Age Prediction from Sclera Images using Deep Learning

Authors

  • P. O. Odion Computer Science Dept, Nigerian Defence Academy Kaduna, Nigeria
  • M. N. Musa Cyber Security Dept, Nigerian Defence Academy Kaduna, Nigeria
  • S. U. Shuaibu Computer Science Dept, Nigerian Defence Academy Kaduna, Nigeria

Keywords:

sclera images, pre-trained CNN, age prediction, deep learning, segmentation

Abstract

Automatic age classification has drawn the interest of many scholars in the fields of machine learning and deep learning. In this study, we looked at the problem of estimating age groups using different biometric modalities of human beings. We looked at the problem of determining age groups in humans using various biometric modalities. Specifically, we focused on the use of transfer learning for sclera age group classification. 2000 Sclera images were collected from 250 individuals of various ages, and Otsu thresholding was used to segment the images using morphological processes. Experiment was conducted to determine how accurately the age group of a person can be classified from sclera images using pretrained CNN architectures. The segmented images were trained and tested on four different pre-trained models (VGG16, ResNet50, MobileNetV2, EffcientNet-B1), which were compared based on different performance metrics in which ResNet-50 was shown to outperform the others, resulting in an accuracy, precision, recall and F1-score of 95% while VGG-16, EffcientNetB1, and MobileNetV2 had 94%, 93%, and 91%, respectively. The findings from the study showed that there is an aging template in the sclera that can be utilized to classify age.

Author Biography

M. N. Musa, Cyber Security Dept, Nigerian Defence Academy Kaduna, Nigeria

Computer Science Department and a senior lecturer

Dimensions

S. Narejo, E. Pasero & F. Kulsoom, “EEG based eye state classification using deep belief network and stack encoder”, International Journal of Electrical Computer Engineering 6 (2016) 3131.

A. Othmani, A. Taleb, H. Abdelkawy & A. Hadid, “Age estimation from faces using deep learning: A comparative analysis”, Computer Vison and Image Processing 196 (2020) 102961.

D. O. Oyewola, G. D. Emmanuel, N. N. Juliana, A. U. Terrang & S. A. Akinwunmi, ”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 3 (2021) 395.

V. Umarani, A. Julian & J. Deepa, “Sentiment Analysis using various Machine Learning and Deep Learning Techniques”, Journal of the Nigerian Society of Physical Sciences 3 (2021) 385.

A. B. Yusuf, R. M. Dima & S. K. Aina, “Optimized Breast Cancer Classification using Feature Selection and Outliers Detection”, Journal of the Nigerian Society of Physical Sciences 3 (2021) 298.

O. Olubi, E. Oniya & T. Owolabi, “Development of predictive model for radon-222 estimation in the atmosphere using stepwise regression and grid search based-random forest regression” Journal of the Nigerian Society of Physical Sciences 3 (2021) 132.

A. Mollahosseini, D. Chan & M. H. Mahoor, “Going deeper in facial expression recognition using deep neural networks”, IEEE Winter Conference on Applications of Computer Vision (2016) 1.

R. Angulu, J. R. Tapamo & A. O. Adewumi, “Age estimation via faces: A Survey”, EURASIP Journal of Image and Video Processing 2018 (2018) 1.

K. Wang & A. Kumar, “Cross-spectral iris recognition using supervised CNN amd supervised discrete hashing”, Pattern Recognition 86 (2019) 85.

J. R. Beattie, A. M. Pawlak, J. J. McGarvey & A.W. Stitt, “Sclera as a surrogate marker for determining AGE-modifications in Bruch’s membrane using a Rzman spectroscopy-based index of aging”, Investigate ophthalmology & visual science 52 (2011) 1593.

A. Abbasi & M. Khan, “Iris-pupil thickness based method for determining age group of a person”, International Arab Journal of Information Technology 13 (2016).

S. Das, I. D. Ghosh & A. Chattopadhyay, “Deep age estimation using sclera images in multiple environment”, Applied Information Processing Systems (2022) 93.

V. Patil & A. Patil, “Human identification method: sclera recognition”, International Journal of Computer SScience Networks 6 (2017) 24.

