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

Face image processing method and device, image equipment and storage medium

A face image and processing method technology, applied in the information field, can solve problems such as poor transformation effect, and achieve the effect of simple realization, good deformation effect, simple and convenient transformation

Active Publication Date: 2020-10-09
BEIJING SENSETIME TECH DEV CO LTD
View PDF10 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In related technologies, various neural networks are used to transform the face image from the original face to the target face, but practice shows that this transformation is often accompanied by transformations that users do not expect to see, resulting in poor transformation effects

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 processing method and device, image equipment and storage medium
  • Face image processing method and device, image equipment and storage medium
  • Face image processing method and device, image equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0143] In the process of face generation, it is a very practical application to guide face transformation by defining or selecting new attributes, such as specifying to generate a younger photo from a photo of an adult woman.

[0144] Aiming at the problem of face attribute changes, a scheme for generating corresponding face attributes is proposed from the perspectives of face image geometric attributes (facial key point information) and face texture attributes. By separately processing the geometric attributes and the texture attributes, it is possible to better control the transformation model of the facial geometric attributes for different attributes, and convert the first key point information into the second key point information more accurately. Then, the neural network and the second key point information are used to encode the face texture, so as to obtain the second face image after transforming the geometric attributes of the face.

example 2

[0146] refer to Figure 7 As shown, the face image processing method provided by the present disclosure may include:

[0147] First, an attribute transformation module is used to obtain the shape information of the current face image and provide it for different geometric attributes of the face. For the input original image (the original image here is equivalent to the first human face image), through the extraction of 106 facial key point information, combined with the 106 facial key point information to obtain the facial geometric attributes of the human face. The geometric attribute of the face here is the shape information. Then, according to the geometric attributes of the expected generated face, the corresponding position transformation is performed on the current key point information. The generation constraint of face shape transformation is provided by the face geometric attribute transformation parameters, and the face image obtained through the position transform...

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 discloses a face image processing method and device, image equipment and a storage medium. The face image processing method comprises the steps of obtaining first key point information of a first face image; performing position transformation on the first key point information to obtain second key point information conforming to a second human face geometric attribute; wherein the second face geometric attribute is different from a first face geometric attribute corresponding to the first key point information; and performing face texture coding processing by using a neural network and the second key point information to obtain a second face image.

Description

technical field [0001] The present disclosure relates to the field of information technology, and in particular to a face image processing method and device, an image device, and a storage medium. Background technique [0002] During the process of face image processing, the user may need to convert his own face into a face he likes. Specifically, for example, an older face image is converted into a younger face image. In related technologies, various neural networks are used to transform the face image from the original face to the target face, but practice shows that this transformation is often accompanied by transformations that users do not expect to see, resulting in poor transformation effects. Contents of the invention [0003] In view of this, the embodiments of the present disclosure expect to provide a face image processing method and device, an image device, and a storage medium. [0004] The disclosed technical solution is achieved in this way: [0005] The...

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
IPC IPC(8): G06T5/00G06T5/50G06T7/40G06T7/60
CPCG06T5/50G06T7/40G06T7/60G06T2207/20221G06T2207/30201G06T2207/20084G06T5/80G06T9/002G06T11/60G06V40/171G06V10/755G06V40/161G06N3/02G06T3/00
Inventor 吴文岩钱晨孙克强吴潜溢徐园园
Owner BEIJING SENSETIME TECH DEV CO 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