Human face collection recognition method and system implementing same

A recognition method and face collection technology, applied in the field of face recognition, can solve problems such as inability to identify events, and achieve the effect of improving the accuracy of comparison

Inactive Publication Date: 2016-12-07
广东金杭科技有限公司
View PDF5 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The anti-terrorist department has been studying countermeasures, based on the fact that there is not enough police force to monitor; even through real-time monitoring by people, it is still impossible to identify the incident in a timely and effective manner

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
  • Human face collection recognition method and system implementing same
  • Human face collection recognition method and system implementing same
  • Human face collection recognition method and system implementing same

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] refer to figure 1 As shown, the present invention provides a face collection and recognition method, which specifically includes a step of inputting photo information of a person and a step of comparing.

[0051] The steps of inputting the personnel photo information include:

[0052] Step 1: using an image acquisition module to collect photo information of personnel, the collected photos include a frontal photo, three left face photos and three right face photos;

[0053] Step 2: adopt input module to input the photo information collected in a database, this database is as at least one dedicated data platform (such as the provincial-level dedicated data platform of the public security system or the dedicated database built by the bank, etc., which can be connected as required Different data platforms do not limit the implementation of the present invention) sub-database, which matches with the person information stored in the dedicated data platform; wherein the photo...

Embodiment 2

[0097] The present invention also provides a multi-dimensional modeling and comparison system for face recognition realizing the above method, including:

[0098] The image collection module 10 is used to collect photo information of personnel, and the photos collected include a frontal photo, three left side face photos and three right side face photos;

[0099] The entry module 11 is used to enter the collected photo information into a database, wherein the photo information of each person is used as an index module;

[0100] The first collection module 1, the first collection module 1 is used for real-time acquisition of the profile photo of the target person;

[0101] Comparing module 2, described comparing module 2 is used for carrying out similarity comparison with the profile photo of the profile picture that the first collection module 1 obtains and any index template 40 in the database 4 as auxiliary label, judges whether There is an avatar photo with a preset first ...

Embodiment 3

[0109] Such as Figure 4 As shown, the present invention also provides specific embodiments of case detection combined with the above system.

[0110] In this embodiment, the above-mentioned system is used for arresting criminals and destroying criminal groups.

[0111] Since in the system establishment process, the image collection module 10 has collected the photo information of all household registration personnel, and the photos collected include a front photo, three left side face photos and three right side face photos; and input by the input module 11 In the database 4, that is, in the index template 40 in the database 4, the existing character information of the criminal gang member A is stored, specifically including the existing avatar photo (the front face photo as the main label and six side face photos as the auxiliary label ) and the corresponding person identity information.

[0112]When a certain member A entered the monitoring range of any first collection m...

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 human face collection recognition method and system. The method comprises the following steps: collecting the information of seven pictures of a person; 2, enabling the picture information to be recorded in a database; 3, enabling a first collection module to obtain the head portrait picture of a target person in real time; 4, enabling a comparison module to carry out the similarity comparison of the head portrait picture obtained at step 3 with a side face picture, serving as an auxiliary label, in any index template in the database, and judging whether there is a head portrait picture with a preset first threshold value or not: judging that the head portrait picture of the target person and an existing head portrait picture belong to the same person if there is the head portrait picture with the preset first threshold value, and enabling an extraction module to extract a front face picture which is corresponding to the side face image serving as the auxiliary label and serves as a main label, or else, independently building a new index template. The method employs the seven pictures as the index templates, can enable a non-front human face to have a matching degree, and can improve the comparison accuracy of human faces.

Description

technical field [0001] The present invention relates to the technical field of face recognition, and more specifically, relates to a face collection and recognition method and a system for realizing the method. Background technique [0002] Face recognition is a popular computer technology research field. It belongs to biometric identification technology, which is to distinguish individual organisms by their biological characteristics (generally referring to people). The biological characteristics studied by biometric identification technology include face, fingerprint, palm print, iris, retina, voice (voice), body shape, etc. Among them, only facial features are the most intuitive, reliable and accurate, and using facial features for identity verification is the most natural and direct means. Compared with other human biometrics, face feature recognition can conveniently and effectively verify the identity of the subject without the cooperation of the subject's behavior, a...

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): G06K9/00
CPCG06V40/166G06V40/172
Inventor 吴建忠
Owner 广东金杭科技有限公司
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