Age-Group Classification from Facial Parts Using a Multi-Stream Convolutional Neural Network
Keywords:
Feature extraction, Age estimation, CNN, Classification Analysis, Dataset.Abstract
Age is a most significant part of human life. With time, there are many changes in the facial structure. The facial structure indicates the combination of the parts of the face (eyebrows, mouth, nose, eyes, and cheeks), shape, and texture of the skin. Several strategies have been proposed by researchers for age detection, although more work is still needed in this area for better results. In this study, we describe a method for estimating a person’s age by using facial landmarks to crop facial features from an image of a person. The multi-stream CNN (convolutional neural network) model receives input from the facial regions that were clipped. The suggested approach uses age recognition methods on images that haven’t been filtered. We are working on an Adience benchmark dataset that is primarily intended for identifying age and gender. Compared with processing complete facial images, the proposed approach processes cropped facial parts, reducing the amount of image data presented to each stream. The resulting performance is evaluated using the Adience benchmark dataset. The proposed architecture addresses overfitting through L2 regularization and dropout, while the data are evaluated using the reported cross-validation protocol.
Downloads
References
El Dib, M. Y., & Onsi, H. M. (2011). Human age estimation framework using different facial parts. Egyptian Informatics Journal, 12(1), 53–59.
Guo, G., Fu, Y., Huang, T. S., & Dyer, C. R. (2008, January). Locally adjusted robust regression for human age estimation. In 2008 IEEE Workshop on Applications of Computer Vision, 1–6, IEEE.
Agbo-Ajala, O., &Viriri, S. (2020). A lightweight convolutional neural network for real and apparent age estimation in unconstrained face images. IEEE Access, 8, 162800–162808.
Hasan, N. F., & Mahdi, S. Q. (2020, April). Facial features extraction using LBP for human age estimation based on SVM classifier. In 2020 International Conference on Computer Science and Software Engineering (CSASE), 50–55, IEEE. DOI: 10.1109/CSASE48920.2020.9142061.
Han, S. (2020, August). Age estimation from face images based on deep learning. In 2020 International Conference on Computing and Data Science (CDS), 288–292, IEEE. DOI: 10.1109/CDS49703.2020.00063.
Kazemi, V., & Sullivan, J. (2014). One millisecond face alignment with an ensemble of regression trees. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1867–1874. DOI: 10.1109/CVPR.2014.241.
Dibeklioğlu, H., Alnajar, F., Salah, A. A., & Gevers, T. (2015). Combining facial dynamics with appearance for age estimation. IEEE Transactions on Image Processing, 24(6), 1928–1943.
Fu, Y., Xu, Y., & Huang, T. S. (2007, July). Estimating human age by manifold analysis of face pictures and regression on aging features. In 2007 IEEE International Conference on Multimedia and Expo, 1383–1386, IEEE. DOI: 10.1109/ICME.2007.4284917.
Angeloni, M., de Freitas Pereira, R., & Pedrini, H. (2019). Age estimation from facial parts using compact multi-stream convolutional neural networks. In Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops. DOI: 10.1109/ICCVW.2019.00366.
Del Coco, M., Carcagni, P., Leo, M., Spagnolo, P., Mazzeo, P. L., &Distante, C. (2017). Multi-branch CNN for multi-scale age estimation. 19th International Conference on Image Analysis and Processing – ICIAP, Catania, Italy, September 11–15, 2017, Proceedings, Part II 19, 234–244, Springer International Publishing.
Al-Shannaq, A. S., & Elrefaei, L. A. (2019). Comprehensive analysis of the literature for age estimation from facial images. IEEE Access, 7, 93229–93249. DOI: 10.1109/ACCESS.2019.2927825.
Eidinger, E., Enbar, R., & Hassner, T. (2014). Age and gender estimation of unfiltered faces. IEEE Transactions on Information Forensics and Security, 9(12), 2170–2179. DOI: 10.1109/tifs.2014.2359646.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
