刚性区域特征点的3维人脸识别
|
摘要
目的针对3维人脸识别中存在表情变化的问题,提出了一种基于刚性区域特征点的3维人脸识别方法。方法该方法首先在人脸纹理图像上提取人脸图像的特征点,并删除非刚性区域内的特征点,然后根据采样点的序号,在人脸空间几何信息上得到人脸图像特征点的3维几何信息,并建立以特征点为中心的刚性区域内的子区域,最后以子区域为局部特征进行人脸识别测试,得到不同子区域对人脸识别的贡献,并以此作为依据对人脸识别的结果进行加权统计。结果在FRGC v2.0的3维人脸数据库上进行实验测试,该方法的识别准确率为98.5%,当错误接受率(FAR)为0.001时的验证率为99.2%,结果表明,该方法对非中性表情下的3维人脸识别具有很好的准确性。结论该方法可以有效克服表情变化对3维人脸识别的影响,同时对3维数据中存在的空洞和尖锐噪声等因素具有较好的鲁棒性,对提高3维人脸识别性能具有重要意义。
Objective A novel approach to 3D face recognition based on rigid region feature points is proposed to solve the problem of expression variance. Method The feature points of a face image are extracted on the face texture image by image block center vector sampling and probability map spatial relation model approximation,and the feature points in the nonrigid region are deleted. According to the serial number of the sampling points that are extracted from the face texture image,the 3D geometric information of the feature points of the face image is obtained based on the geometric information of the face space,and the subregion of the rigid region centered at the feature points is established. The subregion is used as the local feature for face recognition test. The contributions of different subregions to face recognition are obtained,and the result of face recognition is weighted by the contribution rate of different subregions. Result Experimental tests are performed on the FRGC ver2. 0 3D face database. The recognition accuracy rate is 98. 5%. The false accuracy rate is 0. 001,and the verification rate is 99. 2%. The method of non-neutral expression of 3D face recognition demonstrates good recognition performance. Conclusion The proposed approach can effectively overcome the influence of facial expression variance on 3Dface recognition because of the deleted feature points in the nonrigid region and has good robustness to the holes and sharp noises in the 3D data. This approach can greatly improve the performance of 3D face recognition.
Objective A novel approach to 3D face recognition based on rigid region feature points is proposed to solve the problem of expression variance. Method The feature points of a face image are extracted on the face texture image by image block center vector sampling and probability map spatial relation model approximation,and the feature points in the nonrigid region are deleted. According to the serial number of the sampling points that are extracted from the face texture image,the 3D geometric information of the feature points of the face image is obtained based on the geometric information of the face space,and the subregion of the rigid region centered at the feature points is established. The subregion is used as the local feature for face recognition test. The contributions of different subregions to face recognition are obtained,and the result of face recognition is weighted by the contribution rate of different subregions. Result Experimental tests are performed on the FRGC ver2. 0 3D face database. The recognition accuracy rate is 98. 5%. The false accuracy rate is 0. 001,and the verification rate is 99. 2%. The method of non-neutral expression of 3D face recognition demonstrates good recognition performance. Conclusion The proposed approach can effectively overcome the influence of facial expression variance on 3Dface recognition because of the deleted feature points in the nonrigid region and has good robustness to the holes and sharp noises in the 3D data. This approach can greatly improve the performance of 3D face recognition.
引文
[1]Guillaumin M,Mensink T,Verbeek J,et al.Face recognition from caption-based supervision[J].International Journal of Computer Vision,2012,96(1):64-82.[DOI:10.1007/s11263-011-0447-x]
[2]Zhuang L S,Chan T H,Yang A Y,et al.Sparse illumination learning and transfer for single-sample face recognition with image corruption and misalignment[J].International Journal of Computer Vision,2015,114(2-3):272-287.[DOI:10.1007/s11263-014-0749-x]
[3]Kakadiaris I A,Passalis G,Toderici G,et al.Three-dimensional face recognition in the presence of facial expressions:an annotated deformable model approach[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(4):640-649.[DOI:10.1109/TPAMI.2007.1017]
[4]Lu X G,Jain A K.Deformation modeling for robust 3D face matching[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(8):1346-1357.[DOI:10.1109/TPAMI.2007.70784]
[5]Al-Osaimi F,Bennamoun M,Mian A.An expression deformation approach to non-rigid 3D face recognition[J].International Journal of Computer Vision,2009,81(3):302-316.[DOI:10.1007/s11263-008-0174-0]
[6]Lei Y J,Bennamoun M,El-Sallam A A.An efficient 3D face recognition approach based on the fusion of novel local low-level features[J].Pattern Recognition,2013,46(1):24-37.[DOI:10.1016/j.patcog.2012.06.023]
[7]Li X L,Da F P.A rapid method for 3D face recognition based on rejection algorithm[J].Acta Automatica Sinica,2010,36(1):153-158.[李晓莉,达飞鹏.基于排除算法的快速三维人脸识别方法[J].自动化学报,2010,36(1):153-158.][DOI:10.3724/SP.J.1004.2010.00153]
[8]Li X L,Da F P.3D face recognition based on profile and rigid regions[J].Journal of Image and Graphics,2010,15(2):266-273.[李晓莉,达飞鹏.基于侧面轮廓线和刚性区域的3维人脸识别[J].中国图象图形学报,2010,15(2):266-273.][DOI:10.11834/jig.20100213]
[9]Li Y C,Da F P.Expression-insensitive 3D face recognition method based on facial fiducial points[J].Journal of Image and Graphics,2014,19(10):1459-1467.[李燕春,达飞鹏.基于特征点表情变化的3维人脸识别[J].中国图象图形学报,2014,19(10):1459-1467.][DOI:10.11834/jig.20141007]
[10]Wang Y M,Pan G,Liu J Z.A deformation model to reduce the effect of expressions in 3D face recognition[J].The Visual Computer,2011,27(5):333-345.[DOI:10.1007/s00371-010-0530-2]
[11]Lei Y J,Bennamoun M,Hayat M,et al.An efficient 3D face recognition approach using local geometrical signatures[J].Pattern Recognition,2014,47(2):509-524.[DOI:10.1016/j.patcog.2013.07.018]
[12]Martinez B,Valstar M F,Binefa X,et al.Local evidence aggregation for regression-based facial point detection[J].IEEETransactions on Pattern Analysis and Machine Intelligence,2013,35(5):1149-1163.[DOI:10.1109/TPAMI.2012.205]
[13]Wang Y M,Pan G,Wu Z H.A survey of 3D face recognition[J].Journal of Computer-Aided Design&Computer Graphics,2008,20(7):819-829.[王跃明,潘纲,吴朝晖.三维人脸识别研究综述[J].计算机辅助设计与图形学学报,2008,20(7):819-829.]
