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

Human face countenance synthesis method based on dense characteristic corresponding and morphology

A technology of facial expressions and dense features, applied in image data processing, instruments, calculations, etc., can solve the problems of insufficient vividness of expressions, achieve the effects of enhancing realism, improving robustness, and improving processing speed

Inactive Publication Date: 2006-11-29
XI AN JIAOTONG UNIV
View PDF0 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

The technical effect of this patented technology allows for efficient separation and analysis of different types of data about faces or their appearance during imagery. It achieves these goals through decomposition/representation techniques like histograms, which help identify variations between shapes and colors within an object being imaged. By combining specific patterns together, it created more accurate representations of complex objects such as humans. Overall, this technique enhances how we perceive things around us better than just looking back over them themselves.

Problems solved by technology

The technical problem addressed in this patents relates to improving facial animation quality through combining facial movements from multiple sources into single ones without requiring extensive effort for interpretation. Existing approaches involve manually selecting parameters and performing complex calculations, making them time-consuming and prone to errors due to variations between individuals' appearance patterns.

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
  • Human face countenance synthesis method based on dense characteristic corresponding and morphology
  • Human face countenance synthesis method based on dense characteristic corresponding and morphology
  • Human face countenance synthesis method based on dense characteristic corresponding and morphology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] refer to figure 1 As shown, the expression synthesis algorithm based on dense feature correspondence is divided into two parts: offline and online, including various steps:

[0031] Suppose the reference image is I Average , it is known that the neutral (natural) expression image of a specific face is A, the specific expression image is A′, the neutral (natural) expression image of the face to be transformed is B, and a face with an expression similar to A′ is synthesized Image B'. Specific steps are as follows:

[0032] 1) According to the reference image I Average Decompose the image of A, A' and B to obtain the corresponding image expressions (shpA, texA), (shpA', texA') and (shpB, texB), where shp represents the shape vector, and tex represents the texture vector ;

[0033] 2) Calculate the new shape vector after expression transformation: shpB'=shpB+ΔShp, wherein ΔShp=shpA'-shpA;

[0034] 3) Calculate the new texture vector after expression transformation: t...

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

A method for synthesizing human face expression based on dense feature correspondence and morphology includes realizing effective separation of position information and grey scale information of human face feature in image by using decomposition-presentation of human face image and arresting shape and vein difference in expression variation with no interference to each other, utilizing morphological means to pick up black-white spot noise region and mapping said difference on new human face image as well as using linear interpolation mode to filter out noise for finalizing expression synthesis.

Description

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

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
Owner XI AN JIAOTONG 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

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