ENHANCING AGE ESTIMATION FROM SCLERA IMAGES USING RESNET-50, VGG16, AND RANDOM FOREST
Abstract
This study presents a novel hybrid model for age prediction from sclera images, combining deep learning architectures ResNet-50 and VGG-16 with a Random Forest classifier. The hybrid approach aims to optimize both accuracy and computational efficiency, addressing limitations in previous methodologies. Results demonstrate exceptional performance, with the hybrid model achieving an overall accuracy of 98.85% and outperforming benchmark models. Detailed evaluation metrics reveal high precision, recall, and F1-scores across age groups, supported by insights from the confusion matrix. The model's practical applicability is demonstrated through efficient training and testing processes. This research bridges gaps in existing literature by integrating transfer learning, deep learning, and ensemble methods, while also addressing issues of computational complexity. The study underscores the potential of hybrid models to advance age prediction from biometric images, setting a new benchmark for future research in the field.
References
Abbasi, A., & Khan, M. (2016). Iris-pupil thickness-based method for determining age group of a person. Int. Arab J. Inf. Technol, 13(6).
Aminu Bashir Suleiman, S. L. (2023). CARDIOVASCULAR DISEASE PREDICTION USING RANDOM FOREST MACHINE LEARNING. FUDMA Journal of Sciences (FJS), 282-289. DOI: https://doi.org/10.33003/fjs-2023-0706-2128
Awujoola, O. J., Aniemeka, T. E., Ogwueleka, F. N., Abioye, O. A., Awujoola, A. E., & Uwa, C.O. (2024). Improved Breast Cancer Detection in Mammography Images: Integration of Convolutional Neural Network and Local Binary Pattern Approach. In Machine Learning Algorithms Using Scikit and TensorFlow Environments (pp. 221-248). IGI Global. DOI: https://doi.org/10.4018/978-1-6684-8531-6.ch011
Beattie, J. R., Pawlak, A. M., McGarvey, J. J., & Stitt, A. W. (2011). Sclera as a surrogate marker for determining AGE-modifications in Bruch's membrane using a Raman spectroscopybased index of aging. Investigative ophthalmology & visual science, 52(3), 1593-1598. DOI: https://doi.org/10.1167/iovs.10-6554
Das, S., De Ghosh, I., & Chattopadhyay, A. (2021). An efficient deep sclera recognition framework with novel sclera segmentation, vessel extraction and gaze detection. Signal Processing: Image Communication, 97, 116349. DOI: https://doi.org/10.1016/j.image.2021.116349
Erbilek, M., Fairhurst, M., & Abreu, M. C. D. C. (2013, December). Age prediction from iris biometrics. In 5th International Conference on Imaging for Crime Detection and Prevention (ICDP 2013) (pp. 1-5). IET. DOI: https://doi.org/10.1049/ic.2013.0258
Galbally J, Haraksim R, Beslay L. A Study of Age and Ageing in fingerprint Biometrics, IEEE Transactions on Information Forensics and Security, 14(5), 13511365, 2019. DOI: https://doi.org/10.1109/TIFS.2018.2878160
Irhebhude, M. E., Kolawole, A. O., & Abemi, H. (2023). Age And Gender Classification from Iris Images of the Eye Using Machine Learning Techniques. Academy Journal of Science and Engineering, 17(2), 54-69.
Kumar S, Rani S, Jain A, Verma C, Raboaca MS, Ills Z, Neagu BC. Face Spoofing, Age, Gender and Facial Expression Recognition Using Advance Neural Network Architecture-Based Biometric System, Sensors, 22(14), 51-60, 2022. DOI: https://doi.org/10.3390/s22145160
Narejo, S., Pasero, E., & Kulsoom, F. (2016). EEG based eye state classification using deep belief network and stacked autoencoder. International Journal of Electrical and Computer Engineering (IJECE), 6(6), 3131-3141. DOI: https://doi.org/10.11591/ijece.v6i6.12967
Odion, P. O., Musa, M. N., & Shuaibu, S. U. (2022). Age Prediction from Sclera Images using Deep Learning. Journal of the Nigerian Society of Physical Sciences, 787-787. DOI: https://doi.org/10.46481/jnsps.2022.787
Olorunsola, o., & olorunshola, O. Deep Learning Ensemble Approach to Age Group Classification based on fingerprint pattern. Advances in Artificial Intelligence Research 3(2), 76-84. DOI: https://doi.org/10.54569/aair.1303116
Othmani, A., Taleb, A. R., Abdelkawy, H., & Hadid, A. (2020). Age estimation from faces using deep learning: A comparative analysis. Computer Vision and Image Understanding, 196, 102961. DOI: https://doi.org/10.1016/j.cviu.2020.102961
Oyewola, D. O., Dada, E. G., Ndunagu, J. N., Umar, T. A., & Akinwunmi, S. A. (2021). COVID-19 risk factors, economic factors, and epidemiological factors nexus on economic impact: machine learning and structural equation modelling approaches. Journal of the Nigerian Society of Physical Sciences, 395-405. DOI: https://doi.org/10.46481/jnsps.2021.173
Rajput, M. R., & Sable, G. S. (2020). Age Group Estimation from Human Iris. In Soft Computing and Signal Processing: Proceedings of 2nd ICSCSP 2019 2 (pp. 519-529). Springer Singapore. DOI: https://doi.org/10.1007/978-981-15-2475-2_48
Rajput, M., & Sable, G. (2019, June). Deep learning-based gender and age estimation from human Iris. In Proceedings of the international conference on advances in electronics, electrical & computational intelligence (ICAEEC). DOI: https://doi.org/10.2139/ssrn.3576471
Russell, R., Sweda, J. R., Porcheron, A., & Mauger, E. (2014). Sclera color changes with age and is a cue for perceiving age, health, and beauty. Psychology and Aging, 29(3), 626. DOI: https://doi.org/10.1037/a0036142
Sgroi, A., Bowyer, K. W., & Flynn, P. J. (2013, June). The prediction of old and young subjects from iris texture. In 2013 International Conference on Biometrics (ICB) (pp. 1-5). IEEE. DOI: https://doi.org/10.1109/ICB.2013.6613010
Umarani, V., Julian, A., & Deepa, J. (2021). Sentiment analysis using various Machine learning and deep learning Techniques. Journal of the Nigerian Society of Physical Sciences, 385-394. DOI: https://doi.org/10.46481/jnsps.2021.308
Vitek, M., Rot, P., truc, V., & Peer, P. (2020). A comprehensive investigation into sclera biometrics: a novel dataset and performance study. Neural Computing and Applications, 32, 17941-17955. DOI: https://doi.org/10.1007/s00521-020-04782-1
Copyright (c) 2025 FUDMA JOURNAL OF SCIENCES
This work is licensed under a Creative Commons Attribution 4.0 International License.
FUDMA Journal of Sciences
