Test system and test method of millions of one-to-many face recognition products

A test system and multi-face technology, applied in character and pattern recognition, special data processing applications, instruments, etc., can solve the problems of complex recognition and comparison technology, and there are no tens of millions of face recognition products, so as to save testing Time, faster comparison speed, and scalable effects

Inactive Publication Date: 2009-12-30
THE FIRST RES INST OF MIN OF PUBLIC SECURITY +1
View PDF0 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Domestic one-to-many face recognition products usually have a test query sample of 100,000 or one million, and the test samples are basically completed on a single computer or server. The comparison technology is complicated. On the other hand, the product involves network, database, load processing and other multi-field technologies. Therefore, there is no test of tens of millions of face recognition products at home and abroad.

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
  • Test system and test method of millions of one-to-many face recognition products
  • Test system and test method of millions of one-to-many face recognition products

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] In the present invention, the basic terms of face recognition product testing are as follows:

[0024] 1) Login

[0025] The feature template extraction unit performs feature extraction on image samples.

[0026] 2) Disapproved

[0027] During the login process, the feature template extraction unit cannot extract features normally.

[0028] 3) Disapproval rate

[0029] The ratio of disapprovals to the total number of logins, expressed as a percentage.

[0030] 4) Login time

[0031] The time spent on a single login, expressed in milliseconds (ms).

[0032] 5) Compare

[0033] The process of comparing the features of two faces.

[0034] 6) Match similarity

[0035] The output result of the feature comparison represents the similarity of the two feature files involved in the comparison. Its value is represented by a single-precision floating-point number ranging from 0.00 to 1.00. The larger the number, the greater the similarity of the comparison, and the smalle...

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 relates to a test system and test method of millions of one-to-many face recognition products, wherein, a characteristic template extracting unit, an image data storage unit and a template data storage unit are respectively interconnected each other; and a comparing request unit is connected with a comparing unit which is respectively connected with a template data storage unit and a result data storage unit. Each unit consists of a computer or a plurality of computers connected by a network. The comparing unit is provided with a one-to-many characteristic comparing template. The invention also provides a test method of millions of one-to-many face recognition products and has the advantages that all the units of the test system are respectively a modularized structure, are independent and also can be combined in any manner; the test system can carry out multimachine multiprocess parallel test and has strong expandability. By adopting the same test interface protocol and the comparing result storage protocol, the invention can obtain test result of all phases (all modules) by one-time test, also can acquire the total test results; the performance for testing millions of one-to-many face recognition products is fast, accurate and comprehensive.

Description

technical field [0001] The invention relates to the field of computer biometric feature recognition, in particular to a test system and test method for tens of millions of one-to-many face recognition products. Background technique [0002] With the development of biometric technology, face recognition technology has gradually moved from a prototype system to commercial use, and professional commercial face recognition systems and products have emerged both at home and abroad. Face recognition technology mainly includes one-to-one verification and one-to-many recognition. One-to-many face recognition is to compare one face sample with multiple (or N) face samples that need to be queried, and return the comparison similarity according to user requirements. One or more samples that are ranked first in descending order of degree. Face recognition technology applications mainly include one-to-one verification applications and one-to-many recognition applications. [0003] Tens...

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): G06F17/30G06K9/00
Inventor 田青宛根训田强李建勇
Owner THE FIRST RES INST OF MIN OF PUBLIC SECURITY
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