结合加权子空间和相似度度量学习的人脸验证方法研究
|
摘要
在无约束条件下,人脸表情、姿态、光照以及背景等复杂因素可能导致人脸图像的类内变化大于类间变化.针对如何降低较大的类内变化对人脸验证研究的影响,本文结合加权子空间,提出了一种带先验相似性和先验距离约束的相似度度量学习方法.首先,利用类内人脸对样本,学习带权重的类内协方差矩阵,通过加权子空间的投影,从人脸图像中获得鲁棒性的人脸特征表达;其次,利用样本对的相似性与差异性,建立了带先验相似性和先验距离约束的相似度度量学习模型,优化后的度量矩阵可以有效提高特征向量的类内鲁棒性和类间判别性;最后,利用优化的度量矩阵计算人脸对的相似度.在LFW(Labeled Faces in the Wild)数据集的实验验证了所提模型的有效性,与其它同类相似度度量学习方法相比,优化的度量矩阵更能准确地评估人脸间的相似性,并在受限训练集上取得了91.2%的识别率.
Under the unconstrained conditions,intra-personal variation is much larger than the interpersonal variation in face images due to the affecting factors such as expression,posture,illumination and background etc.To reduce the influence of larger intra-personal on face verification,we proposed a similarity metric learning method with priori similarity and priori distance constraint by combining weighted subspace.First,the weighted intra-personal covariance matrix is learned by employing intra-personal face samples.By projecting into the intra-subspace,robust face feature representations can be obtained from face images.Second,we set up the similarity metric learning model with priori similarity and priori distance constraint,which effectively employs the similarity and discrimination information of samples that are in pairs,and the learned metric matrix can improve the robustness to intra-personal and discrimination to inter-personal.Finally,the updated metric matrix is used to compute the similarity scores of face-pairs.The experiments have been conducted on the Labeled Faces in the Wild(LFW)dataset,which shows the effectiveness of our proposed model.Compared with other metric learning methods,our learned metric matrix has higher accuracy rate for evaluating the face-pair similarity,and achieves a verification rate of91.2% on the restricted setting.
Under the unconstrained conditions,intra-personal variation is much larger than the interpersonal variation in face images due to the affecting factors such as expression,posture,illumination and background etc.To reduce the influence of larger intra-personal on face verification,we proposed a similarity metric learning method with priori similarity and priori distance constraint by combining weighted subspace.First,the weighted intra-personal covariance matrix is learned by employing intra-personal face samples.By projecting into the intra-subspace,robust face feature representations can be obtained from face images.Second,we set up the similarity metric learning model with priori similarity and priori distance constraint,which effectively employs the similarity and discrimination information of samples that are in pairs,and the learned metric matrix can improve the robustness to intra-personal and discrimination to inter-personal.Finally,the updated metric matrix is used to compute the similarity scores of face-pairs.The experiments have been conducted on the Labeled Faces in the Wild(LFW)dataset,which shows the effectiveness of our proposed model.Compared with other metric learning methods,our learned metric matrix has higher accuracy rate for evaluating the face-pair similarity,and achieves a verification rate of91.2% on the restricted setting.
引文
[1]XIANG Y,SU G.Multi-parts and multi-feature fusion in face verification[C]//Computer Vision and Pattern Recognition Workshops(CVPRW),IEEE Computer Society Conference on.Anchorage AK US:IEEE Computer Society,2008:1-6.
[2]HUANG G B,LEE H,LEARNED-MILLER E.Learning hierarchical representations for face verification with convolutional deep belief networks[C]//Computer Vision and Pattern Recognition(CVPR),IEEE Conference on.Rhode Island,USA:IEEE Computer Society,2012:2518-2525.
[3]LI H,HUA G,LIN Z,et al.Probabilistic elastic matching for pose variant face verification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Portland Maine,USA:IEEE Computer Society,2013:3499-3506.
[4]HUANG R,LI T,YE M,et al.Unconstrained face verification by optimally organizing multiple classifiers[J].International Journal of Control,Automation and Systems,2014,12(4):833-842.
