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

Single-person multi-graph feature recognition method and device based on generative adversarial network, and medium

A feature recognition and network technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve problems such as inaccuracy, lack of use of information, insufficient performance, etc., to achieve the effect of improving performance and retaining commonality

Inactive Publication Date: 2020-01-03
SHANGHAI YITU NETWORK SCI & TECH
View PDF14 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The existing technology has a low degree of utilization of information on the collection of face pictures. Basically, only a single piece of information and some simple statistical information are used, and more information is not used. There are problems of inaccuracy and insufficient performance.

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
  • Single-person multi-graph feature recognition method and device based on generative adversarial network, and medium
  • Single-person multi-graph feature recognition method and device based on generative adversarial network, and medium
  • Single-person multi-graph feature recognition method and device based on generative adversarial network, and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] In order to make the object, technical solution and beneficial effects of the present invention more clear, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0031] This embodiment uses the deep learning machine of NVIDIA DGX-1, including 8 Nvidia Tesla-V100 computing cards, each computing card has more than 21 billion transistors, and the core area is 815 square millimeters (other equivalent computing power can also be used computing resources); and use tensorflow training framework (or other deep learning training framework).

[0032] The problem solved in this embodiment is to improve the performance of face set recognition and comparison on the basis of the existing face recognition model. First, obtain the existing face recognition mode...

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 single-person multi-graph feature recognition method and device based on a generative adversarial network, and a medium, and the method comprises the steps: obtaining a facedata set of a single person, and obtaining a feature vector set through extraction; constructing a generative adversarial network, and compressing the feature vector set into a first feature vector through a generator; extracting a second feature vector of the to-be-recognized face picture; and putting the two feature vectors into a discriminator, and judging the probability of having a fusion relationship. The commonality of input features during prediction is reserved, and the difference of recognition is not influenced among the input features; wherein all information in the input featuresis contained as much as possible; and the comparison performance of multiple pictures is improved.

Description

technical field [0001] The invention relates to the technical field of computer image processing, in particular to a method, device and medium for single-person multi-image feature recognition based on generative confrontation networks. Background technique [0002] Face recognition technology has high development prospects and economic benefits in the fields of public security investigation, access control system, target tracking and other civilian security control systems. [0003] Machine learning is one of the branches of artificial intelligence, and it is at the core. Machine learning allows computers to learn to learn, which can simulate human learning behavior, build learning ability, and realize recognition and judgment. Machine learning uses algorithms to analyze massive amounts of data, find patterns from them, complete learning, and use the learned thinking model to make decisions and predict real events. Machine learning is a method of artificial intelligence, ...

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
CPCG06V40/168G06F18/22G06F18/214
Inventor 康燕斌张志齐
Owner SHANGHAI YITU NETWORK SCI & TECH
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