Face attribute recognition method and device

A technology of attribute recognition and first face, applied in the field of image processing, can solve problems such as poor recognition effect

Pending Publication Date: 2020-12-08
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The embodiment of the present application solves the technical problem of poor recognition effect in a face recognition method in the prior art by providing a face attribute recognition method and device, and improves the recognition effect of face recognition

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 attribute recognition method and device
  • Face attribute recognition method and device
  • Face attribute recognition method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0073] This embodiment provides a face attribute recognition method, which is applied to an electronic device, and the electronic device may be a server on the network side, or a terminal device on the user side. Wherein, the terminal device may be: a PC (Personal Computer, personal computer), or a smart phone, or a tablet computer, or a vehicle-mounted computer, or a digital camera, or a game console, or a smart TV, etc. Here, for the What kind of specific device the terminal device is is not specifically limited in this embodiment.

[0074] like figure 1 As shown, the face attribute recognition method includes:

[0075] Step S101; Obtain the first human face sample picture data set and the second human face sample picture data set, wherein, each face sample picture in the first human face sample picture data set carries M human face attribute labels, and the M The face attribute tags correspond to M face attributes respectively, and the M face attributes are different, and...

Embodiment 2

[0130] Based on the same inventive idea, such as figure 2 As shown, the present embodiment provides a face attribute recognition device 200, including:

[0131] The acquiring unit 201 is configured to acquire a first human face sample picture data set and a second human face sample picture data set, wherein each face sample picture in the first human face sample picture data set carries M human face attributes tags, the M face attribute tags correspond to M face attributes respectively, and each face sample picture in the second face sample image data set carries N face attribute tags, and the N face attribute tags correspond to N face attributes, M and N are integers greater than or equal to 1;

[0132] The training unit 202 is configured to perform model training based on the first human face sample picture data set to obtain a first face recognition model, and to perform model training based on the second human face sample picture data set to obtain a second human face r...

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 attribute recognition method, which comprises the steps of obtaining a first human face sample picture data set and a second human face sample picture data set, each human face sample picture in the first human face sample picture data set carrying M human face attribute tags, wherein each face sample picture in the second face sample picture data set carries Nface attribute tags; performing model training based on the first face sample picture data set to obtain a first face recognition model, and performing model training based on the second face samplepicture data set to obtain a second face recognition model; and the first face recognition model and the second face recognition model are fused to construct a target face recognition model, and the target face recognition model can be used for recognizing the M + N face attributes in the target picture. According to the invention, the recognition effect of face recognition is improved. Meanwhile,the invention discloses a face attribute recognition device.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a face attribute recognition method and device. Background technique [0002] Face recognition technology is widely used in photography, security, target tracking and other scenarios. By analyzing the user's face image, various face attributes of the user can be determined. Nowadays, when performing face recognition, there are few face attributes that can be recognized, resulting in poor recognition effect of face recognition. This is an urgent problem to be solved at present. Contents of the invention [0003] The embodiment of the present application solves the technical problem of poor recognition effect in a face recognition method in the prior art by providing a face attribute recognition method and device, and improves the recognition effect of face recognition. [0004] In the first aspect, the present application provides the following technical soluti...

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): G06K9/00G06K9/62
CPCG06V40/172G06F18/214
Inventor 李阳光刘慧慧周泽南苏雪峰许静芳
Owner BEIJING SOGOU TECHNOLOGY DEVELOPMENT 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