基于等测地区域的三维面貌相似度评价方法

doi:10.3969/j.issn.1000-3428.2012.13.005

计算机工程 ›› 2012, Vol. 38 ›› Issue (13): 17-21. doi: 10.3969/j.issn.1000-3428.2012.13.005

基于等测地区域的三维面貌相似度评价方法

李红艳，武仲科，周明全，武广艳

(北京师范大学信息科学与技术学院，北京 100875)

收稿日期:2011-11-14 出版日期:2012-07-05 发布日期:2012-07-05
作者简介:李红艳(1987－)，女，硕士研究生，主研方向：计算机图形学，虚拟现实；武仲科，教授、博士、博士生导师；周明全，教授、博士生导师；武广艳，硕士研究生
基金资助:
国家自然科学基金资助重点项目(60736008/F010207)；中央高校基本科研业务费专项基金资助项目(2009SD-11)；北京市自然科学基金资助重点项目(4081002)

3D Face Similarity Evaluation Method Based on Iso-Geodesic Regions

LI Hong-yan, WU Zhong-ke, ZHOU Ming-quan, WU Guang-yan

(College of Information Science and Technology, Beijing Normal University, Beijing 100875, China)

Received:2011-11-14 Online:2012-07-05 Published:2012-07-05

摘要/Abstract

摘要：

提出一种基于等测地区域的三维面貌相似度评价方法。对待比较的面貌模型，采用鼻尖点重叠以及PCA和ICP配准方法消除平移、旋转因素的影响，根据距离鼻尖点的测地距离，将面貌模型简化为一系列测地区域，利用一个12维的分布向量表征任意2块测地区域之间的空间分布关系，将整个面貌模型中所有等测地区域对应的分布向量组成分布矩阵，计算分布矩阵之间的相似性来衡量2个面貌之间的相似度。实验结果表明，该方法为颅面复原提供了检验平台，是一种有效的表情无关人脸识别方法。

关键词: 姿势标准化, PCA配准, ICP配准, 等测地区域, 分布向量, 相似度计算

Abstract:

This paper puts forward an assessment method which is based on Iso-Geodesic regions. In order to standardize the posture, it applies nose tip overlap to eliminate translation error and the classical Principal Component Analysis(PCA) and Iterative Closest Point(ICP) alignment algorithm to eliminate rotation error. Furthermore, it simplifies each 3D face with sever Iso-Geodesic regions, and each pair of regions can be described by a distribution vector of 12 dimensions, which reflects 3D distribution feature. Then each face model can be represented by a distribution matrix which consists of all distribution vectors, and the similarity between two distribution matrixes illustrates the similarity between two face models. Experimental result shows that the method provides an effective platform for the evaluation of the face recovery, and it is an efficient and expression irrelevant 3D face recognition method.

Key words: posture standardization, Principal Component Analysis(PCA) alignment, Iterative Closest Point(ICP) alignment, Iso-Geodesic region, distribution vector, similarity calculation

中图分类号:

TP391

李红艳, 武仲科, 周明全, 武广艳. 基于等测地区域的三维面貌相似度评价方法[J]. 计算机工程, 2012, 38(13): 17-21.

LI Gong-Yan, WU Zhong-Ke, ZHOU Meng-Quan, WU An-Yan. 3D Face Similarity Evaluation Method Based on Iso-Geodesic Regions[J]. Computer Engineering, 2012, 38(13): 17-21.