[14]Phillips P J,Flynn P J,Scruggs T,et al.Overview of the face recognition grand challenge[C]//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.San Diego,CA,USA:IEEE,2005,947-954.[DOI:10.1109/CVPR.2005.268]
[15]Wang X Q,Ruan Q Q,Jin Y,et al.Three-dimensional face recognition under expression variation[J].EURASIP Journal on Image and Video Processing,2014,2014:#51.[DOI:10.1186/1687-5281-2014-51]
[16]Elaiwat S,Bennamoun M,Boussaid F,et al.A curvelet-based approach for textured 3D face recognition[J].Pattern Recognition,2015,48(4):1235-1246.[DOI:10.1016/j.patcog.2014.10.013]
[2]Zhuang L S,Chan T H,Yang A Y,et al.Sparse illumination learning and transfer for single-sample face recognition with image corruption and misalignment[J].International Journal of Computer Vision,2015,114(2-3):272-287.[DOI:10.1007/s11263-014-0749-x]
[3]Kakadiaris I A,Passalis G,Toderici G,et al.Three-dimensional face recognition in the presence of facial expressions:an annotated deformable model approach[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(4):640-649.[DOI:10.1109/TPAMI.2007.1017]
[4]Lu X G,Jain A K.Deformation modeling for robust 3D face matching[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(8):1346-1357.[DOI:10.1109/TPAMI.2007.70784]
[5]Al-Osaimi F,Bennamoun M,Mian A.An expression deformation approach to non-rigid 3D face recognition[J].International Journal of Computer Vision,2009,81(3):302-316.[DOI:10.1007/s11263-008-0174-0]
[6]Lei Y J,Bennamoun M,El-Sallam A A.An efficient 3D face recognition approach based on the fusion of novel local low-level features[J].Pattern Recognition,2013,46(1):24-37.[DOI:10.1016/j.patcog.2012.06.023]
[7]Li X L,Da F P.A rapid method for 3D face recognition based on rejection algorithm[J].Acta Automatica Sinica,2010,36(1):153-158.[李晓莉,达飞鹏.基于排除算法的快速三维人脸识别方法[J].自动化学报,2010,36(1):153-158.][DOI:10.3724/SP.J.1004.2010.00153]
[8]Li X L,Da F P.3D face recognition based on profile and rigid regions[J].Journal of Image and Graphics,2010,15(2):266-273.[李晓莉,达飞鹏.基于侧面轮廓线和刚性区域的3维人脸识别[J].中国图象图形学报,2010,15(2):266-273.][DOI:10.11834/jig.20100213]
[9]Li Y C,Da F P.Expression-insensitive 3D face recognition method based on facial fiducial points[J].Journal of Image and Graphics,2014,19(10):1459-1467.[李燕春,达飞鹏.基于特征点表情变化的3维人脸识别[J].中国图象图形学报,2014,19(10):1459-1467.][DOI:10.11834/jig.20141007]
[10]Wang Y M,Pan G,Liu J Z.A deformation model to reduce the effect of expressions in 3D face recognition[J].The Visual Computer,2011,27(5):333-345.[DOI:10.1007/s00371-010-0530-2]
[11]Lei Y J,Bennamoun M,Hayat M,et al.An efficient 3D face recognition approach using local geometrical signatures[J].Pattern Recognition,2014,47(2):509-524.[DOI:10.1016/j.patcog.2013.07.018]
[12]Martinez B,Valstar M F,Binefa X,et al.Local evidence aggregation for regression-based facial point detection[J].IEEETransactions on Pattern Analysis and Machine Intelligence,2013,35(5):1149-1163.[DOI:10.1109/TPAMI.2012.205]
[13]Wang Y M,Pan G,Wu Z H.A survey of 3D face recognition[J].Journal of Computer-Aided Design&Computer Graphics,2008,20(7):819-829.[王跃明,潘纲,吴朝晖.三维人脸识别研究综述[J].计算机辅助设计与图形学学报,2008,20(7):819-829.]
[14]Phillips P J,Flynn P J,Scruggs T,et al.Overview of the face recognition grand challenge[C]//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.San Diego,CA,USA:IEEE,2005,947-954.[DOI:10.1109/CVPR.2005.268]
[15]Wang X Q,Ruan Q Q,Jin Y,et al.Three-dimensional face recognition under expression variation[J].EURASIP Journal on Image and Video Processing,2014,2014:#51.[DOI:10.1186/1687-5281-2014-51]
[16]Elaiwat S,Bennamoun M,Boussaid F,et al.A curvelet-based approach for textured 3D face recognition[J].Pattern Recognition,2015,48(4):1235-1246.[DOI:10.1016/j.patcog.2014.10.013]