本研究探討性別導向之人臉年齡估測。在年齡估測的研究中，討論性別導向之年齡估測文獻極少，而現有文獻對於性別導向之年齡估測目前只運用於YGA資料庫上，對於性別造成年齡估測影響的測試略為不足，故本研究將此概念運用至兩個公開資料庫FG-NET和MORPH。年齡估測相關文獻中曾提到不同族群的年齡特徵可能可以相互應用，但提出此應用之文獻取樣極為不足，故本論文將FG-NET和MORPH進行跨種族的效能比較。為增加研究價值，本論文提出了如何利用社群網站快速而準確的蒐集具有區域特性之人臉資料庫，並參與性別導向與跨種族的實驗。
本論文主要探討兩個重點：(1)性別導向之年齡估測應用於不同資料庫；(2)對FG-NET、MORPH和自行蒐集的年齡資料庫進行跨種族的效能比較。首先假設影像中受測者之性別為已知，利用遮罩式Gabor濾波器進行性別導向的特徵擷取，此濾波器的參數除了常見的方向(orientation)與尺寸(scale)外，增加了大小可改變的遮罩視窗，大幅增加濾波器輸出的特徵之變化性。並利用離散餘旋轉換(Discrete Cosine Transform：DCT)進行特徵降維，以Adaboost演算法挑出可助益年齡估測之特徵，再由支持向量機(Support Vector Machine：SVM)進行性別導向之年齡群組分類。為增加實用價值，本研究並結合一性別分類器，以達自動年齡估測之效能。

It is recently proven that face-based age estimation can be improved if the gender of the face is known. Given the gender of a face, the estimation of the age of the face is called Gender-Oriented Age Estimation (GOAE). Few works are available as references on GOAE, and this thesis is dedicated to deepening our understanding in this regard by proposing an algorithm for GOAE. Unlike the few previous works that verify the performance on the YGA database, which is not publically accessible, this work selects the public databases, the FG-NET and MORPH, for performance evaluation.
Given a training set, the proposed algorithm first extracts the low frequency parts of the masked Gabor features, and selects the age-related components by an AdaBoost scheme to train an SVM classifier. It is proven in our experiments that the proposed algorithm yields a performance competitive to the state-of-the-art approaches. Because of the ethnic differences between the FG-NET and MORPH, it is also experimentally proven that the age estimation is better undertaken within the same ethnic group. The age features from one ethnic group can substantially downgrade the performance when used to estimate the age of a different ethnic group. To efficiently collect a good scope of samples of the same ethnic group, a social network is exploited for the first time to meet the requirements.

參考文獻
[1] G. Guo, G. Mu, Y. Fu, C. Dyer, and T.S. Huang, “A Study on Automatic Age Estimation Using a Large Database,” Proc. IEEE Conf. Computer Vision, pp.1986-1991, Sept. 29 2009-Oct. 2 2009.
[2] S. Yan, D. Xu, B. Zhang, H. Zhang, Q. Yang, and S. Lin, “Graph Embedding and Extension: A General Framework for Dimensionality Reduction,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 29, no. 1, pp. 40-51, Jan. 2007.
[3] D. Cai, X. He, K. Zhou, J. Han, and H. Bao, “Locality Sensitive Discriminant Analysis,” Proc. 20th Int’l Joint Conf. Artificial Intelligence, pp. 708–713, Jan. 2007.
[4] D. Cai, X. He, J. Han, and H.-J. Zhang, “Orthogonal Laplacianfaces for Face Recognition,” IEEE Trans. Image Processing, vol. 15, no. 11, pp. 3608-3614, Nov. 2006.
[5] A. R. Webb. Statistical Pattern Recognition, 2nd Edition. John Wiley, 2002.
[6] G. Guo, G. Mu, Y. Fu, and T.S. Huang, “Human Age Estimation Using Bio Inspired Features,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp.112-119, 20-25 June 2009.
[7] X. Geng, Z.-H. Zhou, Y. Zhang, G. Li, and H. Dai, “Learning from Facial Aging Patterns for Automatic Age Estimation,” Proc. ACM Conf. Multimedia, pp. 307-316, 2006.
