Face clustering method and device

A clustering method and clustering technology, applied in the field of face recognition, can solve the problem of clustering wrong photo class A and photo class B, and achieve the effect of improving accuracy

Active Publication Date: 2019-04-26
XIAOMI INC
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problem of face clustering, when there are other face photos corresponding to the wrong faces in photo class A in photo class B, it is possible to mistakenly cluster photo class A and photo class B into the same photo The problem in the class, the present disclosure provides a face clustering method and device

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 clustering method and device
  • Face clustering method and device
  • Face clustering method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0094] Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatuses and methods consistent with aspects of the present disclosure as recited in the appended claims.

[0095] When clustering face photos, the method of full clustering or incremental clustering can be used for clustering.

[0096] The process of full clustering is as follows:

[0097] The first step is to initialize all face photos that need to be clustered, obtain m face information in the face photos, and use the obtained m face information as m photo categories;

[0098] The secon...

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 disclosure discloses a face clustering method and device, belonging to the field of face recognition. The face clustering method includes: obtaining the first photo category and the second photo category; clustering the face photos in the first photo category to obtain at least one photo subcategory; The class is determined as the correct face subclass; calculate the distance between the correct face subclass and the second photo class; if the distance is less than the threshold, the first photo class and the second photo class are clustered into the same photo class; solve If there are other face photos corresponding to the wrong faces in the first photo class in the second photo class, it is possible to mistakenly cluster the first photo class and the second photo class into the same photo class; It achieves the effect of avoiding a photo category during clustering because there are a few wrong face photos, introducing more clustering errors of wrong face photos, and improving the accuracy of clustering.

Description

technical field [0001] The present disclosure relates to the field of face recognition, in particular to a face clustering method and device. Background technique [0002] The face clustering method is a method of clustering similar faces based on facial features. In a photo management program, photos corresponding to different faces can be clustered by a face clustering method, thereby forming different photo albums. [0003] A face clustering method in the related art, comprising: first, each face photo is initialized as a photo class; second, according to the feature vector of each face photo, calculate the difference between any two photo classes Third, if the distance between the two photo classes is less than the threshold, then cluster the two photo classes into the same photo class; iterate the second and third steps above. However, in the clustering process, if there are several wrong face photos in photo class A, and there are many other face photos corresponding...

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 Patents(China)
IPC IPC(8): G06K9/00
CPCG06V40/172
Inventor 陈志军李明浩侯文迪
Owner XIAOMI INC
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