Method and device for synthesizing facial expression image

A facial expression and facial expression technology, applied in the field of image processing, can solve the problem of unnatural facial expression image effects

Pending Publication Date: 2018-07-06
BEIJING SAMSUNG TELECOM R&D CENT +1
View PDF6 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the above prior art, if the analyzed expression feature α belongs to category C1, when k is much greater than 1 or very close to 0, kα is likely to

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
  • Method and device for synthesizing facial expression image
  • Method and device for synthesizing facial expression image
  • Method and device for synthesizing facial expression image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] In order to make the technical problem solved by the present invention, the technical scheme adopted and the technical effect achieved clearer, the following will combine Figure 1-Figure 9 The technical solutions of the present invention will be further described in detail. Obviously, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts fall within the protection scope of the present invention.

[0028] Please refer to figure 2 , which is a method flowchart of the first embodiment of the method for synthesizing facial expression images of the present invention.

[0029] S101. Obtain expression features of at least two reference facial expression images.

[0030] The synthesis method of the present invention can be applied to training expression recognition models, and can also be appli...

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 method and a device for synthesizing a facial expression image. The method comprises the steps that the expression features of at least two reference facial expression imagesare acquired; interpolation is performed on the expression features of at least two reference facial expression images so as to obtain new expression features; and the target facial expression imageis adjusted according to the new expression features so as to form the new facial expression image. According to the technical scheme, interpolation is performed on different expression features to obtain new expression features instead of directly amplifying or reducing the existing expression features, and the new facial expression image is obtained according to the new expression features. According to the technical scheme, the synthesized facial expression image effect is natural and the facial expression image is closer to the real expression image.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method and device for synthesizing facial expression images. Background technique [0002] Facial expression recognition is widely used in fields such as entertainment, security, human-computer interaction and social network analysis. In order to recognize facial expressions, it is necessary to train an expression recognition model, which requires a large number of expression images as training data. However, the cost of collecting expression images is high and there are many limitations. In order to solve this problem, a large number of expression images are proposed to be synthesized to train the expression recognition model. [0003] Existing emoticon image synthesis methods are mainly divided into two categories. The first type of method directly operates the facial expression image, and modifies the facial expression image by moving the pixel position of the fa...

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): G06T7/33G06K9/00
CPCG06T2207/30201G06T2207/20212G06V40/174G06T3/4007G06T1/0007G06V40/169
Inventor 钱德恒郭天楚金暎星张辉徐静涛兪炳仁韩在濬崔昌圭
Owner BEIJING SAMSUNG TELECOM R&D CENT
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