基于高斯过程的快速人脸验证
|
摘要
为解决目前实现人脸验证算法所需训练样本多、运算量大、识别速度慢等问题,提出了一种在小样本空间中基于高斯过程的快速人脸验证方法。首先使用共轭梯度下降法从训练样本中学习人脸关键部位特征位置的梯度方向,从而可对待验证人脸进行特征定位;然后使用自适应尺度局部二值模式提取特征,以减小特征维度;最后将谱混合核函数作为高斯过程的核函数对输入的人脸特征进行分类。使用LFW、FERET和Multi-PIE人脸数据库进行训练和测试,实验结果表明使用自适应尺度局部二值模式有效地减小了特征维度,使用高斯过程模型与谱混合核相结合可大幅减少训练样本,显著提升训练速度和测试速度。
This paper proposed a fast face verification method based on Gaussian process in small sample space to solve the problem of large training samples,complex computation and the slow recognition. Firstly,it used the conjugate gradient descent to detect the face feature points,and then used the adaptive multi-scale local binary model to extract the features at the feature points reduced the feature dimensions. Finally,it used the spectral kernel function as the kernel function of the Gaussian process to classify the input face features. This paper carried out training and testing using LFW,FERET and Multi-PIE face database. The experimental results show that the local binary model can effectively reduce the feature dimension. The combination of the Gaussian process model and the spectral hybrid core can greatly reduce the training samples and improve the training speed and test speed.
This paper proposed a fast face verification method based on Gaussian process in small sample space to solve the problem of large training samples,complex computation and the slow recognition. Firstly,it used the conjugate gradient descent to detect the face feature points,and then used the adaptive multi-scale local binary model to extract the features at the feature points reduced the feature dimensions. Finally,it used the spectral kernel function as the kernel function of the Gaussian process to classify the input face features. This paper carried out training and testing using LFW,FERET and Multi-PIE face database. The experimental results show that the local binary model can effectively reduce the feature dimension. The combination of the Gaussian process model and the spectral hybrid core can greatly reduce the training samples and improve the training speed and test speed.
引文
[1] Kumar N,Berg A C,Belhumeur P N,et al. Attribute and simile classifiers for face verification[C]//Proc of IEEE International Conference on Computer Vision. Piscataway,NJ:IEEE Press,2010:365-372.
[2] Huang G B. Learning hierarchical representations for face verification with convolutional deep belief networks[C]//Proc of IEEE Conference on Computer Vision and Pattern Recognition. Washington DC:IEEE Computer Society,2012:2518-2525.
[3] Milanfar H J S P. Face verification using the LARK face,representation[J]. IEEE Trans on Information Forensics&Security,2011,6(4):1275-1286.
[4] Sun Yi,Wang Xiaogang,Tang Xiao’ou. Deep learning face representation from predicting 10,000 classes[C]//Proc of IEEE Conference on Computer Vision and Pattern Recognition. Washington DC:IEEE Computer Society,2014:1891-1898.
[5] Sun Yi,Liang Ding,Wang Xiaogang,et al. DeepID3:face recognition with very deep neural networks[EB/OL].(2015-02-04). https://arxiv.org/abs/1502.00873.
[6] Sun Yi,Chen Yuheng,Wang Xiaogang,et al. Deep learning face representation by joint identification-verification[C]//Proc of the 27th International Conference on Neural Information Processing Systems.Cambridge,MA:MIT Press,2014:1988-1996.
[7] Ben Xianye,Meng Weixiao,Yan Rui,et al. An improved biometrics technique based on metric learning approach[J]. Neurocomputing,2012,97(1):44-51.
[8] Zhu Zhenyao,Luo Ping,Wang Xiaogang,et al. Deep learning identitypreserving face space[C]//Proc of IEEE International Conference on Computer Vision. Piscataway,NJ:IEEE Press,2013:113-120.
[9] Sun Yi,Wang Xiaogang,Tang Xiao’ou. Hybrid deep learning for face verification[C]//Proc of IEEE International Conference on Computer Vision. Piscataway,NJ:IEEE Press,2014:1489-1496.
[10]Chen Dong,Cao Xudong,Wang Liwei,et al. Bayesian face revisited:a joint formulation[C]//Proc of European Conference on Computer Vision. Berlin:Springer-Verlag,2012:566-579.
[11]Kim S J,Magnani A,Boyd S. Optimal kernel selection in kernel fisher discriminant analysis[C]//Proc of International Conference on Machine Learning. New York:ACM Press,2006:465-472.
[12]Chen Dong,Cao Xudong,Wen Fang,et al. Blessing of dimensionality:high-dimensional feature and its efficient compression for face verification[C]//Proc of IEEE Conference on Computer Vision and Pattern Recognition. Washington DC:IEEE Computer Society,2013:3025-3032.
[13] Sagonas C,Tzimiropoulos G,Zafeiriou S,et al. 300 faces in-the-wild challenge:the first facial landmark localization challenge[C]//Proc of IEEE International Conference on Computer Vision Workshops. Washington DC:IEEE Computer Society,2013:397-403.
[14]Jones M J,Viola P. Robust real-time object detection[J]. International Journal of Computer Vision,2001,57(2):137-154.
[15]Zhu Zhenyao,Luo Ping,Wang Xiaogang,et al. Deep learning identitypreserving face space[C]//Proc of IEEE International Conference on Computer Vision. Piscataway,NJ:IEEE Press,2013:113-120.
[16]Wright J,Hua Gang. Implicit elastic matching with random projections for pose-variant face recognition[C]//Proc of IEEE Conference on Computer Vision and Pattern Recognition. Piscataway,NJ:IEEE Press,2009:1502-1509.
[17]Wilson A G,Hu Zhiting,Salakhutdinov R,et al. Deep kernel learning[EB/OL].(2015-11-09). https://arxiv. org/abs/1511. 02222.
[18] Wilson A G. Covariance kernels for fast automatic pattern discovery and extrapolation with Gaussian processes[C]//Proc of the 30 th International Conference on Machine Learning. Piscataway,NJ:IEEE Press,2014.
[19]Schroff F,Kalenichenko D,Philbin J. Face Net:a unified embedding for face recognition and clustering[C]//Proc of IEEE Conference on Computer Vision and Pattern Recognition. Washington DC:IEEE Computer Society,2015:815-823.
[20] Amos B,Ludwiczuk B,Satyanarayanan M. Openface:a general-purpose face recognition library with mobile applications[EB/OL].(2016-06-13). https://hgpu. org/? p=16213.
[21]Taigman Y,Yang Ming,Ranzato M,et al. Deep Face:closing the gap to human-level performance in face verification[C]//Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Piscatway,NJ:IEEE Press,2014:1701-1708.
[22] Ng H W,Winkler S. A data-driven approach to cleaning large face datasets[C]//Proc of IEEE International Conference on Image Processing. Piscatway,NJ:IEEE Press,2015:343-347.
[2] Huang G B. Learning hierarchical representations for face verification with convolutional deep belief networks[C]//Proc of IEEE Conference on Computer Vision and Pattern Recognition. Washington DC:IEEE Computer Society,2012:2518-2525.
[3] Milanfar H J S P. Face verification using the LARK face,representation[J]. IEEE Trans on Information Forensics&Security,2011,6(4):1275-1286.
[4] Sun Yi,Wang Xiaogang,Tang Xiao’ou. Deep learning face representation from predicting 10,000 classes[C]//Proc of IEEE Conference on Computer Vision and Pattern Recognition. Washington DC:IEEE Computer Society,2014:1891-1898.
[5] Sun Yi,Liang Ding,Wang Xiaogang,et al. DeepID3:face recognition with very deep neural networks[EB/OL].(2015-02-04). https://arxiv.org/abs/1502.00873.
[6] Sun Yi,Chen Yuheng,Wang Xiaogang,et al. Deep learning face representation by joint identification-verification[C]//Proc of the 27th International Conference on Neural Information Processing Systems.Cambridge,MA:MIT Press,2014:1988-1996.
[7] Ben Xianye,Meng Weixiao,Yan Rui,et al. An improved biometrics technique based on metric learning approach[J]. Neurocomputing,2012,97(1):44-51.
[8] Zhu Zhenyao,Luo Ping,Wang Xiaogang,et al. Deep learning identitypreserving face space[C]//Proc of IEEE International Conference on Computer Vision. Piscataway,NJ:IEEE Press,2013:113-120.
[9] Sun Yi,Wang Xiaogang,Tang Xiao’ou. Hybrid deep learning for face verification[C]//Proc of IEEE International Conference on Computer Vision. Piscataway,NJ:IEEE Press,2014:1489-1496.
[10]Chen Dong,Cao Xudong,Wang Liwei,et al. Bayesian face revisited:a joint formulation[C]//Proc of European Conference on Computer Vision. Berlin:Springer-Verlag,2012:566-579.
[11]Kim S J,Magnani A,Boyd S. Optimal kernel selection in kernel fisher discriminant analysis[C]//Proc of International Conference on Machine Learning. New York:ACM Press,2006:465-472.
[12]Chen Dong,Cao Xudong,Wen Fang,et al. Blessing of dimensionality:high-dimensional feature and its efficient compression for face verification[C]//Proc of IEEE Conference on Computer Vision and Pattern Recognition. Washington DC:IEEE Computer Society,2013:3025-3032.
[13] Sagonas C,Tzimiropoulos G,Zafeiriou S,et al. 300 faces in-the-wild challenge:the first facial landmark localization challenge[C]//Proc of IEEE International Conference on Computer Vision Workshops. Washington DC:IEEE Computer Society,2013:397-403.
[14]Jones M J,Viola P. Robust real-time object detection[J]. International Journal of Computer Vision,2001,57(2):137-154.
[15]Zhu Zhenyao,Luo Ping,Wang Xiaogang,et al. Deep learning identitypreserving face space[C]//Proc of IEEE International Conference on Computer Vision. Piscataway,NJ:IEEE Press,2013:113-120.
[16]Wright J,Hua Gang. Implicit elastic matching with random projections for pose-variant face recognition[C]//Proc of IEEE Conference on Computer Vision and Pattern Recognition. Piscataway,NJ:IEEE Press,2009:1502-1509.
[17]Wilson A G,Hu Zhiting,Salakhutdinov R,et al. Deep kernel learning[EB/OL].(2015-11-09). https://arxiv. org/abs/1511. 02222.
[18] Wilson A G. Covariance kernels for fast automatic pattern discovery and extrapolation with Gaussian processes[C]//Proc of the 30 th International Conference on Machine Learning. Piscataway,NJ:IEEE Press,2014.
[19]Schroff F,Kalenichenko D,Philbin J. Face Net:a unified embedding for face recognition and clustering[C]//Proc of IEEE Conference on Computer Vision and Pattern Recognition. Washington DC:IEEE Computer Society,2015:815-823.
[20] Amos B,Ludwiczuk B,Satyanarayanan M. Openface:a general-purpose face recognition library with mobile applications[EB/OL].(2016-06-13). https://hgpu. org/? p=16213.
[21]Taigman Y,Yang Ming,Ranzato M,et al. Deep Face:closing the gap to human-level performance in face verification[C]//Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Piscatway,NJ:IEEE Press,2014:1701-1708.
[22] Ng H W,Winkler S. A data-driven approach to cleaning large face datasets[C]//Proc of IEEE International Conference on Image Processing. Piscatway,NJ:IEEE Press,2015:343-347.