Facial Expression Image Synthesis by Using 2D Model with Uncoupled Geometric and Textural Information

林学■; 洪鹏宇

您当前的位置：

首页 >

文章列表页 >

Facial Expression Image Synthesis by Using 2D Model with Uncoupled Geometric and Textural Information

更新时间：2025-12-08

- Facial Expression Image Synthesis by Using 2D Model with Uncoupled Geometric and Textural Information
- Acta Electronica Sinica Issue 11, Pages: 124-127(1998)
- 作者机构：
  
  1. 清华大学计算机科学与技术系!北京
  2. 100084
- 作者简介：
- 基金信息：
- DOI：
  CLC： TN919.
- Published：1998
- 稿件说明：
移动端阅览
[1]林学■,洪鹏宇.基于2D几何与纹理信息分离模型的表情分析与合成[J].电子学报,1998(11):124-127.

林学■, 洪鹏宇. Facial Expression Image Synthesis by Using 2D Model with Uncoupled Geometric and Textural Information[J]. Acta Electronica Sinica, 1998, (11): 124-127.
[1]林学■,洪鹏宇.基于2D几何与纹理信息分离模型的表情分析与合成[J].电子学报,1998(11):124-127. DOI：

林学■, 洪鹏宇. Facial Expression Image Synthesis by Using 2D Model with Uncoupled Geometric and Textural Information[J]. Acta Electronica Sinica, 1998, (11): 124-127. DOI：

摘要

本文提出一种用于特定人逼真表情图像合成的新方法该方法利用二维网格描述脸部呈现不同表情时的几何变化，并使用主分量分析方法将该网格序列用参数化模型表示，从而极大地压缩了数据在重构表情图像时利用参考帧提供的场景纹理信息，结合网格参数模型提供的几何信息，使用图像卷曲与插值技术，生成逼真表情图像．目前使用该方法对人脸下半部表情图像分析及合成进行了初步的实验、实验结果表明了该种方法的有效性

Abstract

A novel image synthesis method of human face with various expressions is presented. In this method the geometrical and textural information implied in expressions are uncoupled. A 2D grid is used to extract the geometric variation of human face with different expressions. A Principal Component Analysis （PCA） is used so that the grid Sequences can be expressed by a few eigengrids. Therefore a parametric model can be developed to control the expressions effectively. During the image synthesis process

image warping and morphing techniques are employed to combine the textural information

supplied by a few reference image frames with the geometrical information

represented in the grid model

so that vivid facial images with different expressions can be preduced. The method presented in this paper has been investigated with some preliminary experiments. Its effectiveness has been proved.

关键词

Keywords

references

Views

104

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A Novel ICA Algorithm for Face Recognition Based on Wavelet Decomposition and Robust Estimation

Blind Source Separation

Frequency Hopping Signal Detection over the Short-Wave Channel

Related Author

AN Gao-yun

RUAN Qiu-qi

ZHANG Xian-da

BAO Zheng

LI Shuo

LI Tian-yun

Related Institution

Institute of Information Science, Beijing Jiaotong University

Key Laboratory for Radar Signal Processing,Xidian University

College of Information Engineering, Information Engineering University

⁰