基于深度学习和约束稀疏表达的人脸识别算法
|
摘要
目前的人脸特征匹配算法大多关注于单图像与单图像的匹配而不能有效利用图像序列之间的相关信息,因而提出了一种基于深度学习与约束稀疏表达的人脸特征匹配算法.通过CNN网络对人脸图像进行特征提取,并利用改进的稀疏表达方法自动选取相似的图像序列进行特征匹配,有效地利用了图像序列之间的相关信息.实验结果表明,该算法在LFW和AR数据库上取得了很好的效果并优于传统的SRC,L1-norm和CRC-RLS算法.
The matching between single image and single image has attracted much attention in the current face feature matching algorithms,in order to make use of the correlation information between image sequences effectively,a face feature matching algorithm based on deep learning and constraint sparse representation was proposed.The feature extraction of face images was carried out through CNN network,and an improved sparse expression method was used to automatically select similar image sequences for feature matching,so that the correlation information between image sequences could be effectively utilized.Experimental results show that the proposed algorithm can achieve better result in LFW and AR databases,and is superior to other face feature matching methods,such as SRC,L1-norm and CRC-RLS.
The matching between single image and single image has attracted much attention in the current face feature matching algorithms,in order to make use of the correlation information between image sequences effectively,a face feature matching algorithm based on deep learning and constraint sparse representation was proposed.The feature extraction of face images was carried out through CNN network,and an improved sparse expression method was used to automatically select similar image sequences for feature matching,so that the correlation information between image sequences could be effectively utilized.Experimental results show that the proposed algorithm can achieve better result in LFW and AR databases,and is superior to other face feature matching methods,such as SRC,L1-norm and CRC-RLS.
引文
[1]Buciu L.A new sparse image representation algorithm applied to facial expression recognition[C]∥Proceedings of the 2004 14th IEEE Signal Processing Society Workshop Machine Learning for Signal Processing.[S.l.]:IEEE,2004.
[2]Li X X,Tao J,Hao Z.Expression-insensitive 3Dface recognition using sparse representation[C]∥2009IEEEConference on Computer Vision and Pattern Recognition.[S.l.]:IEEE,2009.
[3]Wright J,Yang A Y,Sastry S S,et al.Robust face recognition via sparse representation[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2009,31(2):210.
[4]Zhang L,Yang M.Sparse representation or collaborative representation:which helps face recognition?[J].International Conference on Computer Vision,2011(5):471-478.
[5]Li Yuan,Fen Li.Face recognition with occlusion via support vector discrimination dictionary and occlusion dictionary based sparse representation classification[J].Chinese Association of Automation,2016,2017:110-115.
[6]Liu Luoluo,Tran T D,Chin S P.Partial face recognition:a sparse representation-based approach[C]∥IEEE International Conference on Acoustics.Shanghai,China:IEEE,2016:2389-2393.
[7]Zhang Yan,Peng Hua.One sample per person face recognition via sparse representation[J].Iet Signal Processing,2017,10(9):1126-1134.
[8]Wyglinski A M,Labeau F,Kabal P.An efficient bit allocation algorithm for multicarrier modulation[J].Wireless Communications&Networking Conference,2004,2:1194-1199.
[9]Wen Ying.A novel dictionary based SRC for face recognition[C]∥2017IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP).New orleans,LA,USA:IEEE,2017:2582-2586.
[10]Xu Yong,Zhong Zuofeng,Yang Jian,et al.A new discriminative sparse representation method for robust face recognition via l2regularization[J].IEEE Transactions on Neural Networks and Learning Systems,2016(99):1-10.
[11]Farshid Hajati,Mohammad Tavakolian,Soheila Gheisari,et al.Dynamic texture comparison using derivative sparse representation:application to video-based face recognition[J].IEEE Transactions on Human-Machine Systems,2017(99):1-13.
[12]李懿,刘晓东.一种新的模糊稀疏表示人脸识别算法[J].大连理工大学学报,2017,57(2):189-194.Li Yi,Liu Xiaodong.A new fuzzy sparse representation algorithm for face recognition[J].Journal of Dalian University of Technology,2017,57(2):189-194.(in Chinese)
[13]赵清杰,齐惠,张雨,等.基于局部正脸合成和两阶段表示的三阶段人脸识别算法[J].北京理工大学学报,2017,37(6):637-644.Zhao Qingjie,Qi Hui,Zhang Yu,et al.Three-phase face recognition algorithm via locally frontal face synthesis and two-phase face recognition[J].Transactions of Beijing Institute of Technology,2017,37(6):637-644.(in Chinese)
[14]Gao Yuan,Ma Jiayi,Yuille A L.Semi-supervised sparse representation based classification for face recognition with insufficient labeled samples[J].IEEE Transactions on Image Processing,2016(99):1.
[15]He K,Zhang X,Ren S,et al.Deep residual learning for image recognition[C]∥The IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Las Vegas,USA:IEEE,2016:770-778.
[16]Krizhevsky A,Sutskever I,Hinton G E.Imagenet classification with deep convolutional neural networks[C]∥NIPS.Harrahs and Harveys,Lake Tahoe:[s.n],2012:1097-1105.
[17]Simonyan K,Zisserman A.Very deep convolutional networks for large-scale image recognition[EB/OL].2014-01-02.http:∥arXiv.org/abs/1409.1556.