[5]沈媛媛,严严,王菡子.有监督的距离度量学习算法研究进展[J].自动化学报,2014,40(12):2673-2686.SHEN Y Y,YAN Y,WANG H Z.Recent advances on supervised distance metric learning algorithms[J].Acta Automatic Sinica,2014,40(12):2673-2686.(In Chinese)
[6]WOLF L,HASSNER T,TAIGMAN Y.Similarity scores based on background samples[C]//Asian Conference on Computer Vision.Springer Berlin Heidelberg,2009:88-97.
[7]CHOPRA S,HADSELL R,LECUN Y.Learning a similarity metric discriminatively,with application to face verification[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR).San Diego,CA,USA:IEEE Computer Society,2005:539-546.
[8]LIU C,WECHSLER H.Gabor feature based classification using the enhanced fisher linear discriminant model for face recognition[J].IEEE Transactions on Image Processing,2002,11(4):467-476.
[9]GUILLAUMIN M,VERBEEK J,SCHMID C.Is that you?metric learning approaches for face identification[C]//IEEE12th International Conference on Computer Vision.San Francisco,CA,USA:IEEE Computer Society,2009:498-505.
[10]MIGNON A,JURIE F.Pcca:A new approach for distance learning from sparse pairwise constraints[C]//IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Rhode Island,USA:IEEE Computer Society,2012:2666-2672.
[11]KSTINGER M,HIRZER M,WOHLHART P,et al.Large scale metric learning from equivalence constraints[C]//Computer Vision and Pattern Recognition(CVPR),IEEE Conference on.Rhode Island,USA:IEEE Computer Society,2012:2288-2295.
[12]YING Y,LI P.Distance metric learning with eigenvalue optimization[J].Journal of Machine Learning Research,2012,13(1):1-26.
[13]CAO Q,YING Y,LI P.Similarity metric learning for face recognition[C]//Proceedings of the IEEE International Conference on Computer Vision.Portland,Maine,USA:IEEE Computer Society,2013:2408-2415.
[14]NGUYEN H V,BAI L.Cosine similarity metric learning for face verification[C]//Asian Conference on Computer Vision.Springer Berlin Heidelberg,2010:709-720.
[15]FANG Y,CHEN Y Y S,WANG H,et al.Sparse similarity metric learning for kinship verification[C]//Visual Communications and Image Processing(VCIP).Chengdu,China:IEEE Computer Society,2016:1-4.
[16]FANG Y,YAN Y,WANG H,et al.Adaptive metric learning with the low rank constraint[C]//Proceedings of the International Conference on Internet Multimedia Computing and Service.Xi'an,Chian:ACM,2016:61-65.
[17]DING Z,SUH S,HAN J J,et al.Discriminative low-rank metric learningfor face recognition[C]//Automatic Face and Gesture Recognition(FG),11th IEEE International Conference and Workshops on.Ljubljana,Slovenia:IEEE Computer Society,2015:1-6.
[18]HASSNER T,HAREL S,PAZ E,et al.Effective face frontalization in unconstrained images[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Boston,MA,USA:IEEE Computer Society,2015:4295-4304.
[19]HU J,LU J,TAN Y P.Discriminative deep metric learning for face verification in the wild[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Columbus,OH,USA:IEEE Computer Society,2014:1875-1882.
[20]ZHU X,LEI Z,YAN J,et al.High-fidelity pose and expression normalization for face recognition in the wild[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Boston,MA,USA:IEEE Computer Society,2015:787-796.
[21]TAIGMAN Y,YANG M,RANZATO M A,et al.Deepface:Closing the gap to human-level performance in face verification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Columbus,OH,USA:IEEE Computer Society,2014:1701-1708.
[22]SUN Y,WANG X,TANG X.Deep learning face representation from predicting 10,000classes[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Columbus,OH,USA:IEEE Computer Society,2014:1891-1898.
[23]SUN Y,CHEN Y,WANG X,et al.Deep learning face representation by joint identification-verification[C]//Advances in Neural Information Processing Systems.Palais des Congrès de Montréal,2014:1988-1996.
[24]SUN Y,LIANG D,WANG X,et al.Deepid3:Face recognition with very deep neural networks[J].arXiv preprint arXiv:1502.00873,2015.
[25]LU J,PLATANIOTIS K N,VENETSANOPOULOS A N.Face recognition using LDA-based algorithms[J].IEEE Transactions on Neural Networks,2003,14(1):195-200.
