Face feature point generation method, data network training method and related devices

A face feature and data network technology, applied in the field of face alignment, can solve the problem of low efficiency of manual labeling of face feature points, and achieve the effect of solving low efficiency

Active Publication Date: 2020-02-07
重庆紫光华山智安科技有限公司
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the embodiments of the present invention is to provide a method for generating face feature points, a face data network training method and related devices, which can automatically generate face feature points and solve the problem of low efficiency of manually marking face feature points

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 feature point generation method, data network training method and related devices
  • Face feature point generation method, data network training method and related devices
  • Face feature point generation method, data network training method and related devices

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0071] Continue to refer to figure 2 , as a specific implementation manner, step S103 includes:

[0072] Sub-step S1031, merging the color channel of the training image and the heat channel of the face heat map of the training image to generate a third fused image.

[0073] In this embodiment, the training image includes a color channel. The color channel can be three channels of R, G, and B, or it can be three channels of R, G, and B plus a transparent channel. The face heat map of the training image includes Heat channel, the training image is fused with the face heat map of the training image, which can be realized by merging the color channel of the training image with the heat channel of the face heat map of the training image.

[0074] In this embodiment, in order to improve the accuracy of the trained GAN network, the original images obtained from different shooting angles can be processed to obtain the original images fused with different shooting angles and the face...

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 invention relates to the technical field of face alignment, and provides a face feature point generation method, a face data network training method and a related device, and theface feature point generation method comprises the steps: obtaining an original image and a noise map of the original image; fusing the original image and the noise map to generate a first fused image; inputting the first fusion image to a pre-trained generative adversarial GAN network to generate a second fusion image, and fusing the second fusion image with the original image and the face heatmap of the original image; and processing the second fusion image to obtain a plurality of face feature points corresponding to the original image. According to the embodiment of the invention, the method solves a problem that the manual marking of the face feature points is low in efficiency through the automatic generation of the face feature points.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of face alignment, and in particular, relate to a method for generating face feature points, a training method for a face data network, and related devices. Background technique [0002] Face recognition refers to computer technology that uses the analysis and comparison of facial visual feature information for identity identification. In recent years, face recognition technology has been widely used in various fields. For example, transportation, commerce, public safety, etc. In order to make life and work more convenient for users, more and more business processes have introduced face recognition technology. [0003] In order to improve the accuracy of face recognition, a large amount of face data is usually used to train a pre-established face recognition network model, and finally a face recognition network model that can accurately recognize faces is obtained. [0004] Face data...

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): G06K9/00G06K9/62G06N3/08
CPCG06N3/08G06V40/168G06F18/25
Inventor 王猛董欢
Owner 重庆紫光华山智安科技有限公司
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