计算机科学 ›› 2016, Vol. 43 ›› Issue (6): 303-307.doi: 10.11896/j.issn.1002-137X.2016.06.060
朱陶,任海军,洪卫军
ZHU Tao, REN Hai-jun and HONG Wei-jun
摘要: 当前基于深度卷积神经网络的人脸表示学习方法需要利用海量的有标注的人脸数据。在实际应用中,精确标注人脸的身份非常困难。因此,提出了一种基于前向无监督卷积神经网络的人脸表示学习方法。其中,基于K-means聚类获取训练样本虚拟标签,再利用线性判别分析进行卷积核学习。提出的网络结构简单有效,训练阶段不需要反向传递,训练速度显著优于有监督的深度卷积神经网络。实验结果表明,提出的方法在真实条件下的人脸数据集LFW和经典的Feret数据集上取得了优于当前主流的无监督特征学习方法和局部特征描述子的性能。
[1] Zhao W,Chellappa R,Phillips P J,et al.Face recognition:A li-terature survey[J].ACM Computer Surveys (CSUR),2003,35(4):399-458 [2] Turk M,Pentland A.Eigenfaces for recognition[J].Journal of cognitive neuroscience,1991,3(1):71-86 [3] Belhumeur P N,Hespanha J P.Eigenfaces vs.fisherfaces:Re-cognition using class specific linear projection[J].IEEE Tran-sactions on Pattern Analysis and Machine Intelligence,1997,19(7):711-720 [4] Liu C,Wechsler H.Gabor feature based classification using the enhanced fisher linear discriminant model for face[J].IEEE Transactions on Image Processing,2002,11(4):467-476 [5] Ahonen T,Hadid A,Pietikainen M.Face Description with Local Binary Patterns:Application to Face Recogniton[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(12):2037-2041 [6] Vu N S,Caplier A.Enhanced patterns of oriented edge magnitudes for face revognition and image matching[J].IEEE Tran-sactions on Image Processing,2011,21(3):1352-1365 [7] M Bicego,A Lagorio,E Grosso,et al.On the use of SIFT features for face authentication[C]∥Computer Vision and Pattern Recognition Workshop,2006(CVPRW’06).2006:35 [8] Chan T H,Jia K,Gao S,et al.PCANet:A Simple Deep Learning Baseline for Image Classification?[J].IEEE Transactions on Image Processing,2014,4(12):1 [9] Coates A,Ng A Y.Learning Feature Representation Using K-means[M].Springer Berlin Heidelberg,2012 [10] Hartigan J A,Wong M A.Algorithm AS 136:A K-means clustering algorithm[J].Applied Statistics,1979,28(1):100-108 [11] Cui Z,Li W,Xu D,et al.Fusing Robust Face Region Descriptors via Multiple Metric Learning for Face Recognition in the Wild[C]∥Proc.of the 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Portland,OR:IEEE,2013:3554-3561 [12] Huang G B,Mattar M,Berg T,et al.Labeled faces in the wild:A database for studying face recognition in unconstrained environments[C]∥Proc.of the Workshop on Faces in ‘Real-Life’ Images:Detection,Alignment,and Recognition.Marseille,France:Springer Berlin Heidelberg,2008:864-877 [13] Sun Y,Chen Y,Wang X,et al.Deep learning face representation by joint identification-verification[C]∥Proc.of the Advances in Neural Information Processing Systems.2014:1988-1996 [14] Krizhevsky A,Sutskever I,Hinton G E.Imagenet classification with deep convolutional neural networks[C]∥Proc.of the Advances in Neural Information Processing Systems.2012:1097-1105 [15] Taigman Y,Yang M,Ranzato M A,et al.Deepface:Closing the gap to human-level performance in face verification[C]∥Proc.of the 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Columbus,OH:IEEE,2014:1701-1708 [16] Sun Y,Chen Y,Wang X,et al.Deep learning face representation by joint identification-verification[C]∥Proc.of the Advances in Neural Information Processing Systems.2014:1988-1996 [17] Phillips P J,Moon H,Rauss P J,et al.The FERET evaluation methodology for face recognition algorithms[C]∥ IEEE Computer Society Conference on Computer Vision and Pattern Re-cognition.1997:137-143 [18] Tan X,Triggs B.Enhanced local texture feature sets for face recognition under difficult lighting conditions[J].IEEE TIP,2010,19(6):1635-1650 [19] Vu N S,Caplier A.Enhanced patterns of oriented edge magnitudes for face recognition and image matching[J].IEEE TIP,2012,21(3):1352-1368 [20] Xie P,Wu X J.Modular Multilinear Principal Component Analysis and Application in Face Recognition[J].Computer Science,2015,42(3):274-279(in Chinese) 谢佩,吴小俊.分块多线性主成分分析及其在人脸识别中的应用研究[J].计算机科学,2015,42(3):274-279 [21] Tian Hua,Pu Tian-yin.Improved ASM localization method for human facial features[J].Journal of Chongqing Unversity Posts and Telecommunications(Natural Science Edition),2014,6(1):124-130(in Chinese) 田华,蒲天银.一种改进的ASM人脸特征点定位方法[J].重庆邮电大学学报(自然科学版),2014,6(1):124-130 |
No related articles found! |
|