[8] S. Yan, H. Wang, T.S. Huang, and X. Tang, “Ranking with Uncertain Labels,” Proc. IEEE Conf. Multimedia and Expo, pp. 96-99, 2-5 July 2007.
[9] G. Guo, Y. Fu, C. Dyer, and T.S. Huang, “Image-Based Human Age Estimation by Manifold Learning and Locally Adjusted Robust Regression,” IEEE Trans. Image Processing, vol. 17, no. 7, pp. 1178-1188, July 2008.
[10] G. Guo, Y. Fu, T.S. Huang, and C. Dyer, “A Probabilistic Fusion Approach to Human Age Prediction,” Proc. IEEE Computer Vision and Pattern Recognition–Semantic Learning and Applications in Multimedia Workshop, pp.1-6, 23-28 June 2008.
[11] S. Yan, X. Zhou, M. Liu, M. Hasegawa-Johnson, and T.S. Huang, “Regression from Patch-Kernel,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp.1-8, 23-28 June 2008.
[12] Y. Fu, G. Guo, and T.S. Huang, “Age Synthesis and Estimation via Faces: A Survey,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol.32, no.11, pp.1955-1976, Nov. 2010.
[13] M. Riesenhuber and T. Poggio, “Hierarchical Models of Object Recognition in Cortex,” Nature Neuroscience, vol. 2, no. 11, pp. 1019-1025, 1999.
[14] T. Serre, L. Wolf, S. Bileschi, M. Riesenhuber, and T. Poggio, “Robust Object Recognition with Cortex-Like Mechanisms,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 29, no. 3, pp. 411-426, Mar. 2007.
[15] A. Stone, The Aging Process of the Face & Techniques of Rejuvenation, http://www.aaronstonemd.com/Facial_Aging_Rejuvenation.shtm, 2010.
[16] M. Gonzalez-Ulloa and E. Flores, “Senility of the Face: Basic Study to Understand Its Causes and Effects,” Plastic and Reconstructive Surgery, vol. 36, pp. 239-246, 1965.
[17] J.T. Todd, S.M. Leonard, R.E. Shaw, and J.B. Pittenger, “The Perception of Human Growth,” Scientific Am., vol. 242, no. 2, pp. 106-114, 1980.
[18] N. Ramanathan and R. Chellappa, “Modeling Age Progression in Young Faces,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 387-394, 17-22 June 2006.
[19] V. Bruce, M. Burton, T. Doyle, and N. Dench, “Further Experiments on the Perception of Growth in Three Dimensions,” Perception and Psychophysics, vol. 46, no. 6, pp. 528-36, 1989.
[20] Y. Kwon and N. Lobo, “Age Classification from Facial Images,” Computer Vision and Image Understanding, vol. 74, no. 1, pp. 1-21, 1999.
[21] M. Kass, A. Witkin, and D. Terzopoulos, “Snakes: Active Contour Models,” Proc. First IEEE Int’l Conf. Computer Vision, pp. 259-269, 1987.
[22] A. Lanitis, C. Draganova, and C. Christodoulou, “Comparing Different Classifiers for Automatic Age Estimation,” IEEE Trans. Systems, Man, and Cybernetics Part B, vol. 34, no. 1, pp. 621-628, Feb. 2004.
[23] T.F. Cootes, D. Cooper, C.J. Taylor, and J. Graham, “Active Shape Models—Their Training and Application,” Computer Vision and Image Understanding, vol. 61, no. 1, pp. 38-59, Jan. 1995.
[24] X. Geng, Z.-H. Zhou, and K. Smith-Miles, “Automatic Age Estimation Based on Facial Aging Patterns,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 29, no. 12, pp. 2234-2240, Dec. 2007.
[25] Y. Fu, Y. Xu, and T.S. Huang, “Estimating Human Age by Manifold Analysis of Face Pictures and Regression on Aging Features,” Proc. IEEE Conf. Multimedia and Expo, pp. 1383-1386, 2007.
