Facial age recognition based on deep manifold learning

Huiying Zhang; Jiayan Lin; Lan Zhou; Jiahui Shen; Wenshun Sheng; Huiying Zhang; Jiayan Lin; Lan Zhou; Jiahui Shen; Wenshun Sheng

doi:10.3934/mbe.2024198

Mathematical Biosciences and Engineering

2024, Volume 21, Issue 3: 4485-4500. doi: 10.3934/mbe.2024198

Previous Article Next Article

Research article

Facial age recognition based on deep manifold learning

Pujiang Institute, Nanjing Tech University, Nanjing 211200, China

Academic Editor: Yang Kuang

Received: 30 December 2023 Revised: 02 February 2024 Accepted: 18 February 2024 Published: 28 February 2024

Facial age recognition has been widely used in real-world applications. Most of current facial age recognition methods use deep learning to extract facial features to identify age. However, due to the high dimension features of faces, deep learning methods might extract a lot of redundant features, which is not beneficial for facial age recognition. To improve facial age recognition effectively, this paper proposed the deep manifold learning (DML), a combination of deep learning and manifold learning. In DML, deep learning was used to extract high-dimensional facial features, and manifold learning selected age-related features from these high-dimensional facial features for facial age recognition. Finally, we validated the DML on Multivariate Observations of Reactions and Physical Health (MORPH) and Face and Gesture Recognition Network (FG-NET) datasets. The results indicated that the mean absolute error (MAE) of MORPH is 1.60 and that of FG-NET is 2.48. Moreover, compared with the state of the art facial age recognition methods, the accuracy of DML has been greatly improved.
- age recognition,
- manifold learning,
- deep learning,
- convolution neural network,
- feature extraction,
- mean absolute error
Citation: Huiying Zhang, Jiayan Lin, Lan Zhou, Jiahui Shen, Wenshun Sheng. Facial age recognition based on deep manifold learning[J]. Mathematical Biosciences and Engineering, 2024, 21(3): 4485-4500. doi: 10.3934/mbe.2024198

Related Papers:

Abstract

Facial age recognition has been widely used in real-world applications. Most of current facial age recognition methods use deep learning to extract facial features to identify age. However, due to the high dimension features of faces, deep learning methods might extract a lot of redundant features, which is not beneficial for facial age recognition. To improve facial age recognition effectively, this paper proposed the deep manifold learning (DML), a combination of deep learning and manifold learning. In DML, deep learning was used to extract high-dimensional facial features, and manifold learning selected age-related features from these high-dimensional facial features for facial age recognition. Finally, we validated the DML on Multivariate Observations of Reactions and Physical Health (MORPH) and Face and Gesture Recognition Network (FG-NET) datasets. The results indicated that the mean absolute error (MAE) of MORPH is 1.60 and that of FG-NET is 2.48. Moreover, compared with the state of the art facial age recognition methods, the accuracy of DML has been greatly improved.

References

[1]	G. Panis, A. Lanitis, N. Tsapatsoulis, T. F. Cootes, Overview of research on facial ageing using the FG-NET ageing database, IET Biom., 5 (2016), 37–46. https://doi.org/10.1049/iet-bmt.2014.0053 doi: 10.1049/iet-bmt.2014.0053
[2]	C. Wu, H. J. Lee, Learning age semantic factor to enhance group-based representations for cross-age face recognition, Neural Comput. Appl., 34 (2022), 13063–13074. https://doi.org/10.1007/s00521-022-07176-7 doi: 10.1007/s00521-022-07176-7
[3]	Z. Huang, J. Zhang, H. Shan, When age-invariant face recognition meets face age synthesis: A multi-task learning framework, in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2021), 7282–7291. https://arXiv.org/abs/2103.01520
[4]	M. Awais, C. Chen, X. Long, B. Yin, A. Nawaz, S. F. Abbasi, Novel framework: face feature selection algorithm for neonatal facial and related attributes recognition, IEEE Access, 8 (2020), 59100–59113. https://doi.org/10.1109/ACCESS.2020.2982865 doi: 10.1109/ACCESS.2020.2982865
[5]	Y. H. Kwon, N. da V. Lobo, Age classification from facial images, Comput. Vision Image Understanding, 74 (1999), 1–21. https://doi.org/10.1006/cviu.1997.0549 doi: 10.1006/cviu.1997.0549
[6]	G. Guo, G. Mu, Y. Fu, T. S. Huang, Human age estimation using bio-inspired features, in 2009 IEEE Conference on Computer Vision and Pattern Recognition, (2009), 112–119. https://doi.org/10.1109/CVPR.2009.5206681
[7]	K. Y. Chang, C. S. Chen, Y. P. Hung, Ordinal hyperplanes ranker with cost sensitivities for age estimation, in Conference on Computer Vision and Pattern Recognition (CVPR), (2011), 585–592. https://doi.org/10.1109/CVPR.2011.5995437
[8]	B. B. Gao, C. Xing, C. W. Xie, J. Wu, X. Geng, Deep label distribution learning with label ambiguity, IEEE Trans. Image Process., 26 (2017), 2825–2838. https://doi.org/10.1109/TIP.2017.2689998 doi: 10.1109/TIP.2017.2689998
[9]	H. Y. Zhang, W. S. Sheng, Y. Z. Zeng, Face Age recognition algorithm based on label distribution learning, J. Jiangsu Univ., 44 (2023), 180–185.
[10]	S. Mei, Y. Geng, J. Hou, Q. Du, Learning hyperspectral images from RGB images via a coarse-to-fine CNN, Sci. China Inf. Sci., 65 (2022), 1–14. https://doi.org/10.1007/s11432-020-3102-9 doi: 10.1007/s11432-020-3102-9
[11]	M. A. Marjan, M. R. Islam, M. P. Uddin, PCA-based dimensionality reduction for face recognition, Elecommun. Comput. Electron. Control, 19 (2021), 1622–1629. http://doi.org/10.12928/telkomnika.v19i5.19566 doi: 10.12928/telkomnika.v19i5.19566
[12]	G. Guo, Y. Fu, C. R. Dyer, T. S. Huang, Image-based human age estimation by manifold learning and locally adjusted robust regression, IEEE Trans. Image Process., 17 (2008), 1178–1188. https://doi.org/10.1109/TIP.2008.924280 doi: 10.1109/TIP.2008.924280
[13]	X. He, P. Niyogi, Locality preserving projections, Adv. Neural Inf. Process. Syst., 16 (2003).
[14]	Y. Fu, T. S. Huang, Human age estimation with regression on discriminative aging manifold, IEEE Trans. Multimedia, 10 (2008), 578–584. https://doi.org/10.1109/TMM.2008.921847 doi: 10.1109/TMM.2008.921847
[15]	S. Kshatriya, M. Sawant, K. M. Bhurchandi, Feature selection and feature manifold for age estimation, in Computer Vision and Image Processing: 5th International Conference, 1377 (2021), 112–123. https://doi.org/10.1007/978-981-16-1092-9_10
[16]	R. Zhang, A review of face recognition based on deep learning, in Institute of Management Science and Industrial Engineering.Proceedings of 2019 3rd International Conference on Computer Engineering, Information Science and Internet Technology (CII 2019), 2019. https://doi.org/10.26914/c.cnkihy.2019.037191
[17]	V. Pouli, S. Kafetzoglou, E. E. Tsiropoulou, A. Dimitriou, S. Papavassiliou, Personalized multimedia content retrieval through relevance feedback techniques for enhanced user experience, in 2015 13th International Conference on Telecommunications (ConTEL), 2015. https://doi.org/10.1109/ConTEL.2015.7231205
