Three-dimensional human face modelling approach based on front side image

A technology of 3D face and modeling method, which is applied in the field of 3D face modeling based on front and side images, and can solve the problems of high computational cost and low work efficiency

Inactive Publication Date: 2009-01-07
SHANGHAI NORMAL UNIVERSITY
View PDF0 Cites 42 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

According to this, there are many kinds of 3D modeling techniques at present, but most of them are based on interactive methods, which require professionals to select key points. Therefore, the work efficiency is low. At the same time, interactive 3D modeling techniques Most of them need to select hundreds of key points to achieve visually satisfactory results. Therefore, this method still has the problem of high computational overhead.

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
  • Three-dimensional human face modelling approach based on front side image
  • Three-dimensional human face modelling approach based on front side image
  • Three-dimensional human face modelling approach based on front side image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0008] The present invention will be further described below in conjunction with accompanying drawing

[0009] 1 Establish a general face grid parameterized by Candide

[0010] The present invention adopts Ahlberg to release in 2001 the face model of the latest version Candide-3. This version of the face model has reached the unification with the MPEG-4 standard. The model includes 113 key points and 168 triangular patches. The control parameters are composed of static parameters (Facial Definition Parameters, FDP) and dynamic parameters (Facial Animation Parameters, FAP). The Candide-3 model used in the present invention is composed of 113 vertices and 184 triangular faces.

[0011] 2 Conversion of general face model to specific face model

[0012] 2.1 Image preprocessing

[0013] In practice, the two obtained images (photos) cannot be of the same size, so before the feature points are marked, the frontal profile images (photos) must be normalized first, so that the head s...

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 relates to the technical field of computer graphics and image processing, in particular to a 3D human face modeling method based on front silhouette, which mainly models the 3D human face in a fully automatic manner. The method comprises the following steps: a general human face grid model is built by 113 feature points and 184 tri patch information arrays which are connected with the 113 feature points based on Candide parameterization; 2D position information and depth information of a specific human face are determined by virtue of human eyes location algorithm and side nose tip location algorithm by inputting two 2D images, the general face model is modified and transformed into a specific human face model; an interpolating is calculated for the human body patches by Delaunay Triangulation Technology and texture mapping is carried out by the Bilinear Interpolation Technology, thus causing the human face image to be appeared more delicate and accurate; and the method solves the problems such as low efficiency, high calculation expense, and the like, existing in the prior art.

Description

technical field [0001] The invention relates to the technical field of computer graphics and image processing, in particular to a method for modeling a three-dimensional human face based on front profile images. Background technique [0002] With the continuous development of computer graphics, three-dimensional production technology has also been developed rapidly and is widely used in various fields of social production and life. Nowadays, the rapid development of computer network and its entry into our daily life provide unlimited living space for the development and application of 3D technology. With the increasing popularization of network applications, people tend to communicate more and more in the virtual network world, from face-to-face conversations, phone calls, network chats, and mutual e-mails. Human face is an important channel for human to communicate with each other, and it is the carrier of complex expressions and languages ​​such as happiness, anger, sadne...

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): G06T17/00G06T17/20G06T15/00
Inventor 马燕祁抗抗王映波
Owner SHANGHAI NORMAL UNIVERSITY
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