Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

A method and a system for calculating the credibility of face recognition

A face recognition and calculation method technology, applied in the field of face recognition, can solve the problems of huge calculation amount and inaccurate reliability results, and achieve the effect of reliable judgment results and simple reliability calculation.

Pending Publication Date: 2019-01-11
杭州吉吉知识产权运营有限公司
View PDF1 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This invention directly calculates the similarity between the collected face pictures and the pictures in the face picture library to obtain the confidence of identifying the target object, the amount of calculation is huge, and the calculated credibility results are not accurate enough

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 a system for calculating the credibility of face recognition
  • A method and a system for calculating the credibility of face recognition
  • A method and a system for calculating the credibility of face recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] This embodiment discloses a method for calculating the credibility of face recognition, such as figure 1 shown, including steps:

[0049] S101. Select a preset number of face image samples of the same individual and a preset number of non-identical face image samples in the preset face data set;

[0050] S102. Calculate the similarity of each pair of pictures in the same individual face picture samples as a positive sample, and calculate the similarity of each pair of pictures in the non-same individual face pictures as a negative sample;

[0051] S103. Fit the distribution of the number of positive and negative samples along with the similarity value to a normal distribution curve, and obtain the normal distribution expressions of the positive and negative samples respectively;

[0052]S104. Calculate the face recognition reliability according to the ratio of the positive sample distribution to the sum of positive and negative sample distributions.

[0053] With the ...

Embodiment 2

[0079] This embodiment discloses a method for calculating the reliability of face recognition. The difference from Embodiment 1 is that this embodiment also includes step S205, step S206 and step S207. Calculate and count, and establish the credibility model of face recognition, and then analyze the credibility of the collected face pictures to make the judgment result more reliable, such as Figure 5 shown, including steps:

[0080] S201. Select a preset number of face image samples of the same individual and a preset number of non-identical face image samples in the preset face data set;

[0081] S202. Calculate the similarity of each pair of pictures in the same individual face picture samples as a positive sample, and calculate the similarity of each pair of pictures in the non-same individual face pictures as a negative sample;

[0082] S203, fitting the distribution of the number of positive and negative samples along with the similarity value to a normal distribution c...

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 a system for calculating the credibility of face recognition, wherein the method comprises the following steps: selecting the same individual face picture samplesof a preset number pair and the different individual face picture samples of a preset number pair in a preset face data set; and calculating the credibility of the preset number pair; calculating similarity of each pair of pictures in the same individual face picture sample as a positive sample and calculating similarity of each pair of pictures in the non-same individual face picture as a negative sample; fitting the distribution of positive and negative samples with similarity value to normal distribution curve, and obtaining the normal distribution expressions of positive and negative samples; calculating the face recognition reliability according to the ratio of the sum of the positive sample distribution and the positive and negative sample distribution. The invention uses the large sample in the face recognition data set to calculate and statistically calculate the credibility of the face recognition result, huge operation is not needed, and the calculation result is more accurate and reliable.

Description

technical field [0001] The invention relates to the field of face recognition, in particular to a method and system for calculating the reliability of face recognition. Background technique [0002] Face recognition technology is a kind of biometric recognition technology based on human facial feature information. It uses a camera or camera to collect images or video streams containing human faces, and automatically detects and tracks human faces in the images. A series of related technologies for recognizing the detected face, usually also called portrait recognition and facial recognition. [0003] With the development of science and technology, face recognition technology is becoming more and more mature. The mainstream recognition methods such as facenet and deepid are to obtain the feature vector through convolution calculation of the face picture, and judge the two pictures by the cosine distance of the feature vector of the two pictures. Whether it is the same person...

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 Applications(China)
IPC IPC(8): G06F16/51G06F16/58G06K9/00G06K9/62
CPCG06V40/168G06V40/172G06F18/22G06F18/214
Inventor 杨一明
Owner 杭州吉吉知识产权运营有限公司
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
Eureka Blog
Learn More
PatSnap group products