Evaluation of Classification and Regression Models Using Facial Images for Human Age Estimation
Keywords:
Convolutional Neural Network, Regression, ClassificationAbstract
The growing interest in automatic age prediction from facial images stems from its security control, potential applications in law enforcement and Human-Computer Interaction (HCI). However, despite notable advancements in this field, automatic age estimation remains a formidable challenge. This complexity arises because the face aging process is influenced not only by intrinsic factors such as genetic components but also by extrinsic factors like lifestyle, expressions, and environmental conditions. Consequently, individuals of the same age may exhibit markedly different appearances due to varying rates of facial aging. In response to these challenges, we propose an experimental approach for automatic age estimation.In literature, researchers carried their research work using pre-trained models as these models saves time, cost and computational resources, avoids over-fitting with increased accuracy but these models are domain specific and acts as black box which makes fine-tuning difficult. In our research, we designed a Convolution Neural Networks model for age estimation and analyzed the performance on the publicly available FGNET, Adience, APPA-REAL, UTKFace, and All-Age-Face datasets by considering age estimation as classification and regression problem. Then compared the proposed model performance with the existing pre-trained models and observed both classification and regression results are in par with the performance of the existing pre-trained models.
Downloads
References
Huerta, I., Fernández, C., Segura, C., Hernando, J., and Prati, A, “A deep analysis on age estimation”, Pattern Recognition Letter 68, 239–249. DOI: 10.1016/j.patrec.2015.06.006
Drobnyh, K. A., and Polovinkin, A. N, “Using supervised deep learning for human age estimation problem”, Int. Arch. Photogram. Remote Sens. Spatial Inf.Sci. XLII-2/W4, 97–100. DOI: 10.5194/isprs-archives-XLII-2-W4-97-2017
George, G., Uppin, C., & Bello, U. A. (2024). Human Age Estimation from Face Images with Deep Convolutional Neural Networks Using Transfer Learning.
Puc, A., Štruc, V., & Grm, K. (2021, January). Analysis of race and gender bias in deep age estimation models. In 2020 28th European Signal Processing Conference (EUSIPCO) (pp. 830-834). IEEE.
Meghana, A. S., Sudhakar, S., Arumugam, G., Srinivasan, P., & Prakash, K. B. (2020). Age and gender prediction using convolution, ResNet50, and inception ResNetV2. International Journal of Advanced Trends in Computer Science and Engineering, 9(2), 1328-1334.
Ghildiyal, A., Sharma, S., Verma, I., & Marhatta, U. (2020, December). Age and gender predictions using artificial intelligence algorithm. In 2020 3rd International Conference on Intelligent Sustainable Systems (ICISS) (pp. 371-375). IEEE.
Sheoran, V., Joshi, S., & Bhayani, T. R. (2021). Age and gender prediction using deep cnns and transfer learning. In Computer Vision and Image Processing: 5th International Conference, CVIP 2020, Prayagraj, India, December 4-6, 2020, Revised Selected Papers, Part II 5 (pp. 293-304). Springer Singapore.
Qawaqneh, Z., Mallouh, A. A., & Barkana, B. D. (2017). Deep convolutional neural network for age estimation based on VGG-face model. arXiv preprint arXiv:1709.01664.
Benkaddour, M. K. (2021). CNN based features extraction for age estimation and gender classification. Informatica, 45(5).
Lapuschkin, S., Binder, A., Muller, K. R., & Samek, W. (2017). Understanding and comparing deep neural networks for age and gender classification. In Proceedings of the IEEE international conference on computer vision workshops (pp. 1629-1638).
Duan, M., Li, K., & Li, K. (2017). An ensemble CNN2ELM for age estimation. IEEE Transactions on Information Forensics and Security, 13(3), 758-772.
Lu, D., Wang, D., Zhang, K., & Zeng, X. (2023). Age estimation from facial images based on Gabor feature fusion and the CIASO‐SA algorithm. CAAI Transactions on Intelligence Technology, 8(2), 518-531.
Deng, Y., Teng, S., Fei, L., Zhang, W., & Rida, I. (2021). A multifeature learning and fusion network for facial age estimation. Sensors, 21(13), 4597.
Raman, V., ELKarazle, K., & Then, P. (2022). Gender-specific facial age group classification using deep learning. Intell. Autom. Soft Comput, 34, 105-118.
Zhang, Z., Song, Y., & Qi, H. (2017). Age progression/regression by conditional adversarial autoencoder. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5810-5818).
Fu, Y., Hospedales, T. M., Xiang, T., Gong, S., & Yao, Y. (2014, September). Interestingness prediction by robust learning to rank. In European conference on computer vision (pp. 488-503). Cham: Springer International Publishing.
Chakraborty, Esha. All Age Face Dataset. 2019. https://www.kaggle.com/datasets/eshachakraborty00/all-age-face-dataset.
Agustsson, E., Timofte, R., Escalera, S., Baro, X., Guyon, I., & Rothe, R. (2017, May). Apparent and real age estimation in still images with deep residual regressors on appa-real database. In 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017) (pp. 87-94). IEEE.
Harel, S. (2015). Effective Face Frontalization in Unconstrained Images (Doctoral dissertation, Open University of Israel).
Gao, B. B., Zhou, H. Y., Wu, J., & Geng, X. (2018, July). Age Estimation Using Expectation of Label Distribution Learning. In IJCAI (Vol. 1, p. 3).
Rothe, R., Timofte, R., & Van Gool, L. (2015). Dex: Deep expectation of apparent age from a single image. In Proceedings of the IEEE international conference on computer vision workshops (pp. 10-15).
Ekmekji, A. (2016). Convolutional neural networks for age and gender classification. Stanford University.
Levi, G., & Hassner, T. (2017). Age and gender classification using convolutional neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops (pp. 34-42).
Anand, A., Labati, R. D., Genovese, A., Munoz, E., Piuri, V., & Scotti, F. (2017, November). Age estimation based on face images and pre-trained convolutional neural networks. In 2017 IEEE symposium series on computational intelligence (SSCI) (pp. 1-7). IEEE.
Xie, J. C., & Pun, C. M. (2020). Deep and ordinal ensemble learning for human age estimation from facial images. IEEE Transactions on Information Forensics and Security, 15, 2361-2374.
Taheri, S., & Toygar, Ö. (2019). On the use of DAG-CNN architecture for age estimation with multi-stage features fusion. Neurocomputing, 329, 300-310.
Sawant, M., Addepalli, S., & Bhurchandi, K. (2019). Age estimation using local direction and moment pattern (ldmp) features. Multimedia Tools and Applications, 78(21), 30419-30441.
Ng, C. C., Yap, M. H., Cheng, Y. T., & Hsu, G. S. (2018). Hybrid ageing patterns for face age estimation. Image and Vision Computing, 69, 92-102.
Chen, S., Zhang, C., & Dong, M. (2017). Deep age estimation: From classification to ranking. IEEE Transactions on Multimedia, 20(8), 2209-2222.
Pontes, J. K., Britto Jr, A. S., Fookes, C., & Koerich, A. L. (2016). A flexible hierarchical approach for facial age estimation based on multiple features. Pattern Recognition, 54, 34-51.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Bhuvaneshwari Patil, Shivanand Ruma, Mallikarjun Hangarge
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.
