单样本的低分辨率单目标人脸识别算法
|
摘要
针对只给定单幅目标图像的情况下,而要在监控视频中查找出该目标人脸图像的问题,提出了一种单样本的低分辨率单目标人脸识别算法。考虑到待识别样本集中的目标与非目标对象数量严重不均衡,以及单目标问题无法利用不同类别间的互斥关系。首先在待识别样本集中,通过聚类算法,将单目标的识别问题转化为多目标识别问题,进而提高开集人脸识别算法的鲁棒性;其次,利用迭代标签传播算法不断优化待识别样本的归属类别;在迭代过程中,按照置信概率估计每个类别的人脸确认阈值,以解决单样本无法训练分类器的问题。在多个人脸数据集上的实验结果表明,该算法对于单目标的单样本的人脸识别精确率既能逼近100%,也具有较高的召回率。
Recognizing the target face from the surveillance video using the given single-target image is still a challenging issue in practical applications. Therefore, a low-resolution single-target face recognition algorithm with single-sample is proposed in this work. Two significant limitations are taken into consideration, the sample numbers of the target objects and non-target objects are seriously unbalanced in the probe set, and the single object problem cannot utilize the mutually exclusive relationship between different categories. In this paper, firstly, to increase the robustness of the open-face face recognition, the clustering algorithm is utilized to transform the single object recognition problem into a multi classification recognition problem. Furthermore, the iterative label propagation algorithm is applied to optimize the attribution probability of the probe sample continuously. During the iteration, the face recognition threshold of each object is estimated according to the confidence probability. Hence, the single sample is capable to train the classifier. Finally, experimental results on multiple face datasets show that the proposed algorithm can achieve good performances in both accuracy and recall rate.
Recognizing the target face from the surveillance video using the given single-target image is still a challenging issue in practical applications. Therefore, a low-resolution single-target face recognition algorithm with single-sample is proposed in this work. Two significant limitations are taken into consideration, the sample numbers of the target objects and non-target objects are seriously unbalanced in the probe set, and the single object problem cannot utilize the mutually exclusive relationship between different categories. In this paper, firstly, to increase the robustness of the open-face face recognition, the clustering algorithm is utilized to transform the single object recognition problem into a multi classification recognition problem. Furthermore, the iterative label propagation algorithm is applied to optimize the attribution probability of the probe sample continuously. During the iteration, the face recognition threshold of each object is estimated according to the confidence probability. Hence, the single sample is capable to train the classifier. Finally, experimental results on multiple face datasets show that the proposed algorithm can achieve good performances in both accuracy and recall rate.
引文
[1] GAO Q,ZHANG L,ZHANG D.Face recognition using FLDA with single training image per person[J].Applied Mathematics and Computation,2008,205(2):726-734.
[2] DENG W,HU J,WU Z,et al.From one to many:Pose-aware metric learning for single-sample face recognition[J].Pattern Recognition,2018(77):426- 437.
[3] HU C,YE M,JI S,et al.A new face recognition method based on image decomposition for single sample per person problem[J].Neurocomputing,2015(160):287- 299.
[4] LU J,TAN Y P,WANG G.Discriminative multimanifold analysis for face recognition from a single training sample per person[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(1):39- 51.
[5] YAN H,LU J,ZHOU X,et al.Multi-feature multi-manifold learning for single-sample face recognition[J].Neurocomputing,2014(143):134-143.
[6] ZHANG P,YOU X,OU W,et al.Sparse discriminative multi-manifold embedding for one-sample face identification[J].Pattern Recognition,2016(52):249- 259.
[7] CHEN S,LIU J,ZHOU Z H.Making FLDA applicable to face recognition with one sample per person[J].Pattern Recognition,2004,37(7):1553-1555.
[8] WRIGHT J,YANG A Y,GANESH A,et al.Robust face recognition via sparse representation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(2):210- 227.
[9] DENG W,HU J,GUO J.Extended SRC:Undersampled face recognition via intraclass variant dictionary[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(9):1864-1870.
