Biological feature adaptive learning identification method and system

A technology of biometric identification and self-adaptive learning, applied in the field of identification, can solve problems such as poor user experience, difficult improvement of system recognition rate, high difficulty in selection of similarity threshold, and achieve good recognition rate effect

Active Publication Date: 2020-11-06
AISPEECH CO LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] In order to at least solve the problems in the existing technology that completely rely on the active labeling behavior of users, the user experience is poor, and it is difficult to achieve the number of labeling required by the system, the system recognition rate is difficult to improve, and the selection of the similarity threshold is difficult.

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
  • Biological feature adaptive learning identification method and system
  • Biological feature adaptive learning identification method and system
  • Biological feature adaptive learning identification method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0037] As an implementation manner, the biological characteristics include voiceprint characteristics;

[0038] The second identity authentication includes: any one of facial feature authentication, iris feature authentication, fingerprint feature authentication, password authentication, and physical card authentication.

[0039] In this embodiment, a mature biometric identification system has multiple identification modules such as face recognition, iris recognition, fingerprint recognition, electronic password or physical key. It is considered as a mature high-level identity authentication system with extremely high security, and the accuracy of identification is extremely high. The security of identification systems such as voiceprint is slightly lower, and it is used as a low-level identification system.

[0040] However, low-level identity authentication often requires more physical characteristics such as the authenticator's environment and the human-computer interactio...

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 embodiment of the invention provides a biometric feature adaptive learning identification method. The method comprises steps of taking the biological characteristics of a user collected during registration as basic characteristics, and storing the basic characteristics into a biological characteristic template; in the process of collecting the biological characteristics of the user to carry out first identity authentication, if second identity authentication is triggered, carrying out identity marking on the biological characteristics by utilizing an authentication result of the second identity authentication; adding the biological characteristics with the marks to a self-adaptive learning template; and carrying out biometric feature recognition on the user by utilizing the biometric feature template and the adaptive learning template which are independent of each other. The embodiment of the invention further provides an identification system for biological feature adaptive learning. According to the method, the relatively mature identity authentication is used to label the feature identity of the biological feature recognition module, the registered feature template is updated adaptively, and the recognition rate is improved, meanwhile, the independent biological feature template and the self-adaptive learning template are respectively used for carrying out biological feature recognition, so the influence of wrong self-adaptive learning on recognition is avoided.

Description

technical field [0001] The invention relates to the field of recognition, in particular to a recognition method and system for self-adaptive learning of biological characteristics. Background technique [0002] Common biometric engine adaptive learning includes: [0003] 1. During the process of user authentication using biometrics collection, the user can manually mark the biometrics collected this time in the system to confirm that the biometrics collected this time are the user's own biometrics, and the system will Automatically add this biometric feature to the user registration feature model for feature comparison, and update the biometric sequence that characterizes the user's features, so as to improve the recognition rate of the biometric feature recognition system. [0004] 2. Through the similarity algorithm. The similarity algorithm can evaluate the similarity between the biometrics collected this time to be identified and the biometrics of the registrant, and u...

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): G06F21/32G06F21/45
CPCG06F21/32G06F21/45
Inventor 顾向涛黄厚军
Owner AISPEECH 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