An Unsupervised Neural Network Method for Age Group Estimation using Facial Features

  • Matthias Omotayo Oladele The Federal Polytechnic, Ede
  • Elijah Omidiora Ladoke Akintola University of Technology, Ogbomoso
  • Temilola Morufat Adepoju Ladoke Akintola University of Technology, Ogbomoso
Keywords: Age estimation, Facial Features, Unsupervised Neural Network, Principal Component analysis, Self - Organizing Feature Map

Abstract

Age estimation from facial features is an important research subject in the field of face recognition. It is an active research area that can be used in wide range of applications such as surveillance and security, telecommunication and digital libraries, human-computer intelligent interaction, and smart environment. This paper developed an unsupervised neural network by using a Self – Organizing Feature Map (SOFM) to estimate age group from facial features.

The face images were divided into eight different age groups ranging from babies, young teenagers, mid teenagers, teenagers, young adults, mid adults, young old and old and SOFM was used to estimate the age group from the input face image. Principal Component Analysis (PCA) was used to extract the facial features and the extracted features were presented to the SOFM for training and testing. The developed system was experimented with 630 face images with different ages from the FG-NET database. 450 samples were used for training while 180 were used for testing. The results showed a training time of 116.333 seconds and an accuracy of 92.2%.

Author Biographies

Matthias Omotayo Oladele, The Federal Polytechnic, Ede
Computer Engineering and Lecturer
Elijah Omidiora, Ladoke Akintola University of Technology, Ogbomoso
Computer Science and Engineering and Professor

References

(1) Cootes, T., Edwards, G and Taylor, C. (2001), “Active Appearance Models”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 23, No. 6, pp. 681-685.

(2) FGNET (2015), “The FG-NET Aging Database”, [Online]. Available: http://www.fgnet.rsunit.com/, 2015.

(3) Guo Guodong, Mu Guowang, Fu Yun and Huang S. Thomas (2009), “Human Age Estimation Using Bio-inspired Features”, IEEE Conference on Computer Vision and Pattern Recognition, pp.112-119.

(4) Horng, W., Lee, C. and Chen, C. (2001), “Classification of Age Groups Based on Facial Features”, Journal of Science and Engineering, Vol. 4, No. 3, pp. 183-192.

(5) Kwon, Y. H. and Lobo, N. Da Vitoria (1999), “Age classification from facial images”, Computer Vision Image Understanding, Vol. 74, No. 1, pp. 1-21

(6) Nagi Jawad (2007), “Design and Development of an Efficient High-speed Face Recognition System” Final Thesis, College of Engineering, Universiti Tenaga Nasional, Selangor, Malaysia.

(7) Oladele, M.O., Omidiora, E.O., and Afolabi, A.O. (2015), “A Face-based Age Estimation System using Back Propagation Neural Network Technique”, British Journal of Mathematics and Computer Science (In Press).

(8) Omidiora, E.O. (2006), “A Prototype of Knowledge-Based System for Black Face Recognition System using Principal Component Analysis and Fisher Disriminant Algorithms”, Unpublished Ph. D. (Computer Science) Thesis, Ladoke Akintola University of Technology, Ogbomoso,

Nigeria.

(9) Ramesha, K., Raja, K.B., Venugopal, K.R. and Patnaik, L.M. (2010), “Feature Extraction based Face Recognition, Gender and Age Classification” International Journal on Computer Science and

Engineering, Vol. 2, No.1, pp. 14 – 23.

(10) Yang, Z.G. and Ai, H.Z. (2007), “Demographic Classification with Local Binary Pattern”, pp. 464 – 473.

Published
2016-01-03