本論文提出一種基於人臉外觀的人臉年齡辨識的方法。在最近幾年來年齡辨識已逐漸受到重視，許多相關研究與相關應用開始增加，而對電腦視覺領域而言，臉部年齡辨識可以說是一項困難的任務。主要的問題是由於每個人的老化過程受到許多因素影響，產生不同的老化效果，人類外觀往往會受到環境與人為的等各種因素而產生的影響，如健康狀態、生活習慣、工作的環境、遺傳因子、心理情緒(壓力)、疾病、體重急劇變化和暴露在極端的氣候，另外吸菸的行為也會加速外觀老化。
在人臉年齡辨識方面，前人的方法僅單獨考慮使用單一種特徵，但人臉年齡的老化過程，每個年齡階段的外形和紋理變化程度不一。有鑑於此，本論文提出一個以不同特徵對應到不同年齡階段的分類方式。本論文結合了外形特徵，紋理特徵和頻率特徵，分別使用主動外形模型(ASM)，雷登轉換(Radon)，離散餘弦轉換(DCT)等方法，混合多種特徵並進一步進行分類。 在年齡辨識的階段，使用支持向量機(SVM)採用分層分類的架構以及使用支持向量迴歸(SVR)估計年齡。
在實驗結果方面，使用FG-NET的資料庫做為實驗訓練與測試的樣本來源，FG-NET為公開性的資料庫並且在年齡辨識的研究領域中是最常被使用的資料庫之一，資料庫中包含了1002張人臉彩色及灰階影像。將本論文提出的方法與前人的方法做比較，實驗結果顯示出本論文的方法有良好的效果。最後為了應用於現實生活之中，本論文將人臉偵測技術(Adaboost)與人臉年齡辨識架構結合成介面化程式以筆記型電腦、影像擷取卡、PTZ攝影機和RS232傳輸線完成一套人臉年齡辨識介面化程式。

The thesis proposed an approach of human face age estimation based on human appearance. In recent years, face age estimation has raised attentions, and thus relative research and application are derived from that. Yet, it is a challenging issue to classify the age with computer vision. The main problems can be blamed that everybody is suffered from diverse of factors during their aging process, such as health state, working environment, inheritance, pressure, disease, dramatic changes in body weight, exposure in severe climate. In addition, smoking behavior also accelerates the aging process.
Most former researches on human face age estimation simply employ one feature for classification. However, the shapes and textures of faces vary across various stages of age. Consequently, the thesis proposed a method caters different features for the different ranges of age, in which the features of shape, texture characteristics and frequency distributions are considered using Active Shape Model (ASM), Radon conversion, and Discrete Cosine Transform (DCT), respectively. In the identification stage, the Support Vector Machine (SVM), Support Vector Regression (SVR), and the proposed hierarchical classification structure are used for estimatimation.
The well-known FG-NET database is employed as the samples for training and testing in the experiment. The FG-NET is a public and popular database for the research of age estimation, which includes 1002 color and gray human face images. As documented in the experimental results, the proposed scheme provides superior performance than that of the former schemes. Moreover, this study implements a practical system using notebook, video capture card, PTZ camera and RS232 transmission cable to combine the face detection (Adaboost) and the age estimation two fields.

[1] Y. Fu, G. Guo, and T. S. Huang, “Age Synthesis and Estimation via Faces: A Survey,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 32, pp. 1955-1976, Nov. 2010.
[2] T. R. Alley, “Social and Applied Aspects of Perceiving Faces,” Lawrence Erlbaum Associates, Hillsdale, NJ, 1988.
[3] Aaron Stone, The Aging Process of the Face & Techniques of Rejuvenation, http://www.aaronstonemd.com/Facial Aging Rejuvenation.shtm
[4] Aging of the Face, http://www.face-andemotion.com/dataface/facets/aging.jsp
[5] N. Ramanathan and R. Chellappa, “Modeling Age Progression in Young Faces,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 387-394, Jun. 2006.
[6] M. Gonzalez Ulloa and E. Flores, “Senility of the Face: Basic Study to Understand its Causes and Effects,” Plast Reconstr Surg, vol. 36, pp. 239-246, Aug.1965.
[7] Y. H. Kwon and N. da Vitoria Lobo, “Age Classification from facial images,” Computer Vision and Image Understanding, vol. 74, pp. 1-21, Apr. 1999.
[8] R. Iga, K. Izumi, H. Hayashi, G. Fukano, and T. Ohtani, “A Gender and Age Estimation System from Face Images,” SICE Annual Conference, pp. 756-761, Aug. 2003.
[9] H. Takimoto, Y. Mitsukura, M. Fukumi, and N. Akamatsu, “A Design of Gender and Age Estimation System Based on Facial Knowledge,” International Joint Conference on SICE-ICASE, pp. 3883-3886, Oct. 2006.
[10] Y. Fu, Y. Xu, and T. S. Huang, “Estimating Human Ages by Manifold Analysis of Face Pictures and Regression on Aging Features,” IEEE International Conference on Multimedia and Expo, pp. 1383-1386, Jul.2007.
[11] Y. Fu and T. S. Huang, “Human Age Estimation with Regression on Discriminative Aging Manifold,” IEEE Transactions on Multimedia, vol. 10, no. 4, pp. 578-584, Jun. 2008.
[12] S. Yan, H. Wang, X. Tang, and T. S. Huang, “Learning Auto-Structured Regressor from Uncertain Nonnegative Labels,” IEEE 11th International Conference on Computer Vision, pp.1-8, Oct.2007.
