Automatic Generation of Portraits with Multiple Expressions

SONG Hong; HUANG Xiao-chuan; WANG Shu-liang

doi:10.3969/j.issn.0372-2112.2013.08.007

您当前的位置：

首页 >

文章列表页 >

Automatic Generation of Portraits with Multiple Expressions

更新时间：2025-07-16

- Automatic Generation of Portraits with Multiple Expressions
- Acta Electronica Sinica Vol. 41, Issue 8, Pages: 1494-1499(2013)
- 作者机构：
  
  1. 北京理工大学软件学院,北京,100081
  2. 北京理工大学计算机学院,北京,100081
  3. 北京理工大学软件学院,北京,100081
  4. 北京理工大学计算机学院,北京,100081
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China (No.60940024, No.61240010)
- DOI：10.3969/j.issn.0372-2112.2013.08.007
  CLC： TP391.41
- Published：2013
- 稿件说明：
移动端阅览
SONG Hong, HUANG Xiao-chuan, WANG Shu-liang. Automatic Generation of Portraits with Multiple Expressions[J]. Acta Electronica Sinica, 2013, 41(8): 1494-1499.
DOI：

SONG Hong, HUANG Xiao-chuan, WANG Shu-liang. Automatic Generation of Portraits with Multiple Expressions[J]. Acta Electronica Sinica, 2013, 41(8): 1494-1499. DOI： 10.3969/j.issn.0372-2112.2013.08.007.

摘要

肖像是一种能够抓住人物特征

又能隐藏细节

保留个人隐私的艺术表现形式

本文提出一种以中性表情人脸作为输入

自动生成不同表情的肖像算法.首先利用主动形状模型(Active Shape Model

ASM)提取人脸的关键特征点

然后根据统计学习获取的不同表情人脸的FAP(Facial Animation Parameter)规则

对中性人脸的特征点进行变形

生成表情三角网格

将中性人脸图像作为纹理映射到表情人脸网格

生成表情人脸图像

最后利用图像的梯度域信息和非真实感渲染技术

将带表情的人脸生成具有肖像风格的人脸图像.所生成的多表情人脸肖像效果良好

能够应用于网络和报刊杂志等非真实感图形学和数字娱乐等领域中.

Abstract

Portrait is a kind of art form

which can catch the features of a person

hide the details and keep the personal privacy.In this paper

an algorithm for automatic generation of human portrait with multiple expressions is presented.The Active Shape Model is used to extract facial features

and the set of Facial Animation Parameters is used to synthesis the multiple expressions for a neutral face.And with the gradient domain of the image and the Non-Photorealistic Rendering

the portrait-liked face images with multiple expressions can be generated automatically.The generated portraits are effective and vivid.They can be applied in non-photorealistic computer graphics and entertainment

such as video

network

newspapers and magazines.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

⁰