基于深度代价敏感CNN的年龄估计算法

doi:10.16451/j.cnki.issn1003-6059.202002010

Abstract
Figure/Table
References
Related Citation (3)

Download: PDF (695 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Aiming at the problems of the imbalance of sample size in age estimation and the cost of misclassification between different classes, the cost sensitivity is embedded into the deep learning framework, and an age estimation algorithm based on deep cost sensitive convolutional neural networks (CNN) is proposed. Firstly, a loss function is established for each age category to solve the imbalance problem of the training samples. Then, a cost vector is defined to reflect the cost difference caused by misclassification between different classes, and an inverse cross entropy error function is constructed. Finally, the above methods are merged to derive a loss function for CNN to learn the robust face representation for age estimation during the training process. Experiments on different age estimation standard image sets verify the effectiveness of the proposed algorithm.

Key words： Age Estimation Cost Sensitivity Convolutional Neural Networks (CNN) Loss Function

Received: 22 July 2019

ZTFLH:

TP 391.41

Fund:Supported by National Natural Science Foundation of China(No.61571361,61102095),General Program of International Cooperation and Exchange Foundation of Shaanxi Province(No.2017KW-013,2019JM-604)

Corresponding Authors: LI Daxiang, Ph.D., associate professor. His research interests include image retrieval and image classification.

About author:: MA Xuan, master student. His research interests include facial age estimation; REN Yaqiong, master student. Her research interests include machine learning; LIU Ying, Ph.D., professor. Her research interests include image retrieval and image classification.

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	LI Daxiang
	MA Xuan
	REN Yaqiong
	LIU Ying

Cite this article:

LI Daxiang,MA Xuan,REN Yaqiong等. Age Estimation Algorithm Based on Deep Cost Sensitive CNN[J]. , 2020, 33(2): 176-181.

URL:

http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.202002010 OR http://manu46.magtech.com.cn/Jweb_prai/EN/Y2020/V33/I2/176

[1] 吴嘉琪,景丽萍.基于集成人脸对距离学习的跨年龄人脸验证.模式识别与人工智能, 2017, 30(12): 1114-1120.
(WU J Q, JIN L P. Ensemble Face Pairs Distance Metric Learning for Cross-Age Face Verification. Pattern Recognition and Artificial Intelligence, 2017, 30(12): 1114-1120.)
[2] 张珂,王新胜,郭玉荣,等.人脸年龄估计的深度学习方法综述.中国图象图形学报, 2019, 24(8): 1215-1230.
(ZHANG K, WANG X S, GUO Y R, et al. Survey of Deep Lear-ning Methods for Face Age Estimation. Journal of Image and Gra-phics, 2019, 24(8): 1215-1230.)
[3] COOTES T F, EDWARDS G J, TAYLOR C J. Active Appearance Models // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 1998: 484-498.
[4] LANITIS A, DRAGANOVA C, CHRISTODOULOU C. Comparing Different Classifiers for Automatic Age Estimation. IEEE Transactions on Systems, Man, and Cybernetics(Cybernetics), 2004, 34(1): 621-628.
[5] GENG X, ZHOU Z H, ZHANG Y, et al. Learning from Facial Aging Patterns for Automatic Age Estimation // Proc of the 14th ACM International Conference on Multimedia. New York, USA: ACM, 2006: 307-316.
[6] LU J W, LIONG V E, ZHOU J. Cost Sensitive Local Binary Feature Learning for Facial Age Estimation. IEEE Transactions on Image Processing, 2015, 24(12): 5356-5368.
[7] FU Y, XU Y, HUANG T S. Estimating Human Age by Manifold Analysis of Face Pictures and Regression on Aging Features // Proc of the IEEE International Conference on Multimedia and Exposition. Washington, USA: IEEE, 2007: 1383-1386.
[8] NG C C, CHENG Y T, HSU G S, et al. Multi-layer Age Regression for Face Age Estimation // Proc of the 15th IAPR International Conference on Machine Vision Applications. Washington, USA: IEEE, 2017: 294-297.
[9] GUO G D, MU G W, FU Y, et al. Human Age Estimation Using Bio-inspired Features // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2009: 112-119.
[10] FU Y, HUANG T S. Human Age Estimation with Regression on Discriminative Aging Manifold. IEEE Transactions on Multimedia, 2008, 10(6): 578-584.
[11] GUO G D, FU Y, HUANG T S, et al. Locally Adjusted Robust Regression for Human Age Estimation // Proc of the IEEE Workshop on Applications of Computer Vision. Washington, USA: IEEE, 2008. DOI: 10.1109/WACV.2008.4544009.
[12] WANG X K, GUO R, KAMBHAMETTU C. Deeply-Learned Feature for Age Estimation // Proc of the IEEE Winter Conference on Applications of Computer Vision. Washington, USA: IEEE, 2015: 534-541.
[13] NIU Z X, ZHOU M, WANG L, et al. Ordinal Regression with Multiple Output CNN for Age Estimation // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2016: 4920-4928.
[14] GAO B B, XING C, XIE C W, et al. Deep Label Distribution Learning with Label Ambiguity. IEEE Transactions on Image Processing, 2017, 26(6): 2825-2838.
[15] ROTHE R, TIMOFTE R, VAN GOOL L. DEX: Deep Expectation of Apparent Age from a Single Image // Proc of the IEEE International Conference on Computer Vision Workshop. Washington, USA: IEEE, 2015: 252-257.
[16] YI D, LEI Z, LI S Z. Age Estimation by Multi-scale Convolutional Network // Proc of the Asian Conference on Computer Vision. Berlin, Germany: Springer, 2014: 144-158.
[17] CHEN S X, ZHANG C J, DONG M, et al.Using Ranking CNN for Age Estimation // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2017: 742-751.
[18] VIOLA P, JONES M. Rapid Object Detection Using a Boosted Cascade of Simple Features // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2001: 511-518.
[19] HE K M, ZHANG X Y, REN S Q, et al. Deep Residual Learning for Image Recognition // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2006: 770-778.
[20] HU J, SHEN L, ALBANIE S, et al. Squeeze-and-Excitation Networks // Proc of the IEEE Conference on Computer Vision and Pa-ttern Recognition. Washington, USA: IEEE, 2017: 7132-7141.
[21] RAWLS A W, JR RICANEK K. MORPH: Development and Optimization of a Longitudinal Age Progression Database // Proc of the European Workshop on Biometrics and Identity Management. Berlin, Germany: Springer, 2009: 17-24.
[22] JIA Y Q, SHELHAMER E, DONAHUE J, et al. Caffe: Convolutional Architecture for Fast Feature Embedding // Proc of the 22nd ACM International Conference on Multimedia. New York, USA: ACM, 2014: 675-678.
[23] CAO Q, SHEN W, XIE W D, et al. VGGFace2: A Dataset for Recognizing Faces across Pose and Age // Proc of the IEEE Conference on Automatic Face and Gesture Recognition. Washington, USA: IEEE, 2018: 49-57.
[24] CHANG K Y, CHEN C S, HUNG Y P. Ordinal Hyperplanes Ranker with Cost Sensitivities for Age Estimation // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2011: 585-592.
[25] LI L, LIN H T. Ordinal Regression by Extended Binary Classification // SCHÖLKOPF B, PLATT J C, HOFMANN T, eds. Advances in Neural Information Processing Systems 19. Cambridge, USA: The MIT Press, 2007: 865-872.