全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...
电子学报  2003 

人脸的表情与年龄变换和非完整信息的重构技术(下)

, PP. 1963-1970

Keywords: 人像处理,表情变换,年龄变换,视点变换,人脸图像库

Full-Text   Cite this paper   Add to My Lib

Abstract:

非完整视点信息的重构技术可以利用少量的对象视点信息,结合统计学的理论方法对缺失视点信息进行预测和恢复.该文探讨了从单幅2D人像恢复其它视点图像并重构3D形态效果的技术,提出了非完整人像视点续变的技术框架,通过大视点数据库的离线创建,单视点输入的模型匹配,以及大视点空间映射与连续视点重建三个模块,从单视点合成连续的多视点图像.该技术以尽量少的人像2D信息获得高真实度的3D效果,绕过了3D模型重构,可恢复出未知人脸表面的纹理信息.最后结合AIAR人像库的实际建库经验,讨论了人像数据的采集技术和分类方法,提出了在有限拍摄条件下的人像库建立方法与建库实例.

References

[1]  郑南宁,付昀,张婷,卓峰.人脸的表情与年龄变换和非完整信息的重构技术(上)[J].电子学报,2003,31(12A):1955-1962.
[2]  Vetter T, Poggio T.Linear object classes and image synthesis from a single example image[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997,19(7):733-742.
[3]  David Beymer.Vevtorizing face images by interleaving shape and texture computatinns[R].A I Memo 1537, Massachusetts:MIT, 1995.
[4]  张辉,许光祐,谢峰.基于形变模型的物理建模与分析[J].计算机学报,2001,24(6):561-567.
[5]  S M Seize, C R Dyer.View morphing[A].Computer Graphics Annual Conference Series, SIGGRAPH''96[C].New Orleans, Louisiana:ACM SIGGRAPH, August, 1996.21-30.
[6]  S M Seitz, C R Dyer.Complete structure from four point correspondences[A].Proceedings of Intl.Conf.on Computer Vision(ICCV)[C].Cambridge Massachusetts:IEEE Computer Society, 1995.330-337.
[7]  Beier T, Neely S.Feature-based image metamorphosis[J].Computer Graphics, 1992,26(2):35-42.
[8]  付昀.人脸图像渐变算法研究[J].中国图像图形学报(A),2003,(Special.)8:174-182.
[9]  付昀,张婷.人像库的建立方法与关键技术[R].西安:西安交通大学人工智能与机器人研究所,2003.
[10]  J R Bergen, R Hingorani.Hierarchical motion_based frame rate conversion[R].Technical report, David Sarnoff Research Center, April.1990.
[11]  卓峰,徐维朴,张强,张婷,付昀.基于2D样本的人脸图像视点变换[J].计算机应用,2003,12,(Suppl.)23:74-76.
[12]  Lanitis A, Taylor C J, Cootes T F, Ahmad T.Automatic interpretation of human faces and hand gestures using flexible models[A].Proceedings of International Workshop on Face and Gesture Recognition[C].Zurich, Switzerland:IEEE Computer Society, 1995.98-103.
[13]  陈洪.人脸图像自动分析与绘制的统计学习方法[D].西安:西安交通大学人工智能与机器人研究所,2002.
[14]  Cyberware Laboratory Inc.The head & face 3D color scanner bundles the 3030RGB scan head with the PS motion platform[EB/OL].http://www.cyberware.com/products/psInfo.html.2003.
[15]  S Ullman,R Basri.Recognition by linear combinations of models[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 1991,13:992-1006.
[16]  Michael J Jones,Tomaso Poggio.Model-based matching of line drawings by linear combinations of examples[A].Proceedings of the International Conference on Computer Vision[C].Boston Massachusetts, 1995.532-536.
[17]  Michael J Jones, Tomaso Poggio.Model-based matching by linear combinations of examples[R].A I Memo 1583, Massachusetts:MIT, 1996.
[18]  V Blanz, T Vetter.A morphable model for the synthesis of 3D faces[A].Computer Graphics Annual Conference Series, SIGGRAPH''99[C].Los Angeles, California:ACM SIGGRAPH, 1999.187-194.
[19]  Vetter T.Synthesis of novel views from a single face image[J].International Journal of Computer Vision(IJCV), 1998,28(2):103-116.
[20]  S M Seitz, C R Dyer.Physically-valid view synthesis by image interpolation[A].Proceedings of IEEE Workshop on Representations of Visual Scenes[C].Cambridge Massachusetts:IEEE Computer Society, 1995.18-25.
[21]  G Wolberg.Image morphing survey[J].The Visual Computer, 1999,14:360-372.
[22]  Beymer D, Shashua A, Ppggio T.Example based image analysis and synthesis[R].AI Memo 1431, AI Laboratory, MIT, 1993.
[23]  张强.基于稠密特征对应的人脸图像表达及人脸属性变换[D].西安:西安交通大学人工智能与机器人研究所,2003.
[24]  付昀.基于原型样本线性组合的人脸图像CDSGD鲁棒对准算[R].西安:西安交通大学人工智能与机器人研究所.2002.
[25]  Fu Yun, Zheng Nanning.Sequential view synthesis from a single view[R].AIAR.XJTU.Xi''an, 2003.
[26]  Fu Yun, Zheng Nanning.Non-uniform sampling based dynamic matching for the linear model of human faces[R].AIAR.XJTU.Xi''an,2003.
[27]  付昀.基于非统一抽样的动态高斯金字塔分析[R].西安:西安交通大学人工智能与机器人研究所,2003.
[28]  A Shashua, T Riklin-Raviv.The quotient image:class-based re-rendering and recognition with varying illuminations[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2001,23(2):129-139.
[29]  Timothy F Cootes, Gareth J Edwards, Christopher J Taylor.Active appearance models[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001,23(6):681-685.
[30]  Pighin F,Hecker J,Lischinski D,et al.Synthesizing realistic facial expressions from photographs[A].Computer Graphics Annual Conference Series, SIGGRAPH''98[C].Orlando, Florida:ACM SIGGRAPH,1998.75-84.
[31]  付昀.线性人脸对象类模型的匹配提升技术[R].西安:西安交通大学人工智能与机器人研究所,2003.
[32]  Liu Z C, Shan Y, Zhang Z Y.Expressive expression mapping with ratio images[A].Proc.of the 28th Annual Conference on Computer Graphics and Interactive Techniques[C].Los Angeles, California:ACM Press,2001.271-276.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133