[10] ZHU P,YANG M,ZHANG L,et al.Local generic representation for face recognition with single sample per person[C].Proceedings of the Asian Conference on Computer Vision,2014:34- 50.
[11] DING R X,DU D K,HUANG Z H,et al.Variational feature representation-based classification for face recognition with single sample per person[J].Journal of Visual Communication and Image Representation,2015(30):35- 45.
[12] 史静,朱虹,邢楠,等.一种多尺度时频纹理特征融合的场景分类算法[J].仪器仪表学报,2016,37(10):2333- 2339.SHI J,ZHU H,XING N,et al.Multi-scale time-frequency texture feature fusion algorithm for scene classification[J].Chinese Journal of Scientific Instrument,2016,37(10):2333- 2339.
[13] 赵光权,刘小勇,姜泽东,等.基于深度学习的轴承健康因子无监督构建方法[J].仪器仪表学报,2018,39(6):82- 88.ZHAO G Q,LIU X Y,JIANG Z D,et al.Unsupervised health indicator of bearing based on deep learning[J].Chinese Journal of Scientific Instrument,2018,39(6):82- 88.
[14] 刘涵,郭润元.基于X射线图像和卷积神经网络的石油钢管焊缝缺陷检测与识别[J].仪器仪表学报,2018,39(4):247- 256.LIU H,GUO R Y.Detection and identification of SAWH pipe weld defects based on X-ray image and CNN[J].Chinese Journal of Scientific Instrument,2018,39(4):247- 256.
[15] SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[J].Computer Science,2014,arXiv:1409.1556.
[16] PARKHI O M,VEDALDI A,ZISSERMAN A.Deep face recognition[C].Proceedings of the British Machine Vision Conference,2015:1- 12.
[17] 薛杉,朱虹,王婧,史静.低分辨率人脸图像的迭代标签传播识别算法[J].模式识别与人工智能,2018,31(7):602- 611.XUE SH,ZHU H,WANG J,et al.Low-resolution face recognition based on recursive label propagation algorithm[J].Pattern Recognition and Artificial Intelligence,2018,31(7):602- 611.
[18] ZHOU K,MARTIN A,PAN Q,et al.SELP:Semi-supervised evidential label propagation algorithm for graph data clustering[C].International Journal of Approximate Reasoning,2018:139-154.
[19] KAMGAR-PARSI B,LAWSON W,KAMGAR-PARSI B.Toward development of a face recognition system for watchlist surveillance[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(10):1925-1937.
[20] SIENA S,BODDETI V N,KUMAR B V K V.Coupled marginal fisher analysis for low-resolution face recognition[C].Proceedings of European Conference on Computer Vision,2012:240- 249.
[21] HOTTA K,KURITA T,MISHIMA T.Scale invariant face detection method using higher-order local autocorrelation features extracted from log-polar image[C].Proceedings of Third IEEE International Conference on Automatic Face and Gesture Recognition,1998:70-75.
[22] LEE S W,PARK J,LEE S W.Low resolution face recognition based on support vector data description[J].Pattern Recognition,2006,39(9):1809-1812.
[23] HUANG Z,WANG R,SHAN S,et al.Face recognition on large-scale video in the wild with hybrid Euclidean-and-Riemannian metric learning[J].Pattern Recognition,2015,48(10):3113-3124.
[2] DENG W,HU J,WU Z,et al.From one to many:Pose-aware metric learning for single-sample face recognition[J].Pattern Recognition,2018(77):426- 437.
[3] HU C,YE M,JI S,et al.A new face recognition method based on image decomposition for single sample per person problem[J].Neurocomputing,2015(160):287- 299.
[4] LU J,TAN Y P,WANG G.Discriminative multimanifold analysis for face recognition from a single training sample per person[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(1):39- 51.
[5] YAN H,LU J,ZHOU X,et al.Multi-feature multi-manifold learning for single-sample face recognition[J].Neurocomputing,2014(143):134-143.
