Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Face attribute recognition system based on deep learning

An attribute recognition and deep learning technology, applied in the field of face attribute recognition system, can solve the problems of inaccurate judgment of new attributes and lack of learning ability.

Active Publication Date: 2021-11-12
GLOBALTOUR GROUP LTD
View PDF8 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the system does not have the ability to learn. When a new attribute requirement is added, the judgment of the new attribute will not be accurate enough

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 system based on deep learning
  • Face attribute recognition system based on deep learning
  • Face attribute recognition system based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] This embodiment provides a face attribute recognition system based on deep learning, combined with figure 1 , including an input module, an analysis module, a feeding module, a learning module and an output module, the input module is used to input an image, the image is processed by the analysis module and then transmitted to a result pool, the output module Obtain the face attributes in the image according to the result pool, the feeding module contains images with face attributes, and the learning module is used to adjust the parameters of the analysis module;

[0037] The analysis module includes a dispersion unit and an aggregation unit, the dispersion unit processes the input image and sends the image to one of several output terminals, and the aggregation unit is used to combine the output terminal with the The result pool establishes a corresponding relationship, and different result pools have different face attributes;

[0038] The use of the system includes ...

Embodiment 2

[0056] This embodiment includes all the content of Embodiment 1, and provides a face attribute recognition system based on deep learning. The system includes an input module, an analysis module, a feeding module, a learning module and an output module. The input module It is used to input an image, and the image is transmitted to a result pool after being processed by the analysis module, and the output module obtains the face attributes in the image according to the position of the result pool, and the feeding module uses a large number of The graphics of the existing attributes are sent to the input module, and the learning module compares the output results of the output module with the known attributes of the pictures, and adjusts the parameters of the analysis module according to the comparison results;

[0057] combine figure 2 and image 3 , the analysis module includes a dispersion unit and an aggregation unit, the dispersion unit includes a large number of forks, th...

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 provides a face attribute recognition system based on deep learning. The system is characterized in that the system comprises an input module, an analysis module, a feeding module, a learning module and an output module, wherein the input module is used for inputting an image, the image is processed by the analysis module and then is transmitted to a result pool, the output module obtains face attributes in the images according to the result pool, the feeding module contains the images with the face attributes, and the learning module is used for adjusting parameters of the analysis module. According to the system, the type of the face attribute and the corresponding sub-attribute can be automatically set according to the requirement, the corresponding analysis module is generated according to the set attribute, and the more the number of the branching devices in the analysis module is, the higher the learning efficiency is, and the higher the judgment accuracy is.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a face attribute recognition system based on deep learning. Background technique [0002] Face recognition is a biometric technology for identification based on human facial feature information. A camera or camera is used to collect images or video streams containing human faces, and automatically detect and track human faces in the images, and then detect A series of related technologies for face recognition, usually also called portrait recognition and face recognition, based on databases have a high accuracy rate for face recognition, but for attribute recognition of stranger faces without databases, there is still a problem. in development stage. [0003] Many face recognition systems have been developed now. After a large number of searches and references, we found that the existing recognition systems are like the systems disclosed in the publicatio...

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): G06K9/00G06K9/62G06N20/00
CPCG06N20/00G06F18/22
Inventor 张卫平丁烨张浩宇张伟
Owner GLOBALTOUR GROUP LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com