Comparative Analysis of Image Processing-Based Age Estimation Algorithms
DOI:
https://doi.org/10.15649/2346030X.3960Keywords:
age estimation, human computer interaction, computor vision, facial images, neural networksAbstract
The human body grows and develops with age. Age-Specific Human-Computer Interaction (ASHCI) has vast potential applications in daily life. One of the main reasons is that the aging effects on human faces present several unique characteristics that make age estimation a challenging task that requires non-standard classification approaches. Age estimation has become a challenging problem due to uncontrollable environment, insufficient and incomplete training data, strong person-specific, and large age span variation. In real life, computer vision applications requiring automatic age estimation from face images have attracted increasing attention. In this paper, we conferred the main perspectives used to improve the performance of the age estimation system, present the various types of techniques used in age estimation, and reveal where the experiments are being carried out. In addition to that several aging databases consisting of age descriptions are described briefly. Eventually, we presented a comparative analysis between all the preferred methods according to the techniques used.
References
[1] A. Othmani , A. Taleb, H. Abdelkawy and A. Hadid, “Age estimation from faces using deep learning: A comparative analysis,” Computer Vision and Image Understanding, 196, 2020.
[2] Umirzakova, Sabina & Whangbo, Teag Keun, “Edge‐based effective active appearance model for real‐time wrinkle detection”, Skin Research and Technology, 2020, 27. doi:10.1111/srt.12977.
[3] M. Sawant and K. Bhurchundi, “Ordinal Regression with Multiple Output CNN for Age Estimation,” IEEE Access, 2018.
[4] M. M. Sawant, K. M. Bhurchandi, “Age invariant face recognition: a survey on facial aging databases, techniques and effect of aging”, Artificial Intelligence Review, 52, 2019, 981–1008, doi: 10.1007/s10462-018-9661-z.
[5] M. Benkaddour, “CNN Based Features Extraction for Age Estimation and Gender Classification”, Informatica, 45, 2021, doi: 10.31449/inf.v45i5.3262.
[6] H. Liao, Y. Yan, W. Dai, and P. Fan, “Age Estimation of Face Images Based on CNN and Divide-and-Rule Strategy,” Hindawi, Mathematical Problems in Engineering, Volume 2018, 2018.
[7] N. Hasan and S. Mahdi, “Facial Features Extraction using LBP for Human Age Estimation Based on SVM Classifier”, IEEE International Conference on Computer Science and Software Engineering (CSASE), 2020.
[8] O. Osman, “An Effective Age Estimation Method using Scattering Transform,” International Journal of New Technology and Research (IJNTR),Volume-6, 2020.
[9] A. Shejul, K. Kinage, and B. Reddy, “CDBN: Crow Deep Belief Network Based on Scattering and AAM Features for Age Estimation,” Journal of Signal Processing Systems 93, 2021, pg. no. 879–897.
[10] S. Hiba and Y. Keller, “Hierarchical Attention-based Age Estimation and Bias Estimation,” Computer Vision and Pattern Recognition, arXiv.org, 2021.
[11] A. Micheal and P. Geetha, “A Novel Hybrid Feature Framework for Multi-View Age Estimation,” Applied Artificial Intelligence, An International Journal, Volume 35, 2021.
[12] C. Xiao, Z. Zhifeng, C. Jie and Z. Qian, "Combined Deep Learning With Directed Acyclic Graph SVM for Local Adjustment of Age Estimation," in IEEE Access, vol. 9, pp. 370-379, 2021, doi: 10.1109/ACCESS.2020.3046661.
[13] A. Sakata, Y. Makihara, N. Takemura, D. Muramatsu, and Y. Yagi, “How Confident Are You in Your Estimate of a Human Age? Uncertainty-aware Gait-based Age Estimation by Label Distribution Learning,” IEEE Inter national Joint Conference on Biometrics (IJCB), 2020.
[14] N. Liu, “Chronological Age Estimation of Lateral Cephalo metric radiographs with deep learning,” IEEE Transaction on Medicak Imaging, 2021.
[15] P. Siritanawan, H. Ichikawa and K. Kotani, “Facial Age Progression using Conditional Generative Adversarial Network with Heritable Visual Features,” IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2021,pp. 1449-1454.
[16] C. Hu, J. Gao, J. Chen, D. Jiang and Y. Shu, "Fine-Grained Age Estimation With Multi-Attention Network," in IEEE Access, vol. 8, 2020, pp. 196013-196023.