R. Russell, J. R. Sweda, A. Porcheron& E. Mauger, “Sclera color changes with age and is a cue for perceiving age, health and beauty”, Psychology and Aging 29 (2014) 626.

S. Taheri & O. Toygar, “On the use of DAG-CNN architecture for age estimation using multi-stage features fusion”, Neurocomputing 329 (2019) 300.

C. C. Aggarwal, “Neural Networks and Deep Learning”, Springer 10 (2018) 978.

S. Tammina, ”Transfer learning using vgg-16 with deep convolutional neural network for classifying images.” International Journal of Scientific and Research Publications (IJSRP) 10 (2019) 143.

K. Simonyan & A. Zisserman, ”Very deep convolutional networks for large-scale image recognition” arXiv preprint arXiv:1409.1556 (2014).

K. He, X. Zhang, S. Ren & J. Sun, “Deep residual learning for image recognition” In Proceedings of the IEEE conference on computer vision and pattern recognition (2016) 770.

M. Sandler, A. Howard, M. Zhu, A. Zhmoginov & L.C. Chen, “Mobilenetv2: Inverted residuals and linear bottlenecks” In Proceedings of the IEEE conference on computer vision and pattern recognition (2018) 4510.

M. Tan & Q. Le, ”Efficientnet: Rethinking model scaling for convolutional neural networks” International conference on machine learning. PMLR (2019) 6105.

A. Sgroi, K. W. Bowyer & P. J. Flynn, “The Prediction of Old and Young Subjects from Iris Texture”, International Conference on Biometrics (2013) 1.

M. Erbilek, M. Fairhurst & M. D. C. A. Cristiany, “Age prediction from iris biometrics”, 5th International Conference on Imaging for Crime Detection and Prevention (ICDP) (2013) 1.

M. R. Rajput & G. S. Sable, “Age Group Estimation from Human Iris”, Advances in Intelligent Systems and Computing:Soft Computing and Signal Processing, 1118 (2019) 519.

M. Rajput & G. Sable, “Deep learning based gender and age estimstion from human iris”, Proceedings of the International Conference on Advances in Electronics Electrical & Computational Intelligence (ICAEEC) (2019).

S. Das, I. D. Ghosh & A. Chattopadhyay, “An efficient deep learning strategy: Its application in sclera segmentation”, IEEE Applied Signal Processing Conference (ASPCON) (2020) 232.

P. Rot, M. Vitek, K. Grm, Z. Emersic, P. Peer & V. Struc, “Deep sclera segmentation and recognition”, in Handbook of vascular biometrics Cham (2020) 395.

J. T. C. Ming, N. M. Noor, O. M. Rijal, R. M. Kassim & A. Yusuf, “Lung disease classification using di erent deep learning architectures and principal component analysis”, 2nd International Conference on Biosignal Analysis, Processing and Systems (ICBAPS), IEEE (2018) 187.

S.H. Tsang, “Review:MobileNetV2 - lightweight model (image classification)”, 19 May 2019. [Online]. Available: https://towardsdatascience.com/review-mobilenetv2-light-weightmodel-image-classification-8febb490e61c.

M. N. Musa, N. O. Badmos, I. R. Saidu, & U. Abdulrazaq, ”Protective face covering: An application of MobileNetV2 detector”, International Research Journal of Science, Technology, Education, and Management 2 (2022) 1.

L. H. Thai, T. S. Hai & N. T. Thuy, “Image classification using support vector machine and artificial neural network”, International Journal of Information Technology and Computer Science 4 (2012) 32. 8

odion_et_al

Published

2022-08-15

How to Cite

Age Prediction from Sclera Images using Deep Learning. (2022). Journal of the Nigerian Society of Physical Sciences, 4(3), 787. https://doi.org/10.46481/jnsps.2022.787

Issue

Section

Original Research

How to Cite

Age Prediction from Sclera Images using Deep Learning. (2022). Journal of the Nigerian Society of Physical Sciences, 4(3), 787. https://doi.org/10.46481/jnsps.2022.787