Method, device, electronic equipment and medium for establishing passers-by library

A method of establishment, passer-by technology, applied in the field of big data

Active Publication Date: 2018-05-15
ZHEJIANG DAHUA TECH CO LTD
View PDF12 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a method, device, electronic equipment and medium for establishing a passer-by library to solve the problem in the prior art that there are no resources for statistical analysis of non-members of the library

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, device, electronic equipment and medium for establishing passers-by library
  • Method, device, electronic equipment and medium for establishing passers-by library
  • Method, device, electronic equipment and medium for establishing passers-by library

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0075] figure 1 This is a schematic diagram of the process of establishing a passerby library provided by an embodiment of the present invention, and the specific processing process is as follows:

[0076] S101: Extract the target feature of the collected face image.

[0077] In the embodiment of the present invention, the method for establishing a passerby library is applied to an electronic device, which may be a PC, a tablet computer, a smart phone, a personal digital assistant (PDA), an image acquisition device, an image processing device, etc.

[0078] When the electronic device acquires the face image collected by the image acquisition device, the target feature of the face image is extracted. Specifically, for the collected face image, the algorithm existing in the prior art can be used to extract the feature points of the face image, and the target feature of the face image can be obtained according to the extracted feature points. The target feature can be It is the charact...

Embodiment 2

[0096] In order to improve the accuracy of face recognition, on the basis of the foregoing embodiment, in the embodiment of the present invention:

[0097] If the maximum value of the second similarity is greater than the preset second threshold, the method further includes:

[0098] Identify the target second image corresponding to the maximum value of the second similarity, and store the face image in the image group of the second identification information where the target second image is located.

[0099] In the embodiment of the present invention, when the person corresponding to the collected face image does not belong to the deployment control library and the whitelist library, the target feature of the face image and the second feature of each second image in the passerby library are determined respectively. The second similarity, when the maximum value of the second similarity is greater than the preset second threshold, it is determined that the person corresponding to the ...

Embodiment 3

[0103] On the basis of the foregoing embodiment, in the embodiment of the present invention:

[0104] After extracting the target feature of the collected face image, the method further includes:

[0105] Determining the target feature value of the face image according to the target feature;

[0106] The separately determining the first similarity between the target feature and the first feature of each first image stored in the deployment control library and the whitelist library includes:

[0107] Respectively determining the first similarity between the target feature value and the first feature value of each first image stored in the deployment control library and the whitelist library;

[0108] The determining the second similarity between the target feature and the second feature of each second image in the preset passerby library includes:

[0109] The second similarity between the target feature value and the second feature value of each second image in the preset passerby librar...

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 method, a device, electronic equipment and a medium for establishing a passers-by library so as to solve the problem of no resources for statistical analyses of non-library members in the prior art. The method comprises the steps that target features of collected face images are extracted; first similarities between the target features and a first feature of each first image stored in a deploy control library and a white list library are respectively determined; if all first similarities are less than a preset first threshold, second similarities between the target features and a second feature of each second image in a preset passers-by library are determined; whether or not the maximum values of the second similarities are greater than a preset second thresholdis determined; if not, the face images and first identification information corresponding to the face images are added to the preset passers-by library. According to the method, the passers-by libraryfor storing non-library member face information which does not belong to the deploy control library and the white list library is established, thereby facilitating the subsequent statistical analyses.

Description

Technical field [0001] The present invention relates to the technical field of big data, in particular to a method, device, electronic equipment and medium for establishing a passerby library. Background technique [0002] With the improvement of the comparison performance of face recognition, the intelligent application of face-related technology in the security field is becoming more and more mature. At present, it is mainly used in personnel deployment control, real-time alarm, and personnel identity verification. For the application of face recognition comparison, generally, the captured image is compared with a preset library, and then information related to the target person in the library is obtained. [0003] In the prior art, for a captured person, after the face image is recognized, the recognized face image is generally directly structured, and it is mainly used in face recognition, face comparison, and traffic statistics. And other aspects, such as access control, depl...

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
CPCG06F16/583G06F16/5866G06V40/173G06V40/168
Inventor 杨莉陈立力
Owner ZHEJIANG DAHUA 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