[17] J. Xie and C. Pun, "Deep and Ordinal Ensemble Learning for Human Age Estimation From Facial Images," in IEEE Transactions on Information Forensics and Security, vol. 15, 2020, pp. 2361-2374.
[18] Z. Bao, Z. Tan, J. Wan, X. Ma, G. Guo and Z. Lei, "Divergence-Driven Consistency Training for Semi-Supervised Facial Age Estimation," in IEEE Transactions on Information Forensics and Security, vol. 18, 2023, pp. 221-232.
[19] F. Dornaika, S. Bekhouche, and I. Carreras. "Robust regression with deep CNNs for facial age estimation: An empirical study", Expert Systems with Applications 141, 2020.
[20] B. Zhang and Y. Bao, "Cross-Dataset Learning for Age Estimation," in IEEE Access, vol. 10, 2022, pp. 24048-24055.
[21] O. Agbo-Ajala and S. Viriri, "A Lightweight Convolutional Neural Network for Real and Apparent Age Estimation in Unconstrained Face Images," in IEEE Access, vol. 8, 2020, pp. 162800-162808.
[22] A. Takeda, T. Nakagawa, M. Takaso, M. Nakamura, and M. Hitosugi, “Exploring the potential for age estimation using facial image sensing technology for postmortem in vestigation,” Elsevier, Legal Medicine, Volume 48, 2020.
[23] M. Sawant, K. M. Bhurchandi, “Discriminative aging subspace learning for age estimation”, Soft Comput 26, 2022, 9189–9198, doi: 10.1007/s00500-022-07333-z.
[24] “The FG-NET Aging Database,” http://sting.cycollege.ac.cy/alanitis/ fgnetaging/index.htm, 2002.
[25] K. Ricanek and T. Tesafaye, “Morph: A longitudinal image database of normal adult age-progression,” Proceedings of IEEE 7th International Conference on Automatic Face and Gesture Recognition, IEEE, Southampton, 2006, pp. 341–345.
[26] G. Antipov, M. Baccouche, S. Berrani, and J. Dugelay, “Apparent Age Estimation from Face Images Combining General and Children-Specialized Deep Learning Models,” IEEE Conference on Computer Vision and Pattern Workshops(CVPRW), 2016.
[27] P.Phillips, H. Moon, S. Rizvi and P.Rauss, “The FERET Evaluation Methodology for Face-Recognition Algorithms,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 22, no. 10, 2000, pp. 1090- 1104.
[28] B. Chen, C. Chen and W. Hsu, “Cross-Age Celebrity Dataset (CACD),” ECCV 2014, Springer International Publishing Switzerland, Part VI, LNCS 8694, 2014, pp. 768-783.
[29] S. Escalera, J. Fabian, P. Pardo, X. Baro, J. Gonzalez, H. J. Escalante, D. Misevic, U. Steiner, and I. Guyon, “Chalearn looking at people 2015: Apparent age and cultural event recognition datasets and results,” Proceedings of the IEEE International Conference on Computer Vision Workshops, 2015, pp. 1–9.
[30] C. Xu, Y. Makihara, G. Ogi, X. Li, Y. Yagi and J. Lu, “The OU-ISIR Gait Database comprising the Large Population Dataset with Age and performance evaluation of age estimation,” IPSJ Transactions on Computer Vision and Applications, 2017.
[31] M. Minear and D. Park, “A lifespan database of adult facial stimuli. Behavior Research Methods,” Instruments, and Computers, 36, 2004, pp. 630–633.
[32] Z. Huang, J. Zhang, and H. Shan, “When Age-Invarient Face Recognition Meets Face Age Synthesis: A Multi Task Learning Framework,” Computer Vision and Pattern Recognition, arXiv.org, 2021.
[33] S. Moschoglou, A. Papaioannou, C. Sagonas, J. Deng, I. Kotsia, and S. Zafeiriou, “Agedb: the first manually collected, in-the-wild age database,” IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2017, pp 51–59.
[34] T. Zheng, W. Deng, and J. Hu, “Cross-age lfw: A database for studying cross-age face recognition in unconstrained environments”, arXiv.org, 2017.
[35] Z. Niu, M. Zhou, L. Wang, X. Gao, and G. Hua, “Ordinal Regression with Multiple Output CNN for Age Estimation,” IEEE Conference on Computer Vision and Pattern Recognition, 2016.
Downloads
Published
How to Cite
Downloads
Issue
Section
License
Copyright (c) 2025 AiBi Journal of Research, Administration and Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
The journal offers open access under a Creative Commons Attibution License
This work is under license Creative Commons Attribution (CC BY 4.0).
