A Recursive Binary Tree Method for Age Classification of Child Faces

Full Text (PDF, 889KB), PP.56-66

Views: 0 Downloads: 0


Olufade F. W. Onifade 1,* Joseph D. Akinyemi 1 Olashile S. Adebimpe 1

1. Department of Computer Science, University of Ibadan, Ibadan, Nigeria

* Corresponding author.

DOI: https://doi.org/10.5815/ijmecs.2016.10.08

Received: 15 Jun. 2016 / Revised: 16 Jul. 2016 / Accepted: 2 Sep. 2016 / Published: 8 Oct. 2016

Index Terms

Age classification, recursive classification, local binary pattern, support vector machine, machine learning, image processing


This paper proposes an intuitive approach to facial age classification on child faces – a recursive multi-class binary classification tree – using the texture information obtained from facial images. The face area is divided into small regions from which Local Binary Pattern (LBP) histograms were extracted and concatenated into a single vector efficiently representing a facial image. The classification is based on training a set of binary classifiers using Support Vector Machines (SVMs). Each classifier estimates whether the facial image belongs to a specified age range or not until the last level of the tree is reached where the age is finally determined. Our classification approach also includes an overlapping function that resolves overlaps and conflicts in the outputs of two mutually-exclusive classifiers at each level of the classification tree. Our proposed approach was experimented on a publicly available dataset (FG-NET) and our locally obtained dataset (FAGE) and the results obtained are at par with those of existing works.

Cite This Paper

Olufade F.W. Onifade, Joseph D. Akinyemi, Olashile S. Adebimpe, "A Recursive Binary Tree Method for Age Classification of Child Faces", International Journal of Modern Education and Computer Science(IJMECS), Vol.8, No.10, pp.56-66, 2016. DOI: 10.5815/ijmecs.2016.10.08


[1]A. K. Jain, L. Hong, and S. Pankanti, “Biometric Identification,” Commun. ACM, vol. 43, no. 2, pp. 91–98, 2000.
[2]A. K. Jain and A. Ross, “Introduction to Biometrics,” in Handbook of Biometrics, A. K. Jain, P. J. Flynn, and A. Ross, Eds. Springer, 2008, pp. 1–22.
[3]O. F. W. Onifade and K. T. Bamigbade, “GEHE: A Multifactored Model of Soft and Hard Biometric Trait for Ease of Retrieval,” in International Conference on Biometric Security and Multimedia, 2014, pp. 1–5.
[4]“FG-NET,” 2013. [Online]. Available: http://www.sting.cycollege.ac.cy/~alanitis/fgnetaging/index.htm. [Accessed: 17-Jun-2013].
[5]O. F. W. Onifade and J. D. Akinyemi, “GWAgeER – A GroupWise Age Ranking Framework for Human Age Estimation,” Int. J. Image Graph. Signal Process., vol. 7, no. 5, pp. 1–12, 2015.
[6]Y. H. Kwon and V. Lobo, “Age Classification from Facial Images,” Comput. Vis. Image Underst., vol. 74, no. 1, pp. 1–21, 1999.
[7]W. Horng, C. Lee, and C. Chen, “Classification of Age Groups Based on Facial Features,” Tamkang J. Sci. Eng., vol. 4, no. 3, pp. 183–192, 2001.
[8]N. Ramanathan and R. Chellappa, “Modeling Shape and Textural Variations in Aging Faces,” 2008 8Th Ieee Int. Conf. Autom. Face Gesture Recognit. (Fg 2008), Vols 1 2, pp. 1006–1013, 2008.
[9]N. Ramanathan and R. Chellappa, “Modeling age progression in young faces,” in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2006, vol. 1, pp. 387–394.
[10]A. Lanitis, C. Draganova, and C. Christodoulou, “Comparing Different Classifiers for Automatic Age Estimation,” IEEE Trans. Syst. Man, Cybern. Part B Cybern., vol. 34, no. 1, pp. 621–628, 2004.
[11]A. Lanitis, C. J. Taylor, and T. F. Cootes, “Toward automatic simulation of aging effects on face images,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 24, no. 4, pp. 442–455, 2002.
[12]K. Ricanek, Y. Wang, C. Chen, and S. J. Simmons, “Generalized Multi-Ethnic Face Age-Estimation,” in IEEE 3rd International Conference on Biometrics: Theory, Applications and Systems, BTAS 2009, 2009.
[13]K. Luu, K. Ricanek, T. D. Bui, and C. Y. Suen, “Age Estimation using Active Appearance Models and Support Vector Machine Regression,” in IEEE International Conference on Biometrics: Theory, Applications and System, 2009, pp. 314–318.
[14]S. Yan, X. Zhou, M. Hasegawa-johnson, and T. S. Huang, “Regression from Patch-Kernel,” in IEEE Conference on Computer Vision and Pattern Recognition, 2008, pp. 1–8.
[15]J. Suo, T. Wu, S. Zhu, S. Shan, X. Chen, and W. Gao, “Design sparse features for age estimation using hierarchical face model,” in 2008 8th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2008, 2008, pp. 1–6.
[16]F. Gao and H. Ai, “Face age classification on consumer images with gabor feature and fuzzy lda method,” in Advances in biometrics, 2009, pp. 132–141.
[17]G. Guo, G. Mu, Y. Fu, and T. S. Huang, “Human Age Estimation Using Bio-inspired Features,” in IEEE Conference on Computer Vision and Pattern Recognition, 2009, pp. 112–119.
[18]X. Geng, K. Smith-miles, and Z. Zhou, “Facial Age Estimation by Nonlinear Aging Pattern Subspace,” in 16th ACM international conference on Multimedia, 2008, pp. 1–4.
[19]K. Chang, C. Chen, and Y. Hung, “A Ranking Approach for Human Age Estimation Based on Face,” in International Conference on Pattern Recognition, 2010, pp. 3396–3399.
[20]K. Chang, C. Chen, and Y. Hung, “Ordinal Hyperplanes Ranker with Cost Sensitivities for Age Estimation,” in IEEE Conference on Computer Vision and Pattern Recognition, 2011, pp. 585 – 592.
[21]D. Cao, Z. Lei, Z. Zhang, J. Feng, and S. Z. Li, “Human Age Estimation Using Ranking SVM,” in 7th Chinese Conference, CCBR, 2012, vol. 7701, pp. 324–331.
[22]O. F. W. Onifade and J. D. Akinyemi, “A GW Ranking Approach for Facial Age Estimation,” Egypt. Comput. Sci. J., vol. 38, no. 3, pp. 63–74, 2014.
[23]Z. Cao, T. Qin, T.-Y. Liu, M.-F. Tsai, and H. Li, “Learning to Rank : From Pairwise Approach to Listwise Approach,” in 24th International Conference on Machine Learning, 2007, pp. 1–8.
[24]T. Qin, X.-D. Zhang, M.-F. Tsai, D.-S. Wang, T.-Y. Liu, and H. Li, “Query-level loss functions for information retrieval,” Inf. Process. Manag., vol. 44, no. 2, pp. 838–855, Mar. 2008.
[25]F. Xia, T.-Y. Liu, J. Wang, W. Zhang, and H. Li, “Listwise approach to learning to rank,” in Proceedings of the 25th International Conference on Machine Learning - ICML ’08, 2008, pp. 1192–1199.
[26]J. Liu, Y. Ma, L. Duan, F. Wang, and Y. Liu, “Hybrid constraint SVR for facial age estimation,” Signal Processing, vol. 94, no. 2014, pp. 576–582, Jan. 2014.
[27]W. Chao, J. Liu, and J. Ding, “Facial age estimation based on label-sensitive learning and age-oriented regression,” Pattern Recognit., vol. 46, no. 3, pp. 628–641, 2013.
[28]P. X. Gao, “Facial age estimation using Clustered Multi-task Support Vector Regression Machine,” in Proceedings - International Conference on Pattern Recognition, 2012, pp. 541–544.
[29]K. Luu, K. Seshadri, M. Savvides, T. D. Buil, and C. Y. Suenl, “Contourlet Appearance Model for Facial Age Estimation,” in International Joint Conference on Biometrics, 2011, pp. 1–8.
[30]M. Y. ElDib and H. M. Onsi, “Human age estimation framework using different facial parts,” Egypt. Informatics J., vol. 12, no. 1, pp. 53–59, 2011.
[31]K. Ricanek and T. Tesafaye, “MORPH: A Longitudinal Image Database of Normal Adult Age-Progression,” in In IEEE 7th International Conference on Automatic Face and Gesture Recognition, 2006, pp. 341–345.
[32]A. Lanitis, “On the significance of different facial parts for automatic age estimation,” 14th Int. Conf. Digit. Signal Process. Proceedings. DSP 2002 (Cat. No.02TH8628), vol. 2, no. 14, pp. 27–30, 2002.
[33]T. Ojala, M. Pietikäinen, and D. Harwood, “A comparative study of texture measures with classification based on featured distributions,” Pattern Recognit., vol. 29, no. 1, pp. 51–59, 1996.
[34]T. Ahonen, A. Hadid, and M. Pietikäinen, “Face description with local binary patterns: Application to face recognition,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 28, no. 12, pp. 2037–2041, 2006.
[35]T. Ojala, M. Pietikäinen, and T. Mäenpää, “Multiresolution gray-scale and rotation invariant texture classification with local binary patterns,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 24, no. 7, pp. 971–987, 2002.
[36]V. N. Vapnik, The Nature of Statistical Learning Theory, 1st ed. New York: Springer-Verlag, 1995.
[37]C. Chih-Chung and L. Chih-Jen, “LIBSVM: A library for support vector machines,” in IEEE International Conference on Computer Vision and Pattern Recognition, 2001, pp. 387–394.
[38]J. D. Akinyemi, “GWAgeER; A GroupWise Age-Ranking Approach to Age Estimation from Still Facial Image,” University of Ibadan, Ibadan, 2014.