Abstract：Concerning low accuracy of age classification of face images under unrestricted conditions, a new method of face age classification under unconstrained conditions based on deep Residual Networks (ResNets) and large dataset pre-training was proposed. Firstly, the deep residual networks were used as the basis convolutional neural network model to deal with the problem of face age classification. Secondly, the deep residual networks were trained on the ImageNet dataset to learn the expression of basic image features. Thirdly, the large-scale face age images IMDB-WIKI was cleaned, and the IMDB-WIKI-8 dataset was established for fine-tuning the deep residual networks, and migration learning from the general object image to face age image was achieved to make the model adapt to the distribution of the age group and improve the network learning capability. Finally, the fine-tuned network model was trained and tested on the unconstrained Adience dataset, and the age classification accuracy was obtained by the cross-validation method. Through the comparison of 34/50/101/152-layer residual networks, it could be seen that the more layers of the network have the higher accuracy of age classification. And the best state-of-the-art age classification result on Adience dataset with the accuracy of 65.01% was achieved by using the 152-layer residual network. The experimental results show that the combination of deeper residual network and large dataset pretraining can effectively improve the accuracy of face age classification.
[1] 王先梅, 梁玲燕, 王志良, 等. 人脸图像的年龄估计技术研究[J]. 中国图象图形学报, 2012, 17(6):603-618.(WANG X M, LIANG L Y, WANG Z L, et al. Age estimation by facial image:a survey[J]. Journal of Image and Graphics, 2012, 17(6):603-618.) [2] EIDINGER E, ENBAR R, HASSNER T. Age and gender estimation of unfiltered faces[J]. IEEE Transactions on Information Forensics & Security, 2014, 9(12):2170-2179. [3] PANIS G, LANITIS A, TSAPATSOULIS N, et al. Overview of research on facial ageing using the FG-NET ageing database[J]. IET Biometrics, 2016, 5(2):37-46. [4] CHEN B C, CHEN C S, HSU W H. Face recognition and retrieval using cross-age reference coding with cross-age celebrity dataset[J]. IEEE Transactions on Multimedia, 2015, 17(6):804-815. [5] GUO G. Human Age Estimation and Sex Classification[M]. Berlin:Springer, 2012:101-131. [6] HAN H, OTTO C, JAIN A K. Age estimation from face images:human vs. machine performance[C]//Proceedings of the 2013 International Conference on Biometrics. Piscataway, NJ:IEEE, 2013:1-8. [7] 王俊艳, 苏光大, 林行刚. 人脸图像年龄估计[J]. 清华大学学报(自然科学版), 2007, 47(4):526-529.(WANG J Y, SU G D, LIN X G. Face age image estimation[J]. Journal of Tsinghua University (Science and Technology), 2007, 47(4):526-529.) [8] 林时苗, 毛晓蛟, 杨育彬. 基于人脸图像的年龄估计[J]. 计算机科学, 2015, 42(6):32-36.(LIN S M, MAO X J, YANG Y B. Age estimation based on facial image[J]. Computer Science, 2015, 42(6):32-36.) [9] KWON Y H. Age classification from facial images[C]//Proceedings of the 1994 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 1994:762-767. [10] HAYASHI J, YASUMOTO M, ITO H, et al. Age and gender estimation based on wrinkle texture and color of facial images[C]//Proceedings of the 16th International Conference on Pattern Recognition. Piscataway, NJ:IEEE, 2002:405-408. [11] NAKANO M, YASUKATA F, FUKUMI M. Age classification from face images focusing on edge information[C]//Proceedings of the 8th International Conference on Knowledge-Based and Intelligent Information and Engineering Systems. Berlin:Springer, 2004:898-904. [12] LANITIS A, DRAGANOVA C, CHRISTODOULOU C. Comparing different classifiers for automatic age estimation[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2004, 34(1):621-628. [13] COOTES T F, EDWARDS G J, TAYLOR C J. Active appearance models[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(6):681-685. [14] LANITIS A. Comparative evaluation of automatic age-progression methodologies[J]. Journal on Advances in Signal Processing, 2008, 2008(1):Article No. 101. [15] GUO G, MU G, FU Y, et al. A study on automatic age estimation using a large database[C]//Proceedings of the 2009 IEEE 12th International Conference on Computer Vision. Piscataway, NJ:IEEE, 2009:1986-1991. [16] CHOI S E, LEE Y J, LEE S J, et al. Age estimation using a hierarchical classifier based on global and local facial features[J]. Pattern Recognition, 2011, 44(6):1262-1281. [17] GUNAY A, NABIYEV V V. Automatic age classification with LBP[C]//Proceedings of the 23rd International Symposium on Computer and Information Sciences. Piscataway, NJ:IEEE, 2008:1-4. [18] LEVI G, HASSNCER T. Age and gender classification using convolutional neural networks[C]//Proceedings of the 2015 Computer Vision and Pattern Recognition Workshops. Piscataway, NJ:IEEE, 2015:34-42. [19] HOU L, SAMARAS D, KURC T M, et al. Neural networks with smooth adaptive activation functions for regression[DB/OL].[2016-11-16]. https://arxiv.org/abs/1608.06557. [20] EKMEKJI A. Convolutional neural networks for age and gender classification[EB/OL].[2016-11-28]. http://cs231n.stanford.edu/reports/2016/pdfs/003_Report.pdf. [21] ROTHE R, TIMOFTE R, VAN GOOL L. Deep expectation of real and apparent age from a single image without facial landmarks[EB/OL].[2017-05-10].http://homes.esat.kuleuven.be/~konijn/publications/2016/DEEP-EXP.pdf. [22] HOU L, YU C P, SAMARAS D. Squared earth mover's distance-based loss for training deep neural networks[EB/OL].[2017-05-10].https://arxiv.org/pdf/1611.05916.pdf. [23] DEHGHAN A, ORTIZ E G, SHU G, et al. DAGER:Deep age, gender and emotion recognition using convolutional neural network[EB/OL].[2017-03-16].https://arxiv.org/pdf/1702.04280.pdf. [24] 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. [25] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[C]//Proceedings of the 25th International Conference on Neural Information Processing Systems. Lake Tahoe, Nevada:Curran Associates Inc., 2012:1097-1105. [26] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[EB/OL].[2016-12-21]. https://arxiv.org/abs/1409.1556. [27] SZEGEDY C, LIU W, JIA Y, et al. Going deeper with convolutions[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2015:1-9. [28] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2016:770-778. [29] CUBBEE, GROSS S. ResNet models trained on ImageNet[EB/OL].[2016-12-10]. https://github.com/facebook/fb.resnet.torch/tree/master/pretrained.
2017, Vol. 37 