http://www.ecice06.com/CN/Y2012/V38/I13/17

参考文献

[1] Stephan C N, Arthur R S. Assessing Facial Approximation Accuracy: How Do Resemblance Ratings of Disparate Faces Compare to Recognition Tests?[J]. Forensic Science International, 2006, 159(S): 159-163.
[2] Gérald Q, Balaguer T, Staccini P, et al. Assessment of the Accuracy of Three-dimensional Manual Face Reconstruction: A Series of 25 Controlled Cases[J]. International Journal of Legal Medicine, 2007, 121(6): 459-475.
[3] Can T, Wang Yuanfang. CTSS: A Robust and Efficient Method for Protein Structure Alignment Based on Local Geometrical and Biological Distributions[C]//Proc. of IEEE Computer Society Conference on Bioinformatics. Washington D. C., USA: IEEE Computer Society, 2003: 169-179.
[4] Rogen P, Fain B. Automatic Classification of Protein Structure by Using Gauss Integrals[J]. Peptide Nucleic Acids, 2003, 100(1): 119-124.
[5] 徐遵义, 晏磊, 宁书年. 基于Hausdorff距离的海底地形匹配算法仿真研究[J]. 计算机工程, 2007, 33(9): 7-9.
[6] 康来, 赵健, 宋汉辰. 面向二维GIS矢量数据三维可视化的地形匹配技术研究[J]. 计算机科学, 2009, 36(11): 262-265.
[7] 刘玉杰, 张晓冬, 李华. 正交样条矩与三维模型检索[J]. 计算机辅助设计与图形学学报, 2009, 21(7): 968-972.
[8] Richtsmeier J T, Deleon V B. The Promise of Geometric Morphometrics[J]. American Journal of Physical Anthropology, 2002, 35(S): 63-91.
[9] Clement J G, Marks M K. Computer-graphic Facial Reconstruc- tion[M]. London, UK: Elsevier Academic Press, 2005.
[10] Gupta S, Aggarwal J K, Markey M K, et al. 3D Face Recognition Founded on the Structural Diversity of Human Faces[C]//Proc. of CVPR’07. Minneapolis, USA: [s. n.], 2007: 643-649.
[11] Mpiperis I, Malassiotis S, Strintzis M G. 3-D Face Recognition with the Geodesic Polar Representation[J]. IEEE Transations on Information Forensics and Security, 2007, 2(3): 537-547.
[12] ter Haar F B, Veltkamp R C. SHREC’08 Entry: 3D Face Recognition Using Facial Contour Curves[C]//Proc. of IEEE International Conference on Shape Modeling and Applications. New York, USA: [s. n.], 2008.
[13] Feng Shuo, Krim H, Kogan I A. 3D Face Recognition Using Euclidean Integral Invariants Signature[C]//Proc. of the 14th Workshop on Statistical Signal Processing. Madison, USA: [s. n.], 2007: 156-160.
[14] Farkas L G, Munro I R. Anthropometric Facial Proportions in Medicine[M]. Spring Field, USA: Thomas Books, 1987.
[15] Farkas L G. Anthropometry of the Head and Face[M]. New York, USA: Raven Press, 1994.
[16] Besl P J, McKay N D. A Method for Registration of 3-D Shapes[J]. IEEE Trans. on Pattern Anal., 1992, 14(2): 239-256.
[17] Medioni G, Waupotish R. Face Modeling and Recognition in 3-D[C]//Proc. of IEEE Int’l Workshop on Analysis and Modeling of Faces and Gestures. Washington D. C., USA: IEEE Computer Society, 2003.
[18] Lu Xiaoguang, Jain A K, Colbry D. Matching 2.5D Face Scans to 3D Models[J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2006, 28(10): 31-43.
[19] Chang K I, Bowyer K W, Flynn P J. Multiple Nose Region Matching for 3D Face Recognition Under Varying Facial Expression[J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2006, 28(10): 1695-1700.
[20] Timothbe J. Fast Geometric Matching for Shape Registra- tion[EB/OL]. (2002-11-14). http://archiveweb.epfl.ch/parlab.epfl. ch/page79375.html%3Fmatrix=1237804470776.html.
[21] Surazhsky V, Surazhsky T, Kirsanov D, et al. Fast Exact and Approximate Geodesics on Meshes[J]. ACM Transactions on Graphics, 2005, 24(3): 553-560.
[22] Peyré G, Pechaud M, Keriven R, et al. Geodesic Methods in Computer Vision and Graphics[J]. Foundations and Trends in Computer Graphics and Vision, 2010, 5(3-4): 197-397.
[23] Peyré G, Cohen L D. Surface Segmentation Using Geodesic Centroidal Tesselation[C]//Proc. of 3DPVT’04. [S. l.]: IEEE Computer Society, 2004: 995-1002.
[24] Stefano B, Bimbo D, Pala P. 3D Face Recognition Using Iso- Geodesic Stripes[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2010, 32(12): 2162-2177.
[25] Stefano B, Bimbo D, Vicario E. Weighted Walkthroughs Between Extended Entities for Retrieval by Spatial Arrangement[J]. IEEE Transactions on Multimedia, 2003, 5(1): 52-70.

