Method for improving passing rate of face difficult to recognize for face recognition

A face recognition and recognition threshold technology, applied in the field of face recognition, can solve the problems affecting the face, the use of human body recognition, and the low recognition score of face and human body recognition, and achieve the effect of improving the traffic rate and reducing the interference.

Inactive Publication Date: 2019-11-26
UNIVERSAL UBIQUITOUS TECH CO LTD
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In actual use, these interference factors will generally bring a negative impact on face and human body recognit

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
  • Method for improving passing rate of face difficult to recognize for face recognition

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0011] The present invention will be further described below in conjunction with accompanying drawing.

[0012] The present invention is applicable to fields that require recognition and comparison, such as human faces or human bodies. The following uses face recognition as an example to illustrate.

[0013] The method for improving the passing rate of difficult-to-recognize faces for face recognition of the present invention specifically includes the following steps:

[0014] First, set the recognition pass threshold as Th1, and the minimum recognition threshold requirement as Th2, where Th2≤Th1; PersonIDi means the user with ID i in the library, and Ni is the number of times the user has been continuously identified as PersonIDi and the highest comparison score is greater than or equal to Th2. ReduceTh indicates that the recognition threshold reduces the ReduceTh score, and Nth indicates the number of times that the same person is continuously recognized and meets the minimu...

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 provides a method for improving the passing rate of a face difficult to recognize for face recognition, and the method comprises the following steps: firstly setting a recognition passing threshold value as Th1, setting a minimum recognition threshold value as Th2, and enabling Th2 to be smaller than or equal to Th1; when a user triggers recognition, searching the most similar in-library human face and the corresponding comparison score Score _ top 1 in the human face feature library; if Score _ top 1 is greater than or equal to Th1, determining the identification to be successful; when the user IDi cannot reach the identification pass threshold Th1 in the identification process, the identification is directly successful; if a condition that Ni is greater than or equal to Nthis triggered in the process, reducing the identification passing threshold of the user is reduced, wherein the recognition passing threshold value is reduced to Th3 = max (Th2, Th1-ReduceTh), Ni is the number of times that the user IDi is continuously identified as PersonIDi and the highest comparison score is greater than or equal to Th2, and Nth represents the set number of times that the userIDi is continuously identified as the same person and meets the minimum identification threshold requirement Th2, and is used for triggering a mechanism for reducing the identification threshold.

Description

technical field [0001] The invention belongs to the field of face recognition, in particular to a method for face recognition to improve the passing rate of difficult-to-recognize faces. Background technique [0002] Face and human body recognition will be affected by different factors in actual use scenarios, including lighting, irregular registration photos, camera installation height, motion blur, etc. These uncontrolled factors will affect the speed and accuracy of face recognition and human body recognition. In actual use, these interference factors will generally bring a negative impact on face and human body recognition with a lower recognition score than the pass threshold, affecting the use of face and human body recognition. Contents of the invention [0003] In order to solve the above-mentioned technical problems existing in the prior art, the present invention provides a method for improving the passing rate of difficult-to-recognize faces for face recognitio...

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): G06K9/00G06F16/583
CPCG06F16/583G06V40/168
Inventor 郑东赵拯赵五岳
Owner UNIVERSAL UBIQUITOUS TECH CO LTD
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap