基于双路CNN的多姿态人脸识别方法
|
摘要
提出了一种基于卷积神经网络(Convolutional Neural Network,CNN)的多姿态人脸识别方法。利用该方法可以将输入的人脸投影到高维特征空间并输出具备姿态鲁棒性的人脸特征,从而进行精确的多姿态人脸识别。经过大量的实验验证,该模型在多个数据集上取得了良好效果。与传统的单路CNN网络层次结构不同,本文方法采用双路CNN网络层次结构并结合度量学习来优化传统的CNN模型。最后,使用Tensorflow深度学习框架进行实验,实验结果表明,该框架的识别准确率比目前几种常用的多姿态人脸识别算法的识别准确率更高。
Face recognition has always been a hot topic in the field of computer vision and pattern recognition.With the development of deep learning and the improvement of computer computing performance, a fairly good recognition rate can be obtained on multiple datasets. However, the high recognition rates only exist in the input image sets that are obtained by a standard frontal pose. When face pose changes, the recognition rate will decline rapidly,especially in the case that the face angle is at 45° to 90°. This paper proposes an effective method for pose-invariant face recognition based on convolutional neural network(CNN). This network can project the input face to a high dimensional feature space for explicitly disentangling the identity and pose information in the latent feature space.Different from the conventional deep learning methods that mainly rely on single path CNN structure, the proposed method utilizes the two-pathway CNN structure and metric learning to obtain a feature representation that is invariant to false pose. In the image preprocessing stage, we use the ready-made dlib C++ Library to detect the face and wipe out of the effect of the background. During the model phase, we design a CNN architecture similar to Siamese network for metric learning. Finally, this experiments are made via deep learning framework. The authoritative database is adopted o verify the validity of the proposed model in this paper. Experimental results show that the recognition accuracy of this framework is higher than that of several conventional multi-pose face recognition algorithms.
Face recognition has always been a hot topic in the field of computer vision and pattern recognition.With the development of deep learning and the improvement of computer computing performance, a fairly good recognition rate can be obtained on multiple datasets. However, the high recognition rates only exist in the input image sets that are obtained by a standard frontal pose. When face pose changes, the recognition rate will decline rapidly,especially in the case that the face angle is at 45° to 90°. This paper proposes an effective method for pose-invariant face recognition based on convolutional neural network(CNN). This network can project the input face to a high dimensional feature space for explicitly disentangling the identity and pose information in the latent feature space.Different from the conventional deep learning methods that mainly rely on single path CNN structure, the proposed method utilizes the two-pathway CNN structure and metric learning to obtain a feature representation that is invariant to false pose. In the image preprocessing stage, we use the ready-made dlib C++ Library to detect the face and wipe out of the effect of the background. During the model phase, we design a CNN architecture similar to Siamese network for metric learning. Finally, this experiments are made via deep learning framework. The authoritative database is adopted o verify the validity of the proposed model in this paper. Experimental results show that the recognition accuracy of this framework is higher than that of several conventional multi-pose face recognition algorithms.
引文
[1]BANSAL A,NANDURI A,CASTILLO C,et al.UMD-Faces:An annotated face dataset for training deep networks[C]//2017 IEEE International Joint Conference on Biometrics.USA:IEEE,2016:464-473.
[2]CHEN D,CAO X,WEN F,et al.Blessing of dimensionality:High-dimensional feature and its efficient compression for face verification[J].Computer Vision&Pattern Recognition,2013,9(4):3025-3032.
[3]GONZALEZ-JIMENEZ D,ALBA-CASTRO J L.Toward pose-invariant 2-D face recognition through point distribution models and facial symmetry[J].IEEE Transaction Information Forensics&Security,2007,2(3):413-429.
[4]GAO H,EKENEL H K,STIEFELHAGEN R.Pose normalization for local appearance-based face recognition[C]//Advances in Biometrics,Third International Conference.Alghero,Italy:DBLP,2009:32-41.
[5]BLANZ V,VETTER T.Face recognition based on fitting a3D morphable model[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2003,25(9):1063-1074.
[6]ASTHANA A,MARKS T K,JONES M J,et al.Fully automatic pose-invariant face recognition via 3D pose normalization[C]//International Conference on Computer Vision.USA:IEEE,2011:937-944.
[7]DING C,XU C,TAO D.Multi-task pose-invariant face recognition[J].IEEE Transactions on Image Processing,2015,24(3):980-993.
[8]CAO Z,YIN Q,TANG X,et al.Face recognition with learning based descriptor[C]//IEEE Conference on Computer Vision and Pattern Recognition.USA:IEEE,2010:2707-2714.
[9]CHEN D,CAO X,WEN F,et al.Blessing of dimensionality:High-dimensional feature and its efficient compression for face verification[C]//IEEE Conference on Computer Vision and Pattern Recognition.USA:IEEE,2013:3025-3032.
