| 4,334 | 153 | 39 |
| 下载次数 | 被引频次 | 阅读次数 |
研究并实现了一种基于卷积神经网络的人脸识别方法.该网络由2个卷积层、2个池化层、1个全连接层和1个Softmax回归层组成,它能自动提取人脸特征并进行分类.网络通过批量梯度下降法训练特征提取器和分类器,各隐层应用"dropout"方法解决了过拟合问题.应用于ORL和AR人脸数据库的人脸识别率分别达到99.50%和99.62%,识别单张人脸的时间均小于0.05s,而且对光照差异、面部表情变化、有无遮挡物等干扰具有鲁棒性.
Abstract：Feature extraction and classification are two key steps in face recognition.A convolutional neural network composed of two convolutional layers,two pooling layers,one full-connection layer and one Softmax regression layer for face recognition is proposed.The neural network can automatically extract facial features and classify face,with trained feature extractors and the classifier using batch gradient descent.And the network adopts dropout method in hidden layers to avoid the overfitting problem.Experimental results show that proposed network achieves 99.50% recognition accuracy on ORL database and an accuracy of 99.62% on AR database,and it can complete one-time facial recognition in less than 0.05 s.More importantly,the network is robust to illumination variances,facial expressions and occlusions.
[1]陈海霞,崔茜.基于Gabor小波和PCA的人脸识别[J].东北师大学报(自然科学版),2014,46(4):77-80.
[2]孟繁静,王连明.视频人脸识别系统中的最佳人脸捕获[J].东北师大学报(自然科学版),2015,47(3):90-95.
[3]WANG X,TANG X.Dual-space linear discriminant analysis for face recogmtion[C]//CVPR 2004 Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Washington:IEEE,2004,2:564-569.
[4]HEISELE B,HO P,POGGIO T.Face recognition with support vector machines:Global versus component-based approach[C]//ICCV 2001 Proceedings.Eighth IEEE International Conference on Computer Vision.Los Alamitos:IEEE,2001,2:688-694.
[5]ABATE A F,NAPPI M,RICCIO D,et al.2D and 3D face recognition a survey[J].Pattern Recognition Letters,2007,28(14):1885-1906.
[6]NEFIAN A V,HAYES III M H.Hidden markov models for face recogmtion[C]//1998 IEEE International Conference on Acoustics,Speed and Signal Processing,Washington;IEEE,1998:2721-2724.
[7]AHRANJANY S S,RAZZAZI F,GHASSEMIAN M H.A very high accuracy handwritten character recognition system for Farsi/Arabic digits using Convolutional Neural Networks[C]//Theories and Applications(BIC-TA):2010 IEEE Fifth International Conference on Bio-Inspired Computing.Beijing:IEEE,2010:1585-1592.
[8]SYAFEEZA A R,KHALIL-HANI M,LIEW S S,et al.Convolutional neural network for face recognition with pose and Illumination Variation[J].International Journal of Engineering&Technology,2014,6(1):44-57.
[9]TOSHEV A,SZEGEDY C.Deeppose:Human pose estimation via deep neural networks[C]//2014 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Los Alamitos;IEEE,2014:1653-1660.
[10]SERMANET P,EIGEN D,ZHANG X,et al.Overfeat integrated recognition,localization and detection using convolutional networks[J].Neural Networks,2003,16(5):555-559.
[11]LECUN Y,BOTTOU L,BENGIO Y,et al.Gradient-based learning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
[12]HUANG V S,SHADMEHR R,DIEDRICHSEN J.Active learning,learning a motor skill without a coach[J].Journal of neurophysiology,2008,100(2):879-887.
[13]SRIVASTAVA S,HINTION G,KRIZHEVSKY A,et al.Droput:a simple way to prevent neural networks from overfilling[J].The Journal of Machine Learning Reserch,2014,15(1):1929-1958.
[14]YANG M H.Kernel eigenfaces vs.kernel fisherfaces;Face recognition using kernel methods[C]//2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition(FG).Washington;IEEE,2002:0215-0215.
[15]YANG J,ZHANG D,FRANGI A F,et al.Two-dimensional PCA:a new approach to appearance-based face representation and recognition[J].Pattern Analysis and Machine Intelligence,IEEE Transactions on,2004,26(1):131-137.
[16]ROLI F,MARCIALIS G L.Semi-supervised PCA-based face recognition using self-training[M].Structural,Syntactic,and Statistical Pattern Recognition.Berlin Heidelberg:Springer,2006:560-568.
[17]YANG M,ZHANG L.Gabor feature based sparse representation for face recognition with gabor occlusion dictionary[M].Computer Vision-ECCV 2010.Berlin Heidelberg:Springer,2010:448-461.
[18]JIANG Z,LIN Z,DAVIS L S.Learning a discriminative dictionary for sparse coding via label consistent K-SVD[C]//2011IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Washington;IEEE,2011:1697-1704.
基本信息:
DOI：10.16163/j.cnki.22-1123/n.2016.02.016
中图分类号:TP391.41;TP183
引用信息:
[1]陈耀丹,王连明.基于卷积神经网络的人脸识别方法[J].东北师大学报(自然科学版),2016,48(02):70-76.DOI:10.16163/j.cnki.22-1123/n.2016.02.016.
基金信息:
国家自然科学基金资助项目(21227008);; 吉林省科技发展计划项目(20130102028JC)
2016-06-20
2016-06-20