Method for modeling personalized human face basedon orthogonal image

An orthogonal image and modeling method technology, applied in the field of personalized face models, can solve the problem of single angle of personalized face models

Inactive Publication Date: 2007-04-04
SHENZHEN TECHVISUM TECH LTD
View PDF0 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since this method only uses one frontal image, the angle of the personalized face model obtained is relatively single.

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 for modeling personalized human face basedon orthogonal image
  • Method for modeling personalized human face basedon orthogonal image
  • Method for modeling personalized human face basedon orthogonal image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] Figure 1 is an orthogonal face image after normalization.

[0023] First, use a common digital camera to take two orthogonal face images, one frontal face image and one side face image, and the two images must be strictly orthogonal, that is, the angle between the two shots must be 90° Spend.

[0024] 1) Image normalization and general grid projection

[0025] Perform normalization processing on the captured photos, that is, perform normalization processing based on the fact that the height of the face in the face photos taken within the same time period does not change.

[0026] a. Assume that the height of the face in the frontal face image is FrontHeight, and the height of the face in the side face image is SideHeight. Let R=FrontHeight / SideHeight. Scaling and transforming the side face images according to R can make the height of the face images of the two orthogonal images consistent. In this way, the deviation between the two face images caused by the differen...

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 fast human face module building method based on quadrature images includes: take two pictures from the front and side face; normalize the two pictures; make projective grid of the two orthogonal graphs through a general face grid module; get the best matching index of the face graph and the projective grid on the character points; then apply it to the project grid and radial functional interpolation to get an accurate total matching points; resume the three-dimensional data from the matched projective grid to get the face grid module; finally texture mapping the grid module to get the final unique face module.

Description

technical field [0001] The invention relates to the technical field of three-dimensional data modeling, in particular to a method for obtaining a personalized human face model from two orthogonal human face images. Background technique [0002] Face modeling has attracted the attention of researchers due to its wide application. One of the most important directions is personalized modeling. Due to its wide application, it has attracted more and more researchers in face modeling. Pay attention to. [0003] There are currently many methods for personalized modeling. In terms of data sources, modeling can be performed from three-dimensional data, or from multiple images, such as orthographic images. Alternatively, modeling can be done from video. The present invention mainly focuses on the personalized modeling process starting from the orthogonal image. [0004] There are two main approaches for personalized modeling starting from orthogonal images. The first is to select c...

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): G06T17/00
Inventor 陶建华李永林
Owner SHENZHEN TECHVISUM TECH LTD
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