[18]Szegedy C,Liu W,Jia Y P,et al.Going deeper with convolutions[C]∥The IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Boston,Massachusetts:IEEE,2015:1-9.
[19]Schroff F,Kalenichenko D,Philbin J.Facenet:a unified embedding for face recognition and clustering[C]∥CVPR.Boston,Massachusetts:IEEE,2015:815-823.
[20]Sun Y,Chen Y,Wang,et al.Deep learning face representation by joint identification-verification[C]∥NIPS.Montreal,Canada:[s.n.],2014:1988-1996.
[21]Wen Y,Zhang K,Li Z,et al.A discriminative feature learning approach for deep face recognition[C]∥ECCV.Amsterdom,The Netherlands:[s.n.],2016:499-515.
[22]Parkhi O M,Vedaldi A,Zisserman A.Deep face recognition[C]∥Proceedings of the British Machine Vision Conference(BMVC).Swansea,UK:[s.n.],2015:1-12.
[2]Li X X,Tao J,Hao Z.Expression-insensitive 3Dface recognition using sparse representation[C]∥2009IEEEConference on Computer Vision and Pattern Recognition.[S.l.]:IEEE,2009.
[3]Wright J,Yang A Y,Sastry S S,et al.Robust face recognition via sparse representation[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2009,31(2):210.
[4]Zhang L,Yang M.Sparse representation or collaborative representation:which helps face recognition?[J].International Conference on Computer Vision,2011(5):471-478.
[5]Li Yuan,Fen Li.Face recognition with occlusion via support vector discrimination dictionary and occlusion dictionary based sparse representation classification[J].Chinese Association of Automation,2016,2017:110-115.
[6]Liu Luoluo,Tran T D,Chin S P.Partial face recognition:a sparse representation-based approach[C]∥IEEE International Conference on Acoustics.Shanghai,China:IEEE,2016:2389-2393.
[7]Zhang Yan,Peng Hua.One sample per person face recognition via sparse representation[J].Iet Signal Processing,2017,10(9):1126-1134.
[8]Wyglinski A M,Labeau F,Kabal P.An efficient bit allocation algorithm for multicarrier modulation[J].Wireless Communications&Networking Conference,2004,2:1194-1199.
[9]Wen Ying.A novel dictionary based SRC for face recognition[C]∥2017IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP).New orleans,LA,USA:IEEE,2017:2582-2586.
[10]Xu Yong,Zhong Zuofeng,Yang Jian,et al.A new discriminative sparse representation method for robust face recognition via l2regularization[J].IEEE Transactions on Neural Networks and Learning Systems,2016(99):1-10.
[11]Farshid Hajati,Mohammad Tavakolian,Soheila Gheisari,et al.Dynamic texture comparison using derivative sparse representation:application to video-based face recognition[J].IEEE Transactions on Human-Machine Systems,2017(99):1-13.
[12]李懿,刘晓东.一种新的模糊稀疏表示人脸识别算法[J].大连理工大学学报,2017,57(2):189-194.Li Yi,Liu Xiaodong.A new fuzzy sparse representation algorithm for face recognition[J].Journal of Dalian University of Technology,2017,57(2):189-194.(in Chinese)
[13]赵清杰,齐惠,张雨,等.基于局部正脸合成和两阶段表示的三阶段人脸识别算法[J].北京理工大学学报,2017,37(6):637-644.Zhao Qingjie,Qi Hui,Zhang Yu,et al.Three-phase face recognition algorithm via locally frontal face synthesis and two-phase face recognition[J].Transactions of Beijing Institute of Technology,2017,37(6):637-644.(in Chinese)
[14]Gao Yuan,Ma Jiayi,Yuille A L.Semi-supervised sparse representation based classification for face recognition with insufficient labeled samples[J].IEEE Transactions on Image Processing,2016(99):1.
[15]He K,Zhang X,Ren S,et al.Deep residual learning for image recognition[C]∥The IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Las Vegas,USA:IEEE,2016:770-778.
[16]Krizhevsky A,Sutskever I,Hinton G E.Imagenet classification with deep convolutional neural networks[C]∥NIPS.Harrahs and Harveys,Lake Tahoe:[s.n],2012:1097-1105.
[17]Simonyan K,Zisserman A.Very deep convolutional networks for large-scale image recognition[EB/OL].2014-01-02.http:∥arXiv.org/abs/1409.1556.
[18]Szegedy C,Liu W,Jia Y P,et al.Going deeper with convolutions[C]∥The IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Boston,Massachusetts:IEEE,2015:1-9.
[19]Schroff F,Kalenichenko D,Philbin J.Facenet:a unified embedding for face recognition and clustering[C]∥CVPR.Boston,Massachusetts:IEEE,2015:815-823.
[20]Sun Y,Chen Y,Wang,et al.Deep learning face representation by joint identification-verification[C]∥NIPS.Montreal,Canada:[s.n.],2014:1988-1996.
[21]Wen Y,Zhang K,Li Z,et al.A discriminative feature learning approach for deep face recognition[C]∥ECCV.Amsterdom,The Netherlands:[s.n.],2016:499-515.
[22]Parkhi O M,Vedaldi A,Zisserman A.Deep face recognition[C]∥Proceedings of the British Machine Vision Conference(BMVC).Swansea,UK:[s.n.],2015:1-12.
© 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 |