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

Expression similarity measurement method and device

A measurement method and similarity technology, applied in the field of human-computer interaction, can solve the problems of depicting subtle changes in expressions and weak local details, and achieve good robustness

Inactive Publication Date: 2017-12-05
ANQING NORMAL UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The invention discloses a method and device for measuring facial expression similarity, which are used to solve the problems existing in the prior art in describing subtle changes in expressions and weak local details

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
  • Expression similarity measurement method and device
  • Expression similarity measurement method and device
  • Expression similarity measurement method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings, but the present invention can be implemented in many different ways defined and covered by the claims.

[0053] figure 1 Shows a flow chart of the method for measuring expression similarity according to an embodiment of the present invention.

[0054] See figure 1 As shown, the expression similarity measurement methods include:

[0055] S101: Obtain the shape information of the feature points in the target face area by using chain code encoding;

[0056] S103: Measure non-adjacent feature points in the same area in the target face area and feature points between different areas in the target face area to obtain deformation information;

[0057] S105: Perform weighting processing on the shape information and the deformation information in the two target facial regions to obtain the expression similarity distance of the two target facial regions;

[0058] S107: Acq...

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 device for measuring expression similarity based on geometric features, which are used to improve the ability to describe subtle changes and local details of expressions, and to find the most similar expressions. The expression similarity measurement method includes: using chain code coding to obtain the shape information of the feature points in the target facial area; measuring the non-adjacent feature points in the same area in the target facial area and the difference in the target facial area. Obtaining deformation information of inter-regional feature points; adaptively weighting the shape information and the deformation information in the two target facial regions to obtain the expression similarity distance of the two target facial regions; and according to the expression similarity distance Obtain the expression similarity measurement results of the two target facial regions. The facial expression similarity measurement method of the present invention has better robustness to the expression descriptions of different types and different intensities, and especially has advantages in the measurement of the similarity of mouth shape, mouth opening and closing range, and the like.

Description

Technical field [0001] The present invention relates to the technical field of human-computer interaction, and more specifically, to a method and device for measuring expression similarity. Background technique [0002] With the deepening and rapid development of human-computer interaction, facial expression analysis has become a hot spot in current research on emotional computing. As performance-driven is widely used in games, movies, etc., in recent years, researchers have explored various methods to find similar expressions to synthesize highly realistic and natural expression animations. Ira Kemelmacher-Shlizerman et al. used LBP to extract the texture features of the eyes and mouth regions closely related to expressions, and used the chi-square distance to measure the similarity to achieve different human expression mapping, which can better extract local features but portray small changes in expression details There are flaws from time to time. Abhina et al. introduced th...

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 Patents(China)
IPC IPC(8): G06K9/00G06K9/46
Inventor 黄忠刘娟金中朝江巨浪
Owner ANQING NORMAL UNIV
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