be noted that when performing face recognition, if the collected recognition library pictures are photos of the recognizer many years ago, when the recognizer is re-recognized, the existing face recognition system does not consider the identity of the recognizer. Actual age, all recognizers are processed in various age groups, which cannot achieve effective recognition results, that is, when the recognized user and the face inventory have an age span, the existing face recognition system is not accurate

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
  • A method and device for face recognition
  • A method and device for face recognition
  • A method and device for face recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0024] The present invention provides a method for face recognition, such as figure 1 As shown, the method of face recognition may include:

[0025] Step S12, acquiring a face image.

[0026] Step S14, extracting the feature information of the above-mentioned face image.

[0027] Specifically, in this solution, the recognition terminal can be used to collect the face image of the recognized user or receive the inputted face image of the recognized user, and then the recognition terminal can use the pre-built face recognition model to identify the recognized user. Feature extraction is performed on the user's face image.

[0028] Step S16: Perform age assessment on the above-mentioned face image, and generate age information of the above-mentioned face image.

[0029] Specifically, in this solution, after the identification terminal extracts the feature information in the face image of the identified user, the identification terminal can then perform age assessment on the id...

Embodiment 2

[0051] The present invention also provides a face recognition device, which is used to implement the face recognition method of the first embodiment. It should be noted that the face recognition device can also be a face recognition terminal independently, or it can be a face recognition terminal. A device running in a terminal or server, such as figure 2 As shown, the above device may include:

[0052] The acquiring module 22 is used for acquiring a face image.

[0053] The extraction module 24 is used for extracting the feature information of the above-mentioned face image.

[0054] Specifically, in this solution, the acquisition module 22 can be used to collect the face image of the recognized user or the face image of the recognized user received input, and then the extraction module 24 can use a pre-built face recognition model to Feature extraction is performed on the face image of the recognized user.

[0055] The evaluation module 26 is configured to perform age ev...

Embodiment 3

[0079] Optionally, the solution of the present application can also provide a face recognition system that is robust to age, and this system is a face recognition system based on a deep learning model, such as image 3 As shown, the face recognition system may include an image data input module 30, a hidden layer 1, a hidden layer 2, a hidden layer 3, a hidden layer 4, a face recognition feature layer 34, an age assessment feature layer 36, an age assessment module 38 and Face recognition module 40 . The hidden layer 32 may be a convolution operation and a downsampling operation module. The face recognition feature layer 34 is a feature describing a face for face recognition. The age evaluation feature layer 36 is the feature description of the human face for age evaluation. The information of the age evaluation feature layer 36 is shared with the face recognition module 40, and the result of the age evaluation is also fed back to the face recognition module 40, and the face...

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 a method and device for face recognition. The method includes: acquiring a face image; extracting feature information of the face image; performing age assessment on the face image to generate age information of the face image; and age information to perform face recognition on face images. It solves the technical problem of inaccurate recognition of the existing face recognition system when the recognized user and the face database have age spans.

Description

technical field [0001] The present disclosure relates to the field of data processing, and in particular, to a method and device for face recognition. Background technique [0002] Face recognition is a biometric technology for identification based on human facial feature information. At present, face recognition has begun to be applied in many fields, such as access control, equipment login to airports, and monitoring of public areas. [0003] It should be noted that, when performing face recognition, if the collected pictures in the recognition library are photos of the recognizer many years ago, when re-identifying the recognizer, the existing face recognition system does not consider the identity of the recognized person. Actual age, all recognizers are processed at all ages, which cannot achieve an effective recognition effect. That is, when the recognized user and the face database have an age span, the existing face recognition system is not accurate in recognition. ...

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): G06V40/16
CPCG06V40/178G06V40/168
Inventor 李晓宇肖洪波
Owner SENSCAPE TECH BEIJING CO LTD