A method and device for face comparison and a method and system for face recognition

A face and pixel point technology, applied in the computer field, can solve the problems of slow face comparison speed and low accuracy of face contour feature points, and achieve the effect of improving speed

Inactive Publication Date: 2018-07-06
深圳市君利信达科技有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention provides a face comparison method and equipment to solve the problem of slow face comparison speed in the process of face recognition existing in the prior art; the present invention also provides a face recognition method , a system for solving the problem of low accuracy of extracted face contour feature points in the process of face recognition existing in the prior art

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 comparison and a method and system for face recognition
  • A method and device for face comparison and a method and system for face recognition
  • A method and device for face comparison and a method and system for face recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0094] The face recognition method according to the embodiment of the present invention includes two parts: determining the face in the image and comparing the face.

[0095] Methods for determining faces in an image include:

[0096] For an image of a face to be extracted, determine the feature pixels of the image for determining the face;

[0097] For a feature pixel, determine a plurality of local pixels corresponding to the feature pixel for determining local features, and determine the BRIEF (Binary Robust Independent Elementary Features) of each of the local pixels. Eigenvalues;

[0098] Divide the determined plurality of Brief feature values ​​into at least one set, and determine the Brief feature value of each set according to the Brief feature values ​​included in each set;

[0099] Compare the brief feature value of each set with the comparative feature value corresponding to the feature pixel point, and determine the set with the highest similarity, wherein the co...

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 equipment for face comparison, and a method and system for face recognition, which are used to solve the problem in the prior art that the speed of face comparison is relatively slow in the process of face recognition. The method in the embodiment of the present invention includes: for an image that needs to be compared, according to the position of each feature pixel in the image on the face, divide all the feature pixels in the image into multiple groups of feature pixels; determine The pairing rules of the positions on the face corresponding to each group of feature pixels; according to the determined pairing rules, pair each feature pixel in each group of feature pixels, and determine the distance between each pair of feature pixels, according to The determined distance between each pair of feature pixel points determines the distance of each group of feature pixel points; according to the distances of all groups of feature pixel points in the images to be compared, the similarity of the compared images is determined. The speed of face comparison can be improved by adopting the method of the embodiment of the present invention.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a method and device for face comparison, and a method and system for face recognition. Background technique [0002] Face recognition technology is to match the image to be recognized with the image stored in the picture library, and find the image with the highest similarity as the recognition result. With the development of society, the application of face recognition is becoming more and more extensive. [0003] In the actual application process of face recognition technology, it will face the following problems: due to the different lighting conditions, there will be a big difference between the multiple images generated by the same person under different lighting conditions, and at the same time, in the multiple images. There is also a big difference between the faces of the same person, so the face recognition of the images of the same person under different ligh...

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): G06K9/00G06K9/62
CPCG06V40/165G06V40/171
Inventor 徐爱辉吴金勇王军叶土荣
Owner 深圳市君利信达科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products