[26] Y. Fu and T.S. Huang, “Human Age Estimation with Regression on Discriminative Aging Manifold,” IEEE Trans. Multimedia, vol. 10, no. 4, pp. 578-584, June 2008.
[27] D. V. Jadhav and R. S. Holambe, “Radon and Discrete Cosine Transforms Based Feature Extraction and Dimensionality Reduction Approach for Face Recognition,” Signal Processing, vol. 88, pp. 2604-2609, Oct. 2008.
[28] J.-M. Guo, Y.-M. Liou and H.-S. Nguyen, "Human Face Age Estimation with Adaptive Hybrid Features", Proc. IEEE Conf. System Science and Engineering, pp.55-58, 8-10 June 2011.
[29] G. Mahalingam, C. Kambhamettu , "Can Discriminative Cues Aid Face Recognition Across Age?," Proc. IEEE Conf. Automatic Face & Gesture Recognition and Workshops, pp.206-212, 21-25 Mar. 2011.
[30] J. Lu and Y.-P. Tan, "Gait-Based Human Age Estimation," Proc. IEEE Conf. Acoustics Speech and Signal Processing, pp.1718-1721, 14-19 Mar. 2010.
[31] M.Y. El Dib and M. El-Saban, "Human Age Estimation Using Enhanced Bio-Inspired Features (EBIF)," Proc. IEEE Conf. Image Processing, pp.1589-1592, 26-29 Sept. 2010.
[32] L. Shen and L. Bai, “Adaboost Gabor Feature Selection for Classification,” Proc. of Image and Vision Computing New Zealand, 2004.
[33] N. Ahmed, T. Natarajan and K.R. Rao , "Discrete Cosine Transform," IEEE Trans, Computers, vol.C-23, no.1, pp.90-93, Jan. 1974.
[34] J. Zhu, S. Rosset, H. Zou, and T. Hastie. Multi-class AdaBoost. Statistics & its interface, vol. 2, pp.349-360, 2009.
[35] The FG-NET Aging Database, http://www.fgnet.rsunit.com/, http://www-prima.inrialpes.fr/FGnet/, 2010.
[36] K. Ricanek and T. Tesafaye, “MORPH: A Longitudinal Image Database of Normal Adult Age-Progression,” Proc. IEEE Int’l Conf. Automatic Face and Gesture Recognition, pp. 341-345, 2-6 April 2006.
[37] MORPH Face Database, http://faceaginggroup.com/, 2010.
[38] X. Tan and B. Triggs. “Enhanced Local Texture Feature Sets for Face Recognition under Difficult Lighting Conditions,” IEEE Trans. Image Processing, vol.19, no.6, pp.1635-1650, June 2010.
[39] B. Ni, Z. Song, and S. Yan, “Web Image Mining Towards Universal Age Estimator,” Proc. ACM Multimedia, pp.85-94, 2009.
[40] Cortes, Corinna; and Vapnik, Vladimir N.; "Support-Vector Networks", Machine Learning, vol.20, no.3, pp. 273-297, Sep. 1995.
[41] C.-C. Chang and C.-J. Lin, “LIBSVM : a library for support vector machines,” 2001. Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm
[42] Z. Ji, X. Lian, and B. Lu, “Gender classification by information fusion of hair and face,” in State of the Art in Face Recognition. Vienna, Austria: IN-TECH, 2009.
[43] W. Gao, B. Cao, S. Shan, X. Chen, D. Zhou, X. Zhang and D. Zhao, "The CAS-PEAL Large-Scale Chinese Face Database and Baseline Evaluations," IEEE Trans. Systems, Man and Cybernetics, Part A: Systems and Humans, vol.38, no.1, pp.149-161, Jan. 2008.
[44] D. Comaniciu and P. Meer, “Mean Shift: A Robust Approach Toward Feature Space Analysis,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol.24, no.5, pp.603-619, May 2002.
[45] T. Ojala, M. Pietikainen and T. Maenpaa, "Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns," IEEE Trans. Pattern Analysis and Machine Intelligence , vol.24, no.7, pp.971-987, July 2002.
[46] Race: http://en.wikipedia.org/wiki/Race_(human_classification)