Face sample library deployment method and face-recognition-based service processing method and device

A sample library and sample technology, applied in the field of face sample library deployment, can solve the problems of face recognition accuracy decline, business processing error rate increase, etc.

Pending Publication Date: 2019-09-06
CHINA UNIONPAY
View PDF15 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, when the number of samples in the face sample library is too large, the accuracy of face recognition will drop significantly, which will lead to an increase in the error rate of business processing using the face recognition 1:N mode

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
  • Face sample library deployment method and face-recognition-based service processing method and device
  • Face sample library deployment method and face-recognition-based service processing method and device
  • Face sample library deployment method and face-recognition-based service processing method and device

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0123] Example 1: In the process of business processing based on face recognition, the user's payment password and the tested face image are obtained, and the payment password is 135323. The preset sample number threshold is 1000. Then determine the number of human face samples in the password face sample library A1 corresponding to the character password 135323. If the number of human face samples in the human face sample library A1 is less than 1000, the 1:N mode face recognition is directly performed in the human face sample library A1.

[0124] If the number of human face samples in the human face sample library A1 is greater than or equal to 1000, then determine the number of human face samples in the first-level human face sample sub-database A11 obtained by dividing the human face sample library A1. The first-level face sample sub-database A11 is set with a first-level classification data label "3 months", which indicates that the first-level face sample sub-database A...

example 2

[0126] Example 2: In the process of business processing based on face recognition, the user's payment password and the tested face image are obtained, and the payment password is 135323. The preset sample number threshold is 1000. The mouth-to-face sample database corresponding to the character password 135323 is the mouth-to-face sample database A1. The first-level face sample sub-base obtained by dividing the human-face sample base A1 includes the first-level face sample sub-base A11. The second-level face sample sub-base obtained by dividing the first-level face sample sub-base A11 includes the second-level face sample sub-base A111 and A112. Wherein, the number of face samples in the secondary face sample sub-banks A111 and A112 is less than 1000 respectively.

[0127] The second-level face sample sub-database A111 is set with the first-level classification data label "3 months" and the second-level data label "Shanghai", and the second-level face sample sub-database A11...

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 face sample library deployment method and a face-recognition-based service processing method and device, and relates to the field of data processing. The face sample library deployment method comprises the steps: if the number of human face samples in a password human face sample library is larger than or equal to a preset sample number threshold value, obtaining historical service information of a user corresponding to the human face samples in the password human face sample library, wherein confidential service passwords of the user corresponding to the human face samples in the same password human face sample library are the same; and according to the historical service information, dividing the password face sample library to obtain M levels of face sample sub-libraries, wherein M is a positive integer. According to the technical scheme of the invention, the accuracy of service processing adopting face recognition can be improved.

Description

technical field [0001] The invention belongs to the field of data processing, and in particular relates to a face sample library deployment method, a face recognition-based business processing method and a device. Background technique [0002] In recent years, face recognition technology has been widely used in various fields. For example, transportation, commerce, public safety, etc. In order to make life and work more convenient for users, more and more business processes have introduced face recognition technology. For example, payment services, login services and other services with certain confidentiality. In these businesses, the face recognition 1:N mode is often used. [0003] The face recognition 1:N mode refers to the existing face sample library in the face recognition process. There are N samples in the face sample library. Comparing the recognized face picture with the N samples in the face sample library, and identifying whether the recognized face picture...

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
CPCG06V40/161G06V40/172G06Q10/105G06F16/2456G06V40/50G06F16/5866
Inventor 沈玺康家梁周继恩
Owner CHINA UNIONPAY
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