[10]YI D,LEI Z,LI S Z.Towards pose robust face recognition[C]//IEEE Conference on Computer Vision and Pattern Recognition.USA:IEEE,2013:3539-3545.
[11]PARKHI O M,VEDALDI A,ZISSERMAN A.Deep face recognition[C]//British Machine Vision Conference.[s.l.]:[s.n.],2015:1-12.
[12]TAIGMAN Y,YANG M,RANZATO M,et al.DeepFace:Closing the gap to Human-level performance in face verification[C]//IEEE Conference on Computer Vision and Pattern Recognition.USA:IEEE,2014:1701-1708.
[13]SCHROFF F,KALENICHENKO D,PHILBIN J.FaceNet:A unified embedding for face recognition and clustering[C]//IEEE Conference on Computer Vision and Pattern Recognition.USA:IEEE,2015:815-823.
[14]GROSS R,MATTHEWS I,COHN J,et al.Multi-PIE[J].Image&Vision Computing,2010,28(5):807-813.
[15]SENGUPTA S,CHEN J C,CASTILLO C,et al.Frontal to profile face verification in the wild[C]//IEEE Winter Conference on Applications of Computer Vision.USA:IEEE,2016:1-9.
[16]DING C,TAO D.Pose-invariant face recognition with homography-based normalization[J].Pattern Recognition,2017,66:144-152.
[17]LUAN T,YIN X,LIU X.Disentangled representation learning GAN for pose-invariant face recognition[C]//IEEEConference on Computer Vision and Pattern Recognition.USA:IEEE,2017:1283-1292.
[2]CHEN D,CAO X,WEN F,et al.Blessing of dimensionality:High-dimensional feature and its efficient compression for face verification[J].Computer Vision&Pattern Recognition,2013,9(4):3025-3032.
[3]GONZALEZ-JIMENEZ D,ALBA-CASTRO J L.Toward pose-invariant 2-D face recognition through point distribution models and facial symmetry[J].IEEE Transaction Information Forensics&Security,2007,2(3):413-429.
[4]GAO H,EKENEL H K,STIEFELHAGEN R.Pose normalization for local appearance-based face recognition[C]//Advances in Biometrics,Third International Conference.Alghero,Italy:DBLP,2009:32-41.
[5]BLANZ V,VETTER T.Face recognition based on fitting a3D morphable model[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2003,25(9):1063-1074.
[6]ASTHANA A,MARKS T K,JONES M J,et al.Fully automatic pose-invariant face recognition via 3D pose normalization[C]//International Conference on Computer Vision.USA:IEEE,2011:937-944.
[7]DING C,XU C,TAO D.Multi-task pose-invariant face recognition[J].IEEE Transactions on Image Processing,2015,24(3):980-993.
[8]CAO Z,YIN Q,TANG X,et al.Face recognition with learning based descriptor[C]//IEEE Conference on Computer Vision and Pattern Recognition.USA:IEEE,2010:2707-2714.
[9]CHEN D,CAO X,WEN F,et al.Blessing of dimensionality:High-dimensional feature and its efficient compression for face verification[C]//IEEE Conference on Computer Vision and Pattern Recognition.USA:IEEE,2013:3025-3032.
[10]YI D,LEI Z,LI S Z.Towards pose robust face recognition[C]//IEEE Conference on Computer Vision and Pattern Recognition.USA:IEEE,2013:3539-3545.
[11]PARKHI O M,VEDALDI A,ZISSERMAN A.Deep face recognition[C]//British Machine Vision Conference.[s.l.]:[s.n.],2015:1-12.
[12]TAIGMAN Y,YANG M,RANZATO M,et al.DeepFace:Closing the gap to Human-level performance in face verification[C]//IEEE Conference on Computer Vision and Pattern Recognition.USA:IEEE,2014:1701-1708.
[13]SCHROFF F,KALENICHENKO D,PHILBIN J.FaceNet:A unified embedding for face recognition and clustering[C]//IEEE Conference on Computer Vision and Pattern Recognition.USA:IEEE,2015:815-823.
[14]GROSS R,MATTHEWS I,COHN J,et al.Multi-PIE[J].Image&Vision Computing,2010,28(5):807-813.
[15]SENGUPTA S,CHEN J C,CASTILLO C,et al.Frontal to profile face verification in the wild[C]//IEEE Winter Conference on Applications of Computer Vision.USA:IEEE,2016:1-9.
[16]DING C,TAO D.Pose-invariant face recognition with homography-based normalization[J].Pattern Recognition,2017,66:144-152.
[17]LUAN T,YIN X,LIU X.Disentangled representation learning GAN for pose-invariant face recognition[C]//IEEEConference on Computer Vision and Pattern Recognition.USA:IEEE,2017:1283-1292.