基于测地线的躺卧三维颅面模型矫正

白方域; 赵俊莉; 陈郁葱; 邓擎琼; 段福庆; 周明全

doi:10.3788/OPE.20182602.0442

您当前的位置：

首页 >

文章列表页 >

基于测地线的躺卧三维颅面模型矫正

信息科学 | 更新时间：2020-07-05

- 基于测地线的躺卧三维颅面模型矫正
- Rectification of 3D Lying Craniofacial Model Based on Geodesic
- 光学精密工程 2018年26卷第2期页码：442-449
- 作者机构：
  
  1.北京师范大学信息科学与技术学院, 北京 100875
  2.青岛大学数据科学与软件工程学院, 山东青岛 266071
- 作者简介：
  
  [ "白方域(1991-), 男, 甘肃张掖人, 硕士研究生, 2014年于北京师范大学攻读硕士学位, 主要从事图像处理、机器学习、计算机视觉等方面的研究。E-mail:bfy122@hotmial.com" ]
  [ "段福庆(1973-), 男, 陕西人, 博士, 教授, 博士生导师, 1995年、1998年于西北大学分别获得学士、硕士学位, 2006年于中科院自动化所获得博士学位, 担任Springer国际期刊《Frontiers of Computer Science》青年Associate Editor, 担任多个国际会议ACCV、HCII、CAA、ICONIP等程序委员会委员、组织委员会委员、分会主席, 中国计算机学会计算机视觉专业组委员, 中国图象图形学学会医学影像专业委员会委员, 主要研究方向包括摄像机标定, 模式识别与机器学习。E-mail:fqduan@bnu.edu.cn" ]
- 基金信息：
  
  国家自然科学基金资助项目(61572078);国家自然科学基金青年基金资助项目(61702293);北京市自然科学基金资助项目(4152028)
- DOI：10.3788/OPE.20182602.0442
  中图分类号： TP394.1;TH691.9
- 收稿日期：2017-06-06，
  
  录用日期：2017-8-28，
  
  纸质出版日期：2018-02-25
- 稿件说明：
移动端阅览
白方域, 赵俊莉, 陈郁葱, 等. 基于测地线的躺卧三维颅面模型矫正[J]. 光学精密工程, 2018,26(2):442-449.

Fang-yu BAI, Jun-li ZHAO, Yu-cong CHEN, et al. Rectification of 3D Lying Craniofacial Model Based on Geodesic[J]. Optics and precision engineering, 2018, 26(2): 442-449.
白方域, 赵俊莉, 陈郁葱, 等. 基于测地线的躺卧三维颅面模型矫正[J]. 光学精密工程, 2018,26(2):442-449. DOI： 10.3788/OPE.20182602.0442.

Fang-yu BAI, Jun-li ZHAO, Yu-cong CHEN, et al. Rectification of 3D Lying Craniofacial Model Based on Geodesic[J]. Optics and precision engineering, 2018, 26(2): 442-449. DOI： 10.3788/OPE.20182602.0442.

摘要

三维颅面软组织因受重力影响在躺卧与直立两种姿态下的差异较大，为将躺卧姿态下获取的三维颅面模型矫正为直立姿态下的三维模型，本文提出了一种基于测地线的躺卧三维颅面模型的直立矫正方法。首先利用测地距离的内蕴几何不变性，建立两种姿态下面部特征点的点对应；然后，利用主成分分析建立颅面特征点运动模型；最后，对待矫正的躺卧颅面模型，根据颅面特征点运动模型确定特征点的运动，根据特征点的运动确定躺卧颅面模型到直立颅面模型的变形。所提方法将与直立姿态人脸模型间的平均误差从矫正前的10

-2

数量级下降到矫正后的10

-4

数量级。本文利用测地距离的内蕴几何不变性，解决了两种姿态下面部特征点对应的难题；所建立的颅面特征点运动模型，能够较好地表示颅面在两种姿态下发生的形变，从而能够实现有效地模型矫正。

Abstract

The three-dimensional craniofacial soft tissue shapes in the upright and lying postures are different due to the gravity. In order to rectify the three-dimensional craniofacial model from the lying posture to one from the upright posture

a rectification technique of three-dimensional craniofacial models based on geodesic was proposed. Firstly

the correspondences of the craniofacial feature points under two postures were established by using the intrinsic geometric invariance of geodesic distance; Secondly

a statistical model of the feature point motion from lying to upright posture was established by using principal component analysis; Finally

for a craniofacial model in lying posture

the motion of the feature points was determined by the statistical model

and the deformation of the craniofacial model from lying posture to one from upright posture was determined according to the motion of the feature points. The mean error was decreased from 10

-2

orders of magnitude before correction to 10

-4

orders of magnitude after correction. The problem of point correspondence between two postures was well solved by using the intrinsic geometric invariance of geodesic distance. The established feature point motion model can well represent the deformation of the craniofacial model from lying posture to one from upright posture

and thus can achieve effective model correction.

关键词

Keywords

references

WILKINSON C. Computerized forensic facial reconstruction:A review of current systems[J]. Forensic Science, Medicine, and Pathology, 2005, 1(3):173-177.

