多表情人脸肖像的自动生成

doi:10.3969/j.issn.0372-2112.2013.08.007

电子学报 ›› 2013, Vol. 41 ›› Issue (8): 1494-1499.DOI: 10.3969/j.issn.0372-2112.2013.08.007

多表情人脸肖像的自动生成

宋红¹, 黄小川², 王树良¹

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

收稿日期:2012-10-25 修回日期:2013-04-26 出版日期:2013-08-25
- 作者简介:
- 宋红 女,1977年生于陕西西安.博士,副教授.研究方向为计算机图形图像处理与模式识别. E-mail:anniesun@bit.edu.cn 黄小川 男,1988年生于湖南常德.硕士研究生,研究方向为计算机图形图像处理.
- 基金资助:
- 国家自然科学基金 (No.60940024,No.61240010)

Automatic Generation of Portraits with Multiple Expressions

SONG Hong¹, HUANG Xiao-chuan², WANG Shu-liang¹

1. School of Software, Beijing Institute of Technology, Beijing 100081, China;
2. School of Computer Science and Technology, Beijing Institute of Technology, Beijing 100081, China

Received:2012-10-25 Revised:2013-04-26 Online:2013-08-25 Published:2013-08-25
- Supported by:
- National Natural Science Foundation of China (No.60940024, No.61240010)

摘要/Abstract

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.

关键词: 人脸肖像, 多表情, 特征形变

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.

Key words: portrait, multiple expression, feature deformation

中图分类号:

TP391.41

宋红, 黄小川, 王树良. 多表情人脸肖像的自动生成[J]. 电子学报, 2013, 41(8): 1494-1499.

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

参考文献

[1] Sherstinsky A,Picard R.M-Lattice:From morphogenesis to image processing[J].IEEE Transactions on Image Processing.1996,5(7):1137-1150.
[2] Li Y,Kobatake H.Extraction of facial sketch image based on morphological processing[A].Proceedings of the 1997 IEEE International Conference on Image Processing[C].Piscataway,NJ:IEEE,1997.3:316-319.
[3] Hong Chen,Ziqiang Liu et al.Example-based composite sketching of human portraits[A].Proceeding of the 3^rd International Symposium on Non-photorealistic Animation and Rendering[C].New York,NY:ACM,2004.95-153.
[4] Pei-Ying Chiang,Wen-Hung Liao,Tsai—Yen Li.Automatic caricature generation by analyzing facial features[A].In Proceedings of Asian Conference on Computer vision[C].2004,Korea.
[5] P W Hsu,Y Chang,C K.Hsieh,et al.Facial expression cloning:using expressive ratio image and FAP to texture conversion[A].Proceedings of the 4th International Conference on Information,Communications and Signal Processing[C].Piscataway,NJ:IEEE,2003.2:694-698.
[6] B Park,H Chung,et al.A feature based approach to facial expression cloning[J].Computer Animation and Virtual Worlds,2005,16:291-303.
[7] T F Cootes,C J Taylor,et al.Active shape models their training and applications[J].Computer Vision and Image Understanding,1995,61(1):38-59.
[8] Delaunay Triangulation.[OL] http://en.wikipedia.org/wiki/Delaunay_triangulation,2012-10-25.
[9] Tekalp MA,Ostermann J.Face and 2-D mesh animation in MPEG-4[J].Signal Processing:Image Communication,2000,15:387-342.
[10] Matthew N Dailey,Carrie Joyce,et al.Evidence and a computational explanation of cultural differences in facial expression recognition[J].Emotion,2010,10(6):874-893.
[11] Pravin Bhat C.Lawrence Zitnick,et al.Gradientshop:A gradient-domain optimization framework for image and video filtering[J].ACM Transactions on Graphics,2010,29(2):10.1-10.4.
[12] 王磊,邹北骥,等.一种改进的提取人脸面部特征点的AAM拟合算法[J].电子学报,2006,34(8):1424-1427. Wang Lei,Zou Beiji,et al.An improved AAM fitting algorithm for extracting human facial features[J].Acta Electronica Sinica,2006,34(8):1424-1427.(in Chinese)
[13] M.B.Stegmann,B.K.Ersboll,R.Larsen.FAME-a flexible appearance modeling environment[J].IEEE Trans on Medical Imaging,2003,22(10):1319-1331.

[1]	郭凯红, 崔明茜, 刘婷婷. 模糊知识测度下图像脉冲噪声去除方法[J]. 电子学报, 2023, (): 1-14.
[2]	吕杭, 蒋明峰, 李杨, 张鞠成, 王志康. 基于混合时频域特征的卷积神经网络心律失常分类方法的研究[J]. 电子学报, 2023, 51(3): 701-711.
[3]	孙锐, 张磊, 余益衡, 张旭东. 基于局部异构聚合图卷积网络的跨模态行人重识别[J]. 电子学报, 2023, (): 1-16.
[4]	苏天康, 宋慧慧, 樊佳庆, 张开华. 深度信号引导学习混合变换器的高性能无监督视频目标分割[J]. 电子学报, 2023, (): 1-8.
[5]	刘金平, 吴娟娟, 张荣, 徐鹏飞. 基于结构重参数化与多尺度深度监督的COVID-19胸部CT图像自动分割[J]. 电子学报, 2023, (): 1-9.
[6]	王神龙, 雍宇, 吴晨睿. 基于伪孪生神经网络的低纹理工业零件6D位姿估计[J]. 电子学报, 2023, 51(1): 192-201.
[7]	刘杰, 葛一凡, 田明. 文物图像的超分辨率重建算法研究[J]. 电子学报, 2023, 51(1): 139-145.
[8]	李豪, 袁广林, 秦晓燕, 琚长瑞, 朱虹. 基于空间加权对数似然比相关滤波与Deep Snake的目标轮廓跟踪[J]. 电子学报, 2023, 51(1): 105-116.
[9]	刘芳, 朱天贺, 苏卫星, 刘阳. 基于高斯隐马尔可夫模型的人机共享控制区域化决策算法[J]. 电子学报, 2022, 50(11): 2659-2667.
[10]	李斌, 齐延荣, 周清雷. 基于Winograd算法的目标检测加速器设计与优化[J]. 电子学报, 2022, 50(10): 2387-2397.
[11]	魏钰轩, 陈莹. 基于自适应层信息熵的卷积神经网络压缩[J]. 电子学报, 2022, 50(10): 2398-2408.
[12]	白勇强, 禹晶, 李一秾, 肖创柏. 基于深度先验的盲图像去模糊算法[J]. 电子学报, 2022, (): 1-18.
[13]	刘文杰, 赵胶胶, 张颖, 葛业波. 一种量子条件生成对抗网络算法[J]. 电子学报, 2022, 50(7): 1586-1593.
[14]	郭绍陶, 苑玮琦. 基于双高斯纹理滤波模板和极值点韦伯对比度的圆柱锂电池凹坑缺陷检测[J]. 电子学报, 2022, 50(3): 637-642.
[15]	付利华, 赵宇, 姜涵煦, 赵茹, 吴会贤, 闫绍兴. 基于前景感知视觉注意的半监督视频目标分割[J]. 电子学报, 2022, 50(1): 195-206.

多表情人脸肖像的自动生成

Automatic Generation of Portraits with Multiple Expressions

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics