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

Face image automatic generation method based on face contour

A face image, automatic generation technology, applied in the field of computer vision, can solve problems such as difficult to ensure quality, uneven distribution of data sets, unsatisfactory training results, etc., to achieve detailed face feature information and ensure accuracy Effect

Pending Publication Date: 2020-11-13
BEIJING ELECTRONICS SCI & TECH INST
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The existing solution is to use web crawler technology to collect face pictures on the Internet, but it is difficult to guarantee the quality of the picture data sets collected by this method, and the distribution of data sets is often uneven, resulting in unsatisfactory training results

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 image automatic generation method based on face contour
  • Face image automatic generation method based on face contour
  • Face image automatic generation method based on face contour

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0050] Generative Adversarial Networks: Generative Adversarial Networks, GAN is a deep learning model and one of the most promising methods for unsupervised learning on complex distributions in recent years. The model produces quite good output through the mutual game learning of (at least) two modules in the framework: Generative Model and Discriminative Model.

[0051] StyleGAN: Drawing on the idea of ​​style transfer, image generation is regarde...

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 relates to a face image automatic generation method based on a face contour. The method comprises the following steps: step 1, establishing and preparing a data set; step 2, designing aface image generation model based on an image mask mask; 3, training a mask-based face image generation model; 4, performing input data improvement on the face image generation model in the step 3 byusing mapping; step 5, training a face image generation model based on mapping; and step 6, automatically generating a face image based on the trained face image generation model.

Description

technical field [0001] The invention is a method for automatically generating a face image based on a face profile, which belongs to the field of computer vision. Background technique [0002] In the field of image generation, face generation is a big challenge, and there are also very broad application scenarios. In recent years, research on related technologies of human faces has been very hot. Artificial intelligence technologies such as face detection, face recognition, and image aesthetics play a pivotal role in realizing the integration of the Internet of Things. However, the lack of face datasets also greatly restricts the development of related deep learning technologies such as face detection. Although it is recognized that there are some face-specific datasets, the existing datasets are often not comprehensive enough for a wide variety of face-related techniques. Most datasets are European and American faces, which restricts the training of face-related models i...

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): G06N3/04G06T3/40G06T5/00G06T7/13G06T17/00G06K9/62
CPCG06T3/4038G06T7/13G06T17/00G06N3/045G06F18/214G06T5/70Y02T10/40
Inventor 金鑫李忠兰于明学李晓东肖超恩
Owner BEIJING ELECTRONICS SCI & TECH INST
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