HWANG H S, PARK M K, LEE W J, et al.. Facial soft tissue thickness database for craniofacial reconstruction in Korean adults[J]. Journal of Forensic Sciences, 2012, 57(6):1442-1447.

SHUI W Y, ZHOU M Q, DENG Q Q, et al.. Densely calculated facial soft tissue thickness for craniofacial reconstruction in Chinese adults[J]. Forensic Science International, 2016, 266:573.e1-573.e12.

BULUT O, SIPAHIOGLU S, HEKIMOGLU B. Facial soft tissue thickness database for craniofacial reconstruction in the Turkish adult population[J]. Forensic Science International, 2014, 242:44-61.

DONG Y, HUANG L, FENG Z, et al.. Influence of sex and body mass index on facial soft tissue thickness measurements of the northern Chinese adult population[J]. Forensic Science International, 2012, 222(1-3):396.e1-396.e7.

CLAES P, VANDERMEULEN D, DE GREEF S, et al.. Computerized craniofacial reconstruction:conceptual framework and review[J]. Forensic Science International, 2010, 201(1-3):138-145.

税午阳, 周明全, 武仲科, 等.数据配准的颅骨面貌复原方法[J].计算机辅助设计与图形学学报, 2011, 23(4):607-614.

SHUI W Y, ZHOU M Q, WU ZH K, et al.. An approach of craniofacial reconstruction based on registration[J]. Journal of Computer-Aided Design & Computer Graphics, 2011, 23(4):607-614. (in Chinese)

DUAN F Q, HUANG D H, TIAN Y, et al.. 3D face reconstruction from skull by regression modeling in shape parameter spaces[J]. Neurocomputing, 2015, 151:674-682.

LEE W J, YOON A Y, SONG M K, et al.. The archaeological contribution of forensic craniofacial reconstruction to a portrait drawing of a Korean historical figure[J]. Journal of Archaeological Science, 2014, 49:228-236.

DENG Q Q, ZHOU M Q, WU ZH K, et al.. A regional method for craniofacial reconstruction based on coordinate adjustments and a new fusion strategy[J]. Forensic Science International, 2016, 259:19-31.

LEE W J, WILKINSON C M, HWANG H S, et al.. Correlation between average tissue depth data and quantitative accuracy of forensic craniofacial reconstructions measured by geometric surface comparison method[J]. Journal of Forensic Sciences, 2015, 60(3):572-580.

BERAR M, TILOTTA F M, GLAUNÈS J A, et al.. Craniofacial reconstruction as a prediction problem using a Latent Root Regression model[J]. Forensic Science International, 2011, 210(1-3):228-236.

DE GREEF S, CLAES P, MOLLEMANS W, et al.. Semi-automated ultrasound facial soft tissue depth registration:method and validation[J]. Journal of Forensic Science, 2005, 50(6):1282-1288.

CLAES P, VANDERMEULEN D, DE GREEF S, et al.. Craniofacial reconstruction using a combined statistical model of face shape and soft tissue depths:methodology and validation[J]. Forensic Science International, 2006, 159(S1):S147-S158.

KUSTÁR A, FORRÍ L, KALINA I, et al.. FACE-R-A 3D database of 400 living individuals' full head CT-and face scans and preliminary GMM analysis for craniofacial reconstruction[J]. Journal of Forensic Sciences, 2013, 58(6):1420-1428.

赵俊莉, 武仲科, 刘翠婷, 等.形状空间下的3D面貌相似性比较[J].光学精密工程, 2015, 23(4):1138-1145.

ZHAO J L, WU ZH K, LIU C T, et al.. 3D facial similarity comparison in shape space[J]. Opt. Precision Eng., 2015, 23(4):1138-1145. (in Chinese)

MITCHELL J S, MOUNT D M, PAPADIMITRIOU C H. The discrete geodesic problem[J]. SIAM Journal on Computing, 1987, 16(4):647-668.

XIN S Q, WANG G J. Improving Chen and Han's algorithm on the discrete geodesic problem[J]. ACM Transactions on Graphics, 2009, 28(4):104.

BOOKSTEIN F L. Principal warps:Thin-plate splines and the decomposition of deformations[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1989, 11(6):567-585.

吴禄慎, 史皓良, 陈华伟.基于特征信息分类的三维点数据去噪[J].光学精密工程, 2016, 24(6):1465-1473.

WU L SH, SHI H L, CHEN H W. Denoising of three-dimensional point data based on classification of feature information[J]. Opt. Precision Eng., 2016, 24(6):1465-1473. (in Chinese)

王欣, 张明明, 于晓, 等.应用改进迭代最近点方法的点云数据配准[J].光学精密工程, 2012, 20(9):2068-2077.

WANG X, ZHANG M M, YU X, et al.. Point cloud registration based on improved iterative closest point method[J]. Opt. Precision Eng., 2012, 20(9):2068-2077. (in Chinese)

HU Y L, DUAN F Q, YIN B C, et al.. A hierarchical dense deformable model for 3D face reconstruction from skull[J]. Multimedia Tools and Applications, 2013, 64(2):345-364.

浏览量

563

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

形状空间下的3D面貌相似性比较