选择文件类型/文献管理软件名称

选择包含的内容

基于等测地区域的三维面貌相似度评价方法

3D Face Similarity Evaluation Method Based on Iso-Geodesic Regions

PDF

可视化

被引次数

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

本文评价

[1]	郭渝洛, 边浩东, 董润婷, 唐嘉豪, 王晓英, 黄建强. 基于SIMD的并行傅里叶空间图像相似度计算[J]. 计算机工程, 2021, 47(11): 247-253.
[2]	杨海清, 范琦. 基于时空分析的路口相似度计算方法[J]. 计算机工程, 2020, 46(4): 33-39.
[3]	李志欣,兰丹媚,张灿龙,唐素勤. 基于Co-Training的微博垃圾评论识别方法[J]. 计算机工程, 2018, 44(7): 212-218.
[4]	赵英,韩春昊. 马尔科夫模型在网络流量分类中的应用与研究[J]. 计算机工程, 2018, 44(5): 291-295.
[5]	刘业政,熊强,姜元春. 基于多维相似度的利基产品推荐方法[J]. 计算机工程, 2018, 44(3): 195-200.
[6]	陈彦桦,李剑. 一种基于结构特征的树相似度计算方法[J]. 计算机工程, 2018, 44(11): 197-201,208.
[7]	贾伟洋,李书琴,李昕宇,刘斌. 基于离散量和用户兴趣贴近度的协同过滤推荐算法[J]. 计算机工程, 2018, 44(1): 226-232,237.
[8]	段旭磊,张仰森,孙祎卓. 微博文本的句向量表示及相似度计算方法研究[J]. 计算机工程, 2017, 43(5): 143-148.
[9]	程曦,陈军. 基于MapReduce与项目分类的协同过滤算法[J]. 计算机工程, 2016, 42(7): 194-198.
[10]	余峰，余正涛，杨剑锋，郭剑毅，严馨. 基于主题信息的项目评审专家推荐方法[J]. 计算机工程, 2014, 40(6): 201-205.
[11]	程小林，熊焰，刘青文，陆琦玮. 一种基于自适应局部融合参数的协同过滤方法[J]. 计算机工程, 2014, 40(1): 39-44.
[12]	邓少伟, 罗泽, 李树仁, 阎保平. 基于论文共同作者学术关系的学者推荐系统[J]. 计算机工程, 2013, 39(2): 12-17.
[13]	戴立玲, 谢李华, 卢章平, 袁浩. 基于复球面映射的产品形状相似性度量算法[J]. 计算机工程, 2012, 38(18): 258-261.
[14]	秦学勇, 张润梅. 两级相似度计算在主观题机器阅卷中的应用[J]. 计算机工程, 2012, 38(11): 274-276,280.
[15]	赵鹏, 常天庆, 魏巍, 张波. 基于多Agent的战场目标分群方法[J]. 计算机工程, 2011, 37(21): 152-154,158.

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

基于等测地区域的三维面貌相似度评价方法

3D Face Similarity Evaluation Method Based on Iso-Geodesic Regions

PDF

可视化

被引次数

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

本文评价