Practical age estimation using deep label distribution learning

Abstract

Age estimation plays an important role in humancomputer interaction system. The lack of large number of facial images with definite age label makes age estimation algorithms inefficient. Deep label distribution learning (DLDL) which employs convolutional neural networks (CNN) and label distribution learning to learn ambiguity from ground-truth age and adjacent ages, has been proven to outperform current state-of-the-art framework. However, DLDL assumes a rough label distribution which covers all ages for any given age label. In this paper, a more practical label distribution paradigm is proposed: we limit age label distribution that only covers a reasonable number of neighboring ages. In addition, we explore different label distributions to improve the performance of the proposed learning model. We employ CNN and the improved label distribution learning to estimate age. Experimental results show that compared to the DLDL, our method is more effective for facial age recognition.

Keywords

deep learning / convolutional neural networks / label distribution learning / facial age estimation

References

[1] Geng X, Yin C, Zhou Z H. Facial age estimation by learning from label distributions. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(10): 2401–2412

[2] Geng X. Label distribution learning. IEEE Transactions on Knowledge and Data Engineering, 2014, 28(7): 1734–1748

[3] Gao B B, Xing C, Xie C W, Wu J, Geng X. Deep label distribution learning with label ambiguity. IEEE Transactions on Image Processing, 2017, 26(6): 2825–2838

[4] Geng X, Wang Q, Xia Y. Facial age estimation by adaptive label distribution learning. In: Proceeding of the 22nd International Conference on Pattern Recognition. 2014, 4465–4470

[5] Ling M G, Geng X. Soft video parsing by label distribution learning. Frontiers of Computer Science, 2019, 13(2): 302–317

[6] Li Y F, Liang D M. Safe semi-supervised learning: a brief introduction. Frontiers of Computer Science, 2019, 13(4): 669–676

[7] Liu X Y, Wang S T, Zhang M L. Transfer synthetic over-sampling for class-imbalance learning with limited minority class data. Frontiers of Computer Science, 2019, 13(5): 996–1009

[8] Zhao R, Niu X, Wu Y, Luk W, Liu Q. Optimizing CNN-based object detection algorithms on embedded FPGA platforms. In: Proceedings of the 13th International Symposium on Applied Reconfigurable Computing. 2017, 255–267

[9] He Z, Kan M, Zhang J, Chen X, Shan S. A fully end-to-end cascaded CNN for facial landmark detection. In: Proceeding of the 12th IEEE International Conference on Automatic Face and Gesture Recognition. 2017, 200–207

[10] Marmanis D, Wegner J D, Galliani S, Schindler K, Datu M, Stilla U. Semantic segmentation of aerial images with an ensemble of CNNs. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2016, 3(3): 273–480

[11] Ranjan R, Patel VM, Chellappa R. HyperFace: a deep multi-task learning framework for face detection, landmark localization, pose estimation, and gender recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 41(1): 121–135

[12] Graves A, Jaitly N, Mohamed A R. Hybrid speech recognition with deep bidirectional LSTM. IEEE Automatic Speech Recognition and Understanding, 2014, 1(3): 273–278

[13] Fan Y, Lu X J, Li D, Liu Y L. Video-based emotion recognition using CNN-RNN and C3D hybrid networks. In: Proceedings of the 18th ACM International Conference on Multimodal Interaction. 2016, 445–450

[14] Chen Y, Yang X, Zhong B, Pan S, Chen D, Zhang H. CNN tracker: online discriminative object tracking via deep convolutional neural network. Applied Soft Computing, 2016, 2(38): 1088–1098

[15] Guo G, Mu G. Simultaneous dimensionality reduction and human age estimation via kernel partial least squares regression. In: Proceedings of the 24th IEEE Conference on Computer Vision and Pattern Recognition. 2011, 657–644

[16] Guo G, Mu G. Joint estimation of age, gender and ethnicity: CCA vs. PLS. In: Proceedings of the 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition. 2013, 1–6

[17] Horng W B. Classification of age groups based on facial features. Tamkang Journal of Science and Engineering, 2001, 4(3): 183–192

[18] Othman Z A, Adnan D A. Age classification from facial images system. International Journal of Computer Science and Mobile Computing, 2014, 3(10): 291–303

[19] Kwon Y H, Vitoria Lobo N D. Age classification from facial images. Computer Vision and Image Understanding, 1999, 74(1): 1–21

[20] Cootes T F, Edwards G J, Taylor C J. Active appearance models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(6): 681–685

[21] Fu Y, Huang T S. Human age estimation with regression on discriminative aging manifold. IEEE Transactions on Multimedia, 2008, 10(4): 578–584

[22] Geng X, Zhou Z H, Smithmiles K. Automatic age estimation based on facial aging patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(12): 2234–2240

[23] Hardoon D R, Szedmak S, Shawe-Taylor J. Canonical correlation analysis: an overview with application to learning methods. Neural Computation, 2004, 16(12): 2639–2664

[24] Geladi P, Kowalski B R. Partial least-squares regression: a tutorial. Analytica Chimica Acta, 1986, 185(1): 1–17

[25] Basak D, Srimanta P, Patranabis D C. Support vector regression. Neural Information Processing-letter and Reviews, 2007, 11(10): 203–224

[26] Yi D, Lei Z, Li S Z. Age estimation by multi-scale convolutional network. In: Proceedings of the 12th Asian Conference on Computer Vision. 2014, 144–158

[27] Chen S, Zhang C, Dong M. Deep age estimation: from classification to ranking. IEEE Transactions on Multimedia, 2017, 20(8): 2209–2222

[28] Hu Z Z, Wen Y G. Facial age estimation with age difference. IEEE Transactions on Image Processing, 2017, 26(7): 3087–3097

[29] Duan M, Li K, Lia K. An ensemble CNN2ELM for age estimation. IEEE Transactions on Information Forensics and Security, 2017, 99(1): 1–12

[30] Geng X, Yin C, Zhou Z H. Facial age estimation by learning from label distributions. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(10): 2401–2412

[31] Ricanek J K, Tesafaye T. Morph: a longitudinal image database of normal adult age-progression. In: Proceedings the 7th International Conference on Automatic Face and Gesture Recognition. 2006, 341–345

[32] Mathias M, Benenson R, Pedersoli M, Van Gool L. Face detection without bells and whistles. In: Proceedings of European Conference on Computer Vision. 2014, 720–735

RIGHTS & PERMISSIONS

2020 Higher Education Press