Principal Curvature Measures Estimation and Application to 3D Face Recognition
Principal Curvature Measures Estimation and Application to 3D Face Recognition
复制标题
主曲率测量估计及其在 3D 人脸识别中的应用
DOI：
10.1007/s10851-017-0728-2
复制
发表时间：
2017-04
影响因子：
2
通讯作者：
Liming Chen
中科院分区：
文献类型：
--
作者：
Yinhang Tang;Huibin Li;Xiang Sun;Jean-Marie Morvan;Liming Chen
提出了一种基于三种主要曲率度量的三维人脸关键点检测、描述和匹配框架。这些度量给出了光滑曲面和离散曲面的主曲率的统一定义。根据正则循环理论和几何测度理论，可以合理地计算它们。这些度量的强大理论基础为我们提供了一种对以三角形网格表示的真实3D人脸扫描的可靠的离散估计方法。基于这些估计值，该方法可以自动检测出一组稀疏的、可区分的三维人脸特征点。通过这些主曲率度量的直方图来综合描述每个3D特征点周围的局部人脸形状。为了保证这些描述子的姿态不变性，使用了这些主曲率度量的三个主曲率向量来分配标准方向。人脸之间的相似性比较是通过使用基于稀疏表示的重建方法匹配所有基于曲率的局部形状描述符来完成的。提出的方法在三个公共数据库上进行了评估，即FRGC v2.0、Bsporus和Gavab。实验结果表明，三种主曲率度量对于三维人脸形状描述具有很强的互补性，它们的融合可以极大地提高识别性能。我们的方法在中性子集、表达子集和整个FRGC v2.0数据库上分别获得了99.6%、95.7%和97.9%的第一级识别率。这表明我们的方法对适度的面部表情变化是稳健的。此外，在Bsporus数据库的姿态子集(除偏航90°外)和遮挡子集(98.4%)上，该算法也获得了非常有竞争力的性能。即使在像轮廓这样的极端姿势变化的情况下，它的识别率也远远超过了最先进的方法，识别率为57.1%。在Gavab数据库上进行的实验进一步证明了该方法对不同头部姿势变化的鲁棒性。
This paper presents an effective 3D face keypoint detection, description and matching framework based on three principle curvature measures. These measures give a unified definition of principle curvatures for both smooth and discrete surfaces. They can be reasonably computed based on the normal cycle theory and the geometric measure theory. The strong theoretical basis of these measures provides us a solid discrete estimation method on real 3D face scans represented as triangle meshes. Based on these estimated measures, the proposed method can automatically detect a set of sparse and discriminating 3D facial feature points. The local facial shape around each 3D feature point is comprehensively described by histograms of these principal curvature measures. To guarantee the pose invariance of these descriptors, three principle curvature vectors of these principle curvature measures are employed to assign the canonical directions. Similarity comparison between faces is accomplished by matching all these curvature-based local shape descriptors using the sparse representation-based reconstruction method. The proposed method was evaluated on three public databases, i.e. FRGC v2.0, Bosphorus, and Gavab. Experimental results demonstrated that the three principle curvature measures contain strong complementarity for 3D facial shape description, and their fusion can largely improve the recognition performance. Our approach achieves rank-one recognition rates of 99.6, 95.7, and 97.9% on the neutral subset, expression subset, and the whole FRGC v2.0 databases, respectively. This indicates that our method is robust to moderate facial expression variations. Moreover, it also achieves very competitive performance on the pose subset (over 98.6% except Yaw 90°) and the occlusion subset (98.4%) of the Bosphorus database. Even in the case of extreme pose variations like profiles, it also significantly outperforms the state-of-the-art approaches with a recognition rate of 57.1%. The experiments carried out on the Gavab databases further demonstrate the robustness of our method to varies head pose variations.
登录
查看更多内容
DOI：
10.1007/978-1-4471-4063-4
发表时间：
2012
期刊：
--
影响因子：
--
作者：
Nick E. Pears;Yonghuai Liu;P. Bunting
通讯作者：
Nick E. Pears;Yonghuai Liu;P. Bunting
影响因子：
0.8
作者：
J. Morvan;Boris Thibert
通讯作者：
J. Morvan;Boris Thibert
DOI：
10.1201/9781482296860
发表时间：
2001-01
期刊：
--
影响因子：
--
作者：
Yu. A. Aminov
通讯作者：
Yu. A. Aminov
DOI：
10.1007/978-3-540-73792-6
发表时间：
2008-07
期刊：
--
影响因子：
--
作者：
J. Morvan
通讯作者：
J. Morvan
DOI：
10.1023/b:visi.0000029664.99615.94
发表时间：
2004-11-01
影响因子：
19.5
作者：
Lowe, DG
通讯作者：
Lowe, DG