Comparative Evaluation on Supervised Learning Based Age Estimation
Keywords:
Convolutional Neural Network, Local binary Pattern, Local Phase Quantization, Gabor Filter, Support Vector RegressionAbstract
Facial age estimation has got more consideration in the area of computer vision for the past few years. Age estimation is a troublesome task since the distinction between facial pictures with age variations is difficult. In this work, we analyze the problem of age prediction by means of SVR Model and deep learning technique. This paper attempts to find out the efficiency of SVR and Convolution neural network (CNN) on age estimation. Local features such as wrinkles and texture are extracted using Gabor filter, Local Binary Pattern (LBP) and Local Phase Quantization (LPQ). The three features are combined together and the dimension of the feature vector is reduced using Principle Component Analysis. Support Vector Regression (SVR) is utilized to predict the age of an individual. In CNN, the datasets are fine-tuned utilizing the pre-trained VGG-16 model which can group pictures into 1000 categories. The experimental results on the IMDB-WIKI dataset, the ICCV datasets and MORPH 2 dataset shows that CNN outperforms the local feature based SVR model in predicting the age
References
[1] Maximilian, Riesen huber and Tomaso Poggio (1999),”Hierarchical models of object recognition in cortex”, Nature neuroscience, vol. 2, no. 11, pp. 1019–1025.
[2] XinGeng, Chao Yin, and Zhi-Hua Zhou (2013), ‘’Facial age estimation by learning from label distributions’’, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 35,no.10, pp. 2401–2412.
[3] Hu Han, Charles Otto, and Anil K Jain (2013),” Age estimation from face images: Human vs. machine performance”, In International Conference on Biometrics (ICB). IEEE, pp.1-8.
[4] Wen-Bing Horng, Cheng-Ping Lee and Chun-Wen Chen (2001),“Classification of Age Groups Based on Facial Features”, Tamkang Journal of Science and Engineering, vol.4, no.3, pp.183-192.
[5] J. Suo, Min Feng, S. Zhu, S. Shan, X. Chen (2007), “A multi-resolution dynamic model for face aging simulation”, Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, pp. 1-8.
[6] Z. J. Xu, H.Chen, and S. C. Zhu (2005),“A high resolution grammatical model for face representation and sketching”. IEEE CVPR, pp: 470-477.
[7] J. Hayashi, M. Yasumoto, H. Ito, Y. Niwa, and H. Koshimizu (2002), ‘’Age and Gender Estimation from Facial Image Processing’’, the41st SICE Annual Conference, vol. 1, pp. 13 -18, Aug.
[8] K. Ricanek , Y. Wang , C. Chen , S. J. Simmons (2009) “Generalized multi-ethnic face age-estimation”, in Biometrics: Theory, Applications, and Systems, 2009. BTAS’09. IEEE 3rd International Conference on. IEEE, pp. 1-6.
[9] Wen – bingHorng, cheng-Ping Lee and chun-Wen chen (2001),”classification of age groups based on facial feature”, Journal of Science and Engineering, vol. 4, no.3, pp.183-192.
[10] Y. Kwon and N. Da Vitoria Lobo (1999), “Age classification from facial images” Computer vision and image understanding, vol. 74, no. 1, pp.1–21.
[11] A. Lanitis, C. Draganova, and C. Christodoulou (2004), “Comparing different classifiers for automatic age estimation”. In Proceedings of. IEEE Transactions on SMC-B, vol. 34, no.1, pp. 621-628.
[12] A. Lanitis, C. Taylor, T. Cootes (2002), “Toward Automatic Simulation of Aging Effects on Face Images”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 4, pp. 442-455.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.