[13] G. Guo, Y. Fu, T. S. Huang, and C. Dyer, “A Probabilistic Fusion Approach to Human Age Prediction,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, pp. 1-6, Jun.2008.
[14] K. Luu, K. Ricanek, T.D. Bui and C.Y. Suen, “Age estimation using active appearance models and support vector machine regression,” IEEE Third International Conference on Biometrics: Theory Applications and Systems, pp.1-5, Sep.2009.
[15] T. F. Cootes, G. J. Edwards and C. J. Taylor, “Active appearance models,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23 on. 6, pp. 681–685, Jun.2001.
[16] D. Gabor, “Theory of Communications,” J. Institution of Electrical Engineers, vol. 93, pp. 429-457, 1946.
[17] J. G. Daugman, “Uncertainty Relation for Resolution In Space, Spatial- Frequency, and Orientation Optimized by Two-Dimensional Visual Cortical Filters,” J. Optical Society of America A-Optics Image Science and Vision, vol. 2, pp.1160-1169, 1985.
[18] T. Ojala, M. Pietikäinen and D. Harwood, “A Comparative Study of Texture Measures with Classification Based on Feature Distributions,” Pattern Recognition, vol. 29, no. 1, pp. 51-59, Jan.1996.
[19] T. Ojala, M. Pietikainen and T. Maenpaa, “Multiresolution gray-scale and rotation invariant texture classification with local binary patterns,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 7, pp. 971-987, Jul.2002.
[20] Y. H. Wang, “Automatic age estimation based on local feature of face image and regresion,"2009 International Conference on Machine Learning and Cybernetics, pp. 885 - 888, Jul.2009
[21] M. Y. El Dib, M. El Saban, “Human age estimation using enhanced bio-inspired features (EBIF),” IEEE International Conference on Image Processing, pp. 1589-1592, Sep.2010
[22] G. Guo, G. Mu, Y. Fu, and T. S. Huang, “Human Age Estimation Using Bio-Inspired Features,” IEEE Conference on Computer Vision and Pattern Recognition, pp. 112-119, Jun.2009.
[23] J. D. Txia and C. L. Huang, “Age estimation using AAM and local facial features,” International conference on Intelligent Information Hiding and Multimedia Signal Processing, pp. 885-888, Sep.2009.
[24] P. Viola and M. J. Jones, “Robust real-time object detection,” Second International Workshop on Statistical and Computational Theories of Vision, July.2001.
[25] C. P. Papageorgiou, M. Oren and T. Poggio, “A general framework for object detection,” Sixth International Conference on Computer Vision, pp. 555-562, Jan. 1998.
[26] R. Lienhart, A. Kuranov and V. Pisarevsky, “Empirical analysis of detection cascades of boosted classifiers for rapid object detection,” Pattern Recognition, vol. 2781, pp. 297-304, Sep.2003.
[27] D. H. Kim , S. U. Jung and M. J. Chung, “Extension of cascaded simple feature based face detection to facial expression recognition,” Pattern Recognition Letters, vol. 29, no. 11, pp. 1621-1631, Aug.2008.
[28] Y. Freund and R. E. Schapire, “A decision-theoretic generalization of on-line learning and an application to boosting,” Journal of Computer and System Sciences, vol. 55, no. 1, pp.119-139, Aug.1997.
[29] I. L. Dryden and K. V. Mardia, “Statistical Shape Analysis,” John Wiley & Sons, 1998.
[30] 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.
[31] J. Radon, “Uber die Bestimmung von Functionen durch ihre Integralwerte langs gewisser Mannigfaltikeiten,” Math\Phys. Kl, vol. 69, pp.262 - 267, 1917.
[32] C. Cortes and V. Vapnik, “Support-vector networks,” Machine Learning, vol. 20, no. 3, pp. 273-297,Sep.1995.
[33] B. E. Boser, I. M. Guyon and V. N. Vapnik, “A training algorithm for optimal margin classifiers,” Fifth Annual ACM Workshop on Computational Learning Theory, pp. 144-152, Jul.1992.
[34] V. Vapnik, “Estimation of dependences based on empirical data,” Springer-Verlag New York, 1982.
[35] E. Osuna, R. Freund and F. Girosi, “An improved training algorithm for support vector machines,” IEEE Workshop Neural Networks for Signal Processing, pp. 276-285, Sep.1997.
[36] J. C. Platt, “Fast training of support vector machines using sequential minimal optimization,” Advances in Kernel Methods - Support Vector Learning, pp. 185-208, 1999.
[37] C. C. Chang and C. J. Lin, “LIBSVM : a library for support vector machines,” http://www.csie.ntu.edu.tw/~cjlin/libsvm
[38] The FG-NET Aging Database, http://www.fgnet.rsunit.com/
[39] 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, no. 10, pp. 2604-2609, Oct. 2008.
[40] A. Lanitis, C. Draganova and C. Christodoulou, “Comparing different classifiers for automatic age estimation,” IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, vol. 34, no. 1, pp. 621–628, Feb. 2004.
[41] X. Geng, Z. Zhou, and K. Smith Miles, “Automatic age estimation based on facial aging patterns,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.29, no.12, pp. 2234-2240, Dec. 2007.
[42] S. Yan, H. Wang, T. Huang, Q. Yang and X. T. Xiaoou, “Ranking with Uncertain Labels,” IEEE International Conference on Multimedia and Expo, pp. 96-99, Jul. 2007.