基于三维采样点集的人脸识别

计算机科学 ›› 2014, Vol. 41 ›› Issue (Z6): 147-149.

基于三维采样点集的人脸识别

周娟

西南政法大学刑事侦查学院重庆401120 重庆高校物证技术研究中心重庆401120

出版日期:2018-11-14 发布日期:2018-11-14
基金资助:
本文受国家自然科学基金项目(11105236),重庆市高校创新团队项目(KJTD201301)资助

Face Recognition Based on Sampled 3D Points Clouds

ZHOU Juan

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

摘要/Abstract

摘要： 采用基于整体轮廓的提取方法来对三维人脸点集进行重采样表征人脸。首先将三维人脸区域的点集校正到统一的姿态坐标系,并将其转换为深度图,之后计算深度图的一阶和二阶梯度,并设定阈值提取出边界曲线,再找出二维梯度图的边界曲线所对应的三维空间中的曲线点集用来表征人脸,最后用D-ICP算法进行配准并进行相似度测量。在欧洲人脸数据库GAVAB3D中进行了测试,实验结果表明该方法简便有效。

关键词: 三维人脸点集,重采样,边界曲线,D-ICP算法,配准中图法分类号TP391.41文献标识码A

Abstract: This paper resampled the 3D face points clouds based on its whole contour to characterize the face．Firstly,the points set of 3D face region will be adjusted into a unified attitude coordinates and then be changed into depth images.Secondly,the first and second order of gradient ratio of the depth images will be calculated,also a certain threshold will be set to extract the boundary curves of them,in succession,the corresponding points clouds in 3D space of the 2D boundary curves will be found to characterize the human face.Finally,D-ICP algorithm will be used in model registration step and also the similarity of two models will be measured．The experiments were carried out on the European face database GAVAB3D.And the results indicate that our method is handy and effective.

Key words: 3D face points clouds,Resample,Boundary curves,Delaunay-iterative corresponding point(D-ICP) algorithm,Registration

周娟. 基于三维采样点集的人脸识别[J]. 计算机科学, 2014, 41(Z6): 147-149. https://doi.org/

ZHOU Juan. Face Recognition Based on Sampled 3D Points Clouds[J]. Computer Science, 2014, 41(Z6): 147-149. https://doi.org/

参考文献

[1] Dorai C,Weng J,Jain A．Registratio and Integration of Multiple Object Views for 3D Model Construction[J]．IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,0(1):457-464
[2] 徐东艳,孟晓刚．MATLAB函数库查询词典[M]．北京:中国铁道出版,2006:139-151
[3] 贝尔赫,等．计算几何一算法与应用(第二版)[M]．邓俊辉,译．北京:清华大学出版社,2005:206-233
[4] 蒋成成,胡同森,周维.一种改进的迭代最近点算法[J].计算机系统应用,2009,8:84-89
[5] Marr D．A theory of cerebellar cortex[J]．Journal of Physiol,1969,2:437-442
[6] Mahoor M H,Abdel-Mottaleb M．Face recognition based on 3D ridge images obtained from range data[J]．Pattern Recognition,2009,2:445-450
[7] 刘小宁．基于三维模型的人脸识别研究[D].2006:53-92
[8] http://gavab.escet.urjc.es/recursos_en.html
[9] 林庆,马伟阳,单平平,等.眼睛遮挡下的正面人脸识别[J]．计算机科学,2011,8:48-52
[10] 杨荣根,任明武,杨静宇．基于稀疏表示的人脸识别方法[J]．计算机科学,2010,9:17-21
[11] http://www.cbsr.ia.ac.cn/china/3DFace%20Databases%20CH.asp

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed