Face recognition database construction method, face recognition method, device and equipment

A face recognition and database technology, applied in the field of face recognition database construction, can solve the problems of complicated, inefficient and difficult face recognition process

Inactive Publication Date: 2019-03-05
ADVANCED NEW TECH CO LTD
View PDF5 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, if you want to obtain more accurate identification results through the above local sensitive hashing scheme, you need to find one or some hash functions for a large amount of data, so that after the hash map transformation, the adjacent data in the original data space falls into In the

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 recognition database construction method, face recognition method, device and equipment
  • Face recognition database construction method, face recognition method, device and equipment
  • Face recognition database construction method, face recognition method, device and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0112] Such as figure 1 As shown, the embodiment of the present application provides a method for constructing a face recognition database. The execution subject of the method can be a terminal device or a server. The terminal device can be a personal computer, etc., and the server can be an independent server or It is a server cluster composed of multiple servers. In order to improve the construction efficiency of the face recognition database in the embodiments of the present application, the execution subject of the method takes a server as an example for detailed description. The method may specifically include the following steps:

[0113] In step S102, the image feature space of the multiple face images is split into multiple face feature subspaces.

[0114] Among them, multiple facial images may be multiple facial images of different users, and the number of facial images for any user may be one or multiple, such as 10 or 15 facial images. The image feature space can be a ...

Embodiment 2

[0136] Such as Figure 4 As shown, the embodiment of the present application provides a face recognition method. The execution body of the method may be a server or the method may be implemented by a terminal device and a server. The terminal device may be a personal computer, etc., and the server may be an independent A server in the, can also be a server cluster composed of multiple servers. In order to improve the construction efficiency of the face recognition database in the embodiments of the present application, the execution subject of the method takes the server as an example for detailed description. For the implementation by the terminal device and the server according to the situation, you can refer to the following related content. Repeat it again. The method specifically includes the following:

[0137] At present, face recognition is a new way for users to verify their identities. Face recognition technology has been used more and more widely due to its higher rec...

Embodiment 3

[0198] The above is the face recognition method provided by the embodiment of the application. Based on the same idea, the embodiment of the application also provides a device for constructing a face recognition database, such as Figure 7 Shown.

[0199] The device for constructing the face recognition database includes: a feature space splitting module 801, a clustering module 802, and a database construction module 803, wherein:

[0200] The feature space splitting module 801 is configured to split the image feature space of multiple face images into multiple face feature subspaces;

[0201] The clustering module 802 is used to cluster each face feature subspace to obtain cluster center point information and data category information of each face feature subspace;

[0202] The database construction module 803 is used to construct a face recognition database according to the cluster center point information of each face feature subspace and the category information of the data.

[020...

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 application discloses a face recognition database construction method, a face recognition method, a device and equipment. The face recognition database construction method comprises the following steps of dividing an image feature space of a plurality of human face images into a plurality of human face feature subspaces; clustering each facial feature subspace to obtain the clustering center point information and the data category information of each facial feature subspace; constructing the face recognition database according to the clustering center point information and the data category information of each face feature subspace. By utilizing the embodiment of the application, the face recognition process can be realized simply and easily, the face recognition efficiency can be improved, and the resource consumption can be reduced.

Description

Technical field [0001] This application relates to the field of face recognition technology, and in particular to a method for constructing a face recognition database, a face recognition method, device and equipment. Background technique [0002] Face recognition technology has been used more and more widely because of its higher and higher recognition rate and convenience of application, such as video surveillance, access control, smart ID card, etc. At present, with the popularity of cameras, more and more scenarios such as unattended self-service business scenarios and security scenarios need to identify the identity of the user appearing in the camera without the user's perception. [0003] At present, the local sensitivity hashing scheme is a mainstream fast approximate nearest neighbor search technology for massive high-dimensional data. Its principle is to transform two adjacent data points in the original data space through the same mapping or projection transformation. ,...

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): G06K9/00G06K9/62
CPCG06V40/168G06V40/172G06F18/23
Inventor 江南
Owner ADVANCED NEW 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