[18]	H. Wang, V. Sanchez, C. T. Li, Improving face-based age estimation with attention-based dynamic patch fusion, IEEE Trans. Image Process., 31 (2022), 1084–1096. https://doi.org/10.1109/TIP.2021.3139226 doi: 10.1109/TIP.2021.3139226
[19]	N. Sharma, R. Sharma, N. Jindal, Face-based age and gender estimation using improved convolutional neural network approach, Wireless Pers. Commun., 124 (2022), 3035–3054. https://doi.org/10.1007/s11277-022-09501-8 doi: 10.1007/s11277-022-09501-8
[20]	M. Samareh-Jahani, F. Saberi-Movahed, M. Eftekhari, G. Aghamollaei, P. Tiwari, Low-redundant unsupervised feature selection based on data structure learning and feature orthogonalization, Expert Syst. Appl., 240 (2024), 122556. https://doi.org/10.1016/j.eswa.2023.122556 doi: 10.1016/j.eswa.2023.122556
[21]	S. Karami, F. Saberi-Movahed, P. Tiwari, P. Marttinen, S. Vahdati, Unsupervised feature selection based on variance-covariance subspace distance, Neural Networks, 166 (2023), 188–203. https://doi.org/10.1016/j.neunet.2023.06.018 doi: 10.1016/j.neunet.2023.06.018
[22]	A. Krizhevsky, I. Sutskever, G. E. Hinton, Imagenet classification with deep convolutional neural networks, Adv. Neural Inf. Process. Syst., 25 (2012). https://doi.org/10.1145/3065386 doi: 10.1145/3065386
[23]	O. Sendik, Y. Keller, DeepAge: Deep Learning of face-based age estimation, Signal Process. Image Commun., 78 (2019), 368–375. https://doi.org/10.1016/j.image.2019.08.003 doi: 10.1016/j.image.2019.08.003
[24]	S. Lim, Estimation of gender and age using CNN-based face recognition algorithm, J. Xi'an Univ. Sci. Technol., 9 (2020), 203–211. https://doi.org/10.7236/IJASC.2020.9.2.203 doi: 10.7236/IJASC.2020.9.2.203
[25]	Sonal, A. Singh, C. Kant, Face and age recognition using three-dimensional discrete wavelet transform and rotational local binary pattern with radial basis function support vector machine method, Int. J. Electr. Eng. Educ., 60 (2023), 389–404. https://doi.org/10.1177/0020720920988489 doi: 10.1177/0020720920988489
[26]	G. Guo, G. Mu, Simultaneous dimensionality reduction and human age estimation via kernel partial least squares regression, in Conference on Computer Vision and Pattern Recognition (CVPR), (2021), 657–664. https://doi.org/10.1109/CVPR.2011.5995404
[27]	C. Szegedy, S. Ioffe, V. Vanhoucke, A. Alemi, Inception-v4, inception-resnet and the impact of residual connections on learning, in Proceedings of the AAAI Conference on Artificial Intelligence, 31 (2016). https://doi.org/10.1609/aaai.v31i1.11231
[28]	L. Y. Song, S. Zhou, H. P. Lu, Direct ICA on data tensor via random matrix modeling, Signal Process., (2022), 508–519. https://doi.org/10.1016/j.sigpro.2022.108508 doi: 10.1016/j.sigpro.2022.108508
[29]	S. T. Roweis, L. K. Saul, Nonlinear dimensionality reduction by locally linear embedding, Science, 290 (2000), 2323–2326. https://doi.org/10.1126/science.290.5500.2323 doi: 10.1126/science.290.5500.2323
[30]	K. Ricanek, T. Tesafaye, Image-based human age estimation by manifold learning and locally adjusted robust regression, IEEE Comput. Soc., (2006), 341–345. https://doi.org/10.1109/FGR.2006.78 doi: 10.1109/FGR.2006.78
[31]	J. Lu, V. Liong, J. Zhou, Cost-sensitive local binary feature learning for facial age estimation, in IEEE Transactions on Image Processing, (2015), 144–157. https://doi.org/110.1109/TIP.2015.2481327
[32]	H. Liu, J. Lu, J. Feng, J. Zhou, Ordinal deep feature learning for facial age estimation, in 12th International Conference on Automatic Face and Gesture Recognition, (2017), 4465–4470. https://doi.org/10.1109/FG.2017.28
[33]	X. Liu, Y. Zou, H. Kuang, Face image age estimation based on data augmentation and lightweight convolutional neural network, Symmetry, 12 (2020), 146–163. https://doi.org/10.3390/sym12010146 doi: 10.3390/sym12010146

Reader Comments

Your name:*

Email:*
© 2024 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)