[26]MOGHADDAM B,JEBARA T,PENTLAND A.Bayesian face recognition[J].Pattern Recognition,2000,33(11):1771-1782.
[27]PRICE J R,GEE T F.Face recognition using direct,weighted linear discriminant analysis and modular subspaces[J].Pattern Recognition,2005,38(2):209-219.
[28]OJALA T,PIETIKAINEN M,MAENPAA T.Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(7):971-987.
[29]WOLF L,HASSNER T,TAIGMAN Y.Descriptor based methods in the wild[C]//Workshop on Faces in'Real-life'Images:Detection,Alignment,and Recognition.Palais des Congrès Parc Chanot,2008.
[30]HUANG G B,MATTAR M,BERG T,et al.Labeled faces in the wild:A database for studying face recognition in unconstrained environments[C]//Workshop on Faces in'Real-Life'Images:Detection,Alignment,and Recognition.Palais des Congrès Parc Chanot,2008.
[31]TAIGMAN Y,WOLF L,HASSNER T.Multiple one-shots for utilizing class label information[C]//BMVC.London:2009:1-12.
[32]BELHUMEUR P N,HESPANHA J P,KRIEGMAN D J.Eigenfaces vs.fisherfaces:Recognition using class specific linear projection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(7):711-720.
[33]http://www.robots.ox.ac.uk/~vgg/software/vgg_face/
[34]COX D,PINTO N.Beyond simple features:A large-scale feature search approach to unconstrained face recognition[C]//IEEE International Conference on Automatic Face&Gesture Recognition and Workshops(FG).Santa Barbara,CA,USA:IEEE Computer Society,2011:8-15.
[2]HUANG G B,LEE H,LEARNED-MILLER E.Learning hierarchical representations for face verification with convolutional deep belief networks[C]//Computer Vision and Pattern Recognition(CVPR),IEEE Conference on.Rhode Island,USA:IEEE Computer Society,2012:2518-2525.
[3]LI H,HUA G,LIN Z,et al.Probabilistic elastic matching for pose variant face verification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Portland Maine,USA:IEEE Computer Society,2013:3499-3506.
[4]HUANG R,LI T,YE M,et al.Unconstrained face verification by optimally organizing multiple classifiers[J].International Journal of Control,Automation and Systems,2014,12(4):833-842.
[5]沈媛媛,严严,王菡子.有监督的距离度量学习算法研究进展[J].自动化学报,2014,40(12):2673-2686.SHEN Y Y,YAN Y,WANG H Z.Recent advances on supervised distance metric learning algorithms[J].Acta Automatic Sinica,2014,40(12):2673-2686.(In Chinese)
[6]WOLF L,HASSNER T,TAIGMAN Y.Similarity scores based on background samples[C]//Asian Conference on Computer Vision.Springer Berlin Heidelberg,2009:88-97.
[7]CHOPRA S,HADSELL R,LECUN Y.Learning a similarity metric discriminatively,with application to face verification[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR).San Diego,CA,USA:IEEE Computer Society,2005:539-546.
[8]LIU C,WECHSLER H.Gabor feature based classification using the enhanced fisher linear discriminant model for face recognition[J].IEEE Transactions on Image Processing,2002,11(4):467-476.
[9]GUILLAUMIN M,VERBEEK J,SCHMID C.Is that you?metric learning approaches for face identification[C]//IEEE12th International Conference on Computer Vision.San Francisco,CA,USA:IEEE Computer Society,2009:498-505.
[10]MIGNON A,JURIE F.Pcca:A new approach for distance learning from sparse pairwise constraints[C]//IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Rhode Island,USA:IEEE Computer Society,2012:2666-2672.
[11]KSTINGER M,HIRZER M,WOHLHART P,et al.Large scale metric learning from equivalence constraints[C]//Computer Vision and Pattern Recognition(CVPR),IEEE Conference on.Rhode Island,USA:IEEE Computer Society,2012:2288-2295.
[12]YING Y,LI P.Distance metric learning with eigenvalue optimization[J].Journal of Machine Learning Research,2012,13(1):1-26.
