基于曲面形变的三维人脸样本配准

计算机科学 ›› 2014, Vol. 41 ›› Issue (Z11): 116-118.

基于曲面形变的三维人脸样本配准

盖赟

中国青年政治学院计算机教学与应用中心北京100089 北京工业大学城市交通学院北京100124

出版日期:2018-11-14 发布日期:2018-11-14
基金资助:
本文受北京市博士基金(2014ZZ-56),中国青年政治学院青年教师基金(182060326)资助

3D Face Registration Based on Surface Deformation

GE Yun

Online:2018-11-14 Published:2018-11-14

摘要/Abstract

摘要： 三维人脸样本是人脸识别、人脸动画等领域进行模型训练、算法设计及性能比较的重要数据平台。为了提高三维人脸样本的配准效果和配准速度,提出一种基于曲面变形的三维人脸样本配准方法。该方法通过对标准化样本实施一系列的变形操作来建立原始样本与标准样本之间的对应关系。然后基于该对应关系对原始样本进行配准处理,在处理过程中使用统计方法对样本上的毛刺点和空洞进行修补。实验结果表明,使用该方法可以快速、有效地对不同格式的原始样本进行配准。

关键词: 样本配准,最近点匹配,TPS,三维人脸,曲面变形

Abstract: D face database is an important data platform for model training,algorithm design.To improve the matching result and efficiency of 3D face sample,we proposed a new registration method based on surface deformation.First a series of deform operation is performed on the template sample to get the correspondence between template sample and raw sample.The registration operation is performed on the raw sample.In the procedure of matching process,the statistical method is used to tackle the problem of noise point and hollow.The experiment results show that the proposed method has good performance on face registration.

Key words: Sample registration,Closet point match,TPS,3D face sample,Surface deformation

盖赟. 基于曲面形变的三维人脸样本配准[J]. 计算机科学, 2014, 41(Z11): 116-118. https://doi.org/

GE Yun. 3D Face Registration Based on Surface Deformation[J]. Computer Science, 2014, 41(Z11): 116-118. https://doi.org/

参考文献

[1] Goh R,Liu L,Liu X,et al.The CMU face in action (FIA) data-base[C]∥Proceedings of Analysis and Modeling of Faces and Gestures.Beijing:Springer-Verlag,2005:255-263
[2] Beumier C.3D-RMA 3D database.http://www.sic.rma.ac.be/ beumier/DB/3d rma.html#1,2008
[3] Moreno A B,Sanchez A.Gavab DB:A 3D Face Database[C]∥Proceedings of the 2nd COST275 Workshop on Biometrics on the Internet.Vigo:Lecture Notes,2004
[4] Hu Yu-xiao,Zhang Zhen-qiu,Xu Xun,et al.Building LargeScale 3D Face Database for Face Analysis[C]∥Proceedings of Multimedia Content Analysis and Mining.Weihai:Lecture Notes,2007:343-350
[5] Bookstein F L.Principal Warps:Thin-Plate Splines and the Decomposition of Deformations [J].IEEE Trans.Pattern Analysis and Machine Intelligence,1989,11:567-585
[6] 胡永利,尹宝才,程世铨,等.创建中国人三维人脸库关键技术研究[J].计算机研究与发展,2005,42(4):622-628
[7] Bentley J L.Multidimensional binary search trees used for associative searching[J].Communications of the ACM,1975,18(9):509-517

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed