Abstract
In this paper, we propose the novel age estimation system with the real-coded genetic algorithm (RGA) and the neural network (NN). The age is one of important information in our living. There are a lot of studies on age estimation by the computer. However, the conventional method of the age estimation, the most of them are the studies intended for an actual age. Therefore, we pay attention to the mechanism of human age perception. The apparent age feature is extracted by the fourier transform, and the important spectrum for the age perception are selected by the RGA. The age is estimated by the 3 layered NN. It is considered that it can extract important age feature using the RGA and it can analyze the important feature area. In addition, proposed method extracts the age feature at each age. In order to show the effectiveness of the proposed method, we show the simulation examples. From the simulation results, we can confirm that the proposed method works well.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Todd, J.T., Mark, L.S., Shaw, R.E., Pittenger, J.B.: The perception of human growth. Scientific American Perception 242, 106–114 (1980)
Mark, L.S., Pittenger, J.B., Hines, H., Carello, C., Shaw, R.E., Todd, J.T.: Wrinkling and head shape as coordinated sources of age-level information. Perception & Psychophysics 27, 117–124 (1980)
Yamaguchi, M.K., Kato, T., Akamatsu, S.: Relationship between physical traits and subjective impressions of the face - Age and sex information. IEICE Trans. J79-A(2), 279–287 (1996)
Kanno, T., Akiba, M., Teramachi, Y., Nagahashi, H., Agui, T.: Classification of age Group Based on Facial Images of Young Males by Using Neural Networks. IEICE Trans. Inf. & Syst. E84-D(8), 1094–1101 (2001)
Kwon, Y.H., Lobo, N.D.V.: Age classification from facial images. In: CVPR 1994, Seattle, US, June 1994, pp. 762–767 (1994)
Burt, D.M., Perrett, D.I.: Preception of age in adult daudasian male faces: computer graphic manipulation of shape and colour information. Perception 259(1355), 137–143 (1995)
Ueki, K., Hayashida, T., Kobayashi, T.: Subspace-based age-group classification using facial images under various lighting conditions. In: Proc. of IEEE Intl. Conf. on Automatic Face and Gesture Recognition, pp. 43–48 (2006)
Takimoto, H., Mitsukura, Y., Fukumi, M., Akamatsu, N.: A Robust Gender and Age Estimation under Varying Facial Pose. IEEJ Trans. 127(7), 1022–1029 (2007)
Fujiwara, T., Koshimizu, H.: Age and Gender Estimations by Modeling Statistical Relationship among Faces. In: Palade, V., Howlett, R.J., Jain, L. (eds.) KES 2003. LNCS, vol. 2774, pp. 870–876. Springer, Heidelberg (2003)
Nagata, N., Inokuchi, S.: Subjective Age Obtained from Facial Images -How Old We Feel Compared to Others. In: Palade, V., Howlett, R.J., Jain, L. (eds.) KES 2003. LNCS, vol. 2774, pp. 877–881. Springer, Heidelberg (2003)
George, P.A., Hole, G.J.: Factors influencing the accuracy of age estimates of unfamiliar faces. Perception 24(1), 1059–1073 (1995)
Kawato, S., Tetsutani, N.: Circle-Frequency Filter and its Application. In: Proc. Int. Workshop on Advanced Image Technology, pp. 217–222
Kawaguchi, T., Hikada, D., Rizon, M.: Detection of the eyes from human faces by hough transform and separability filter. In: Proc. of ICIP 2000, pp. 49–52 (2000)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Fukai, H., Takimoto, H., Mitsukura, Y., Fukumi, M. (2008). Feature Extraction System for Age Estimation. In: Lovrek, I., Howlett, R.J., Jain, L.C. (eds) Knowledge-Based Intelligent Information and Engineering Systems. KES 2008. Lecture Notes in Computer Science(), vol 5178. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-85565-1_57
Download citation
DOI: https://doi.org/10.1007/978-3-540-85565-1_57
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-85564-4
Online ISBN: 978-3-540-85565-1
eBook Packages: Computer ScienceComputer Science (R0)