[13]CAO Q,YING Y,LI P.Similarity metric learning for face recognition[C]//Proceedings of the IEEE International Conference on Computer Vision.Portland,Maine,USA:IEEE Computer Society,2013:2408-2415.
[14]NGUYEN H V,BAI L.Cosine similarity metric learning for face verification[C]//Asian Conference on Computer Vision.Springer Berlin Heidelberg,2010:709-720.
[15]FANG Y,CHEN Y Y S,WANG H,et al.Sparse similarity metric learning for kinship verification[C]//Visual Communications and Image Processing(VCIP).Chengdu,China:IEEE Computer Society,2016:1-4.
[16]FANG Y,YAN Y,WANG H,et al.Adaptive metric learning with the low rank constraint[C]//Proceedings of the International Conference on Internet Multimedia Computing and Service.Xi'an,Chian:ACM,2016:61-65.
[17]DING Z,SUH S,HAN J J,et al.Discriminative low-rank metric learningfor face recognition[C]//Automatic Face and Gesture Recognition(FG),11th IEEE International Conference and Workshops on.Ljubljana,Slovenia:IEEE Computer Society,2015:1-6.
[18]HASSNER T,HAREL S,PAZ E,et al.Effective face frontalization in unconstrained images[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Boston,MA,USA:IEEE Computer Society,2015:4295-4304.
[19]HU J,LU J,TAN Y P.Discriminative deep metric learning for face verification in the wild[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Columbus,OH,USA:IEEE Computer Society,2014:1875-1882.
[20]ZHU X,LEI Z,YAN J,et al.High-fidelity pose and expression normalization for face recognition in the wild[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Boston,MA,USA:IEEE Computer Society,2015:787-796.
[21]TAIGMAN Y,YANG M,RANZATO M A,et al.Deepface:Closing the gap to human-level performance in face verification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Columbus,OH,USA:IEEE Computer Society,2014:1701-1708.
[22]SUN Y,WANG X,TANG X.Deep learning face representation from predicting 10,000classes[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Columbus,OH,USA:IEEE Computer Society,2014:1891-1898.
[23]SUN Y,CHEN Y,WANG X,et al.Deep learning face representation by joint identification-verification[C]//Advances in Neural Information Processing Systems.Palais des Congrès de Montréal,2014:1988-1996.
[24]SUN Y,LIANG D,WANG X,et al.Deepid3:Face recognition with very deep neural networks[J].arXiv preprint arXiv:1502.00873,2015.
[25]LU J,PLATANIOTIS K N,VENETSANOPOULOS A N.Face recognition using LDA-based algorithms[J].IEEE Transactions on Neural Networks,2003,14(1):195-200.
[26]MOGHADDAM B,JEBARA T,PENTLAND A.Bayesian face recognition[J].Pattern Recognition,2000,33(11):1771-1782.
[27]PRICE J R,GEE T F.Face recognition using direct,weighted linear discriminant analysis and modular subspaces[J].Pattern Recognition,2005,38(2):209-219.
[28]OJALA T,PIETIKAINEN M,MAENPAA T.Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(7):971-987.
[29]WOLF L,HASSNER T,TAIGMAN Y.Descriptor based methods in the wild[C]//Workshop on Faces in'Real-life'Images:Detection,Alignment,and Recognition.Palais des Congrès Parc Chanot,2008.
[30]HUANG G B,MATTAR M,BERG T,et al.Labeled faces in the wild:A database for studying face recognition in unconstrained environments[C]//Workshop on Faces in'Real-Life'Images:Detection,Alignment,and Recognition.Palais des Congrès Parc Chanot,2008.
[31]TAIGMAN Y,WOLF L,HASSNER T.Multiple one-shots for utilizing class label information[C]//BMVC.London:2009:1-12.
[32]BELHUMEUR P N,HESPANHA J P,KRIEGMAN D J.Eigenfaces vs.fisherfaces:Recognition using class specific linear projection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(7):711-720.
[33]http://www.robots.ox.ac.uk/~vgg/software/vgg_face/
[34]COX D,PINTO N.Beyond simple features:A large-scale feature search approach to unconstrained face recognition[C]//IEEE International Conference on Automatic Face&Gesture Recognition and Workshops(FG).Santa Barbara,CA,USA:IEEE Computer Society,2011:8-15.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |