Abstract
This paper proposes an age estimation method from the age period using Triplet Network. Age estimation is still an active research topic in machine learning, and it can be formulated as a regression problem. Usually, a specific age value to each of the training face images is assigned as a correct label, and the model to estimate the age value of an unknown face image is trained from the training samples. In this paper, we consider the age estimation problem from the age period in which only the label of each of the training samples is the age period, such as teens or twenties. In this setting, the model has to interpolate the age values from the age period based on the similarity between the samples in the same age period. To achieve this functionality, we use Triplet Network to capture the age relationship between the face images. Then the age of each image is estimated by the linear regression. The effectiveness of the proposed approach is experimentally confirmed by using MegaAge-Asian, UTKFace, and MegaAge.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Sabri, M., Kurita, T.: Facial expression intensity estimation using Siamese and triplet networks. Neurocomputing 313, 143–154 (2018)
Chen, S., Zhang, C., Dong, M., Le, J., Rao, M.: Using ranking-CNN for age estimation. In: CVPR, pp. 742–751 (2017)
Rothe, R., Timofte, R., Gool, L.V.: DEX: Deep expectation of apparent age from a single image. In: ICCVW, December 2015
Pan, H., Han, H., Shan, S., Chen, X.: Mean-variance loss for deep age estimation from a face. In: CVPR, June 2018
Bromley, J., Guyon, I., LeCun, Y., Sickinger, E., Shah, R.: Signature verification using a “Siamese" time delay neural network. Int. J. Pattern Recogn. Artif. Intell. 7(4), 669–688 (1993)
Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: ICML (2010)
Hoffer, E., Ailon, N.: Deep metric learning using triplet network. In: Feragen, A., Pelillo, M., Loog, M., (eds.) Similarity-Based Pattern Recognition. LNCS, vol. 9370, pp. 84–92. Springer, Heidelberg (2015). https://doi.org/10.1007/978-3-319-24261-3_7
Panis, G., Lanitis, A., Tsapatsoulis, N., Cootes, T.F.: Overview of research on facial ageing using the FG-NET ageing database. Iet Biom. 5(2), 37–46 (2016)
Ricanek, K., Tesafaye, T.: Morph: a longitudinal image database of normal adult age-progression. In: FG, pp. 341–345 (2006)
Zhang, Y., Liu, L., Li, C., Loy, C.C.: Quantifying facial age by posterior of age comparisons. In: Proceedings of British Machine Vision Conference (BMVC) (2017)
Zhang, Z., Song, Y., Qi, H.: Age: progression/regression by conditional adversarial autoencoder. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
Abadi, M.: Tensorflow: large-scale machine learning on heterogeneous distributed systems (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, G., Kurita, T. (2021). Age Estimation from the Age Period by Using Triplet Network. In: Jeong, H., Sumi, K. (eds) Frontiers of Computer Vision. IW-FCV 2021. Communications in Computer and Information Science, vol 1405. Springer, Cham. https://doi.org/10.1007/978-3-030-81638-4_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-81638-4_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-81637-7
Online ISBN: 978-3-030-81638-4
eBook Packages: Computer ScienceComputer Science (R0)