近年來，由於社交平台的興起，越來越多的人開始進行人臉分析的研究。人臉屬性中的年齡和性別均是影響社交互動的基本元素。目前在受限環境中之人臉性別與年齡判斷的研究結果良好且正確率幾乎已達飽和，但是在非限制環境下的判別則仍然具有挑戰性。本文提出了一個兩階段的分類器。首先，利用一個於人臉辨識的大數據集上預先訓練的深度卷積神經網絡（CNN）作為初始模型，接著在較小的數據集上對該模型進行遷移學習，微調其參數。此訓練好的CNN模型不直接用於分類，而是做為特徵提取器。取出特徵後，再訓練隨機森林以進行分類。本文採用Adience benchmark數據集做性別與年齡分類，並於Label Faces in the Wild（LFW）數據集做性別分類以驗證所提出的方法。實驗結果顯示，此二階段分類器的使用相對於僅使用CNN分類的方法有更優的判別力。

Recently, due to the rise of social platforms, more and more people start focusing on the analysis of human's face. Age and gender are two of the facial attributes that plays fundamental roles in social interactions. Although the performance of classifying age and gender in constrained face images is fine and almost saturated, the tasks of uncontrolled images remain challenging. In this thesis, a two-stage classifier is proposed. First, a deep convolutional neural network (CNN) pretrained on a massive dataset for face identification is used as the initial model. The model is then fine-tuned on smaller datasets. Instead of directly performing classification, the model acts as a feature extractor. After obtaining the feature, random forest is applied for the final classification.
The method is evaluated on the Adience benchmark for age and gender estimation and on the Labeled Faces in the Wild (LFW) dataset for gender estimation. It shows that our method outperforms the methods that use only CNN for classification.

[1]I. Ullah, M. Hussain, G. Muhammad, H. Aboalsamh, G. Bebis, and A. M. Mirza, "Gender recognition from face images with local wld descriptor," in Systems, Signals and Image Processing (IWSSIP), 2012 19th International Conference on, 2012, pp. 417-420: IEEE.
[2]Y. H. Kwon, "Age classification from facial images," in Computer Vision and Pattern Recognition, 1994. Proceedings CVPR'94., 1994 IEEE Computer Society Conference on, 1994, pp. 762-767: IEEE.
[3]N. Ramanathan and R. Chellappa, "Modeling age progression in young faces," in Computer Vision and Pattern Recognition, 2006 IEEE Computer Society Conference on, 2006, vol. 1, pp. 387-394: IEEE.
[4]G. Guo, Y. Fu, C. R. Dyer, and T. S. Huang, "Image-based human age estimation by manifold learning and locally adjusted robust regression," IEEE Transactions on Image Processing, vol. 17, no. 7, pp. 1178-1188, 2008.
[5]A. Lanitis., "The FG-NET aging database," ed, 2002.
[6]K. Ricanek and T. Tesafaye, "Morph: A longitudinal image database of normal adult age-progression," in Automatic Face and Gesture Recognition, 2006. FGR 2006. 7th International Conference on, 2006, pp. 341-345: IEEE.
[7]S. Yan, M. Liu, and T. S. Huang, "Extracting age information from local spatially flexible patches," in Acoustics, Speech and Signal Processing, 2008. ICASSP 2008. IEEE International Conference on, 2008, pp. 737-740: IEEE.
[8]K. Fukunaga, Introduction to statistical pattern recognition. Academic press, 2013.
[9]C. Liu and H. Wechsler, "Gabor feature based classification using the enhanced fisher linear discriminant model for face recognition," IEEE