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

1:1 face feature vector comparison method based on interference feature vector data set

A feature vector and face feature technology, applied in the field of face recognition, can solve the problem of unsatisfactory face recognition effect, and achieve the effect of improving the recognition accuracy.

Pending Publication Date: 2018-02-02
安徽慧视金瞳科技有限公司
View PDF8 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this eigenvector comparison method is greatly affected by various factors such as illumination, angle, age, beard, etc., resulting in unsatisfactory face recognition results.

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
  • 1:1 face feature vector comparison method based on interference feature vector data set
  • 1:1 face feature vector comparison method based on interference feature vector data set
  • 1:1 face feature vector comparison method based on interference feature vector data set

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] In order to further illustrate the features of the present invention, please refer to the following detailed description and accompanying drawings of the present invention. The accompanying drawings are for reference and description only, and are not intended to limit the protection scope of the present invention.

[0035] Such as figure 1 As shown, this embodiment discloses a 1:1 face feature vector comparison method based on the interference feature vector data set, including the following steps S1 to S5:

[0036] S1. Using the deep neural network method to calculate the interference feature vector J of each face image in the interference data set i , to construct the interference feature vector data set [J 1 , J 2 ,...,J i ,...,J I ], I is a constant;

[0037] It should be noted that in this embodiment, a face data set containing 2,000 photos of stranger faces is collected as an interference data set. For each photo, use the face feature extraction algorithm b...

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 1:1 face feature vector comparison method based on an interference feature vector data set, which belongs to the technical field of face recognition. The method includes thefollowing steps: calculating the interference feature vector of each face image in an interference data set, and constructing an interference feature vector data set; using a deep neural network method to calculate the feature vector K of a to-be-tested face image; calculating the similarity value between the feature vector K of the to-be-tested face image and each feature vector in a face featurevector data set of a to-be-compared person, and selecting the first t1 similarity values according to the similarity from high to low; calculating the similarity value between the feature vector K ofthe to-be-tested face image and each feature vector in the interference feature vector data set, and selecting the first t2 similarity values according to the similarity from high to low; and determining whether the to-be-tested face image is the to-be-compared person according to the t1 similarity values and the t2 similarity values. Through synthetic judgment on the feature vector of an input face and an interference face feature vector set, the recognition accuracy of the system is improved.

Description

technical field [0001] The invention relates to the technical field of face recognition, in particular to a 1:1 face feature vector comparison method based on an interference feature vector data set. Background technique [0002] Face recognition is a machine vision recognition technology that extracts facial features based on face photos and then identifies identity information. In recent years, with the rapid development of deep neural network and its application in the field of face recognition, the effect of face recognition has been greatly improved. Moreover, face recognition technology has been widely used in finance, education, public security, medical care and many other fields. [0003] Face recognition includes 1:1 face recognition method and 1:N face recognition method. Among them, 1:1 face recognition refers to matching the input face with the designated person in the system, and confirming whether the input face matches the designated person. Personnel are th...

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
IPC IPC(8): G06K9/00
CPCG06V40/168G06V40/172
Inventor 汪俊锋戴平刘罡何勇
Owner 安徽慧视金瞳科技有限公司