[6] ZHANG P,YOU X,OU W,et al.Sparse discriminative multi-manifold embedding for one-sample face identification[J].Pattern Recognition,2016(52):249- 259.
[7] CHEN S,LIU J,ZHOU Z H.Making FLDA applicable to face recognition with one sample per person[J].Pattern Recognition,2004,37(7):1553-1555.
[8] WRIGHT J,YANG A Y,GANESH A,et al.Robust face recognition via sparse representation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(2):210- 227.
[9] DENG W,HU J,GUO J.Extended SRC:Undersampled face recognition via intraclass variant dictionary[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(9):1864-1870.
[10] ZHU P,YANG M,ZHANG L,et al.Local generic representation for face recognition with single sample per person[C].Proceedings of the Asian Conference on Computer Vision,2014:34- 50.
[11] DING R X,DU D K,HUANG Z H,et al.Variational feature representation-based classification for face recognition with single sample per person[J].Journal of Visual Communication and Image Representation,2015(30):35- 45.
[12] 史静,朱虹,邢楠,等.一种多尺度时频纹理特征融合的场景分类算法[J].仪器仪表学报,2016,37(10):2333- 2339.SHI J,ZHU H,XING N,et al.Multi-scale time-frequency texture feature fusion algorithm for scene classification[J].Chinese Journal of Scientific Instrument,2016,37(10):2333- 2339.
[13] 赵光权,刘小勇,姜泽东,等.基于深度学习的轴承健康因子无监督构建方法[J].仪器仪表学报,2018,39(6):82- 88.ZHAO G Q,LIU X Y,JIANG Z D,et al.Unsupervised health indicator of bearing based on deep learning[J].Chinese Journal of Scientific Instrument,2018,39(6):82- 88.
[14] 刘涵,郭润元.基于X射线图像和卷积神经网络的石油钢管焊缝缺陷检测与识别[J].仪器仪表学报,2018,39(4):247- 256.LIU H,GUO R Y.Detection and identification of SAWH pipe weld defects based on X-ray image and CNN[J].Chinese Journal of Scientific Instrument,2018,39(4):247- 256.
[15] SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[J].Computer Science,2014,arXiv:1409.1556.
[16] PARKHI O M,VEDALDI A,ZISSERMAN A.Deep face recognition[C].Proceedings of the British Machine Vision Conference,2015:1- 12.
[17] 薛杉,朱虹,王婧,史静.低分辨率人脸图像的迭代标签传播识别算法[J].模式识别与人工智能,2018,31(7):602- 611.XUE SH,ZHU H,WANG J,et al.Low-resolution face recognition based on recursive label propagation algorithm[J].Pattern Recognition and Artificial Intelligence,2018,31(7):602- 611.
[18] ZHOU K,MARTIN A,PAN Q,et al.SELP:Semi-supervised evidential label propagation algorithm for graph data clustering[C].International Journal of Approximate Reasoning,2018:139-154.
[19] KAMGAR-PARSI B,LAWSON W,KAMGAR-PARSI B.Toward development of a face recognition system for watchlist surveillance[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(10):1925-1937.
[20] SIENA S,BODDETI V N,KUMAR B V K V.Coupled marginal fisher analysis for low-resolution face recognition[C].Proceedings of European Conference on Computer Vision,2012:240- 249.
[21] HOTTA K,KURITA T,MISHIMA T.Scale invariant face detection method using higher-order local autocorrelation features extracted from log-polar image[C].Proceedings of Third IEEE International Conference on Automatic Face and Gesture Recognition,1998:70-75.
[22] LEE S W,PARK J,LEE S W.Low resolution face recognition based on support vector data description[J].Pattern Recognition,2006,39(9):1809-1812.
[23] HUANG Z,WANG R,SHAN S,et al.Face recognition on large-scale video in the wild with hybrid Euclidean-and-Riemannian metric learning[J].Pattern Recognition,2015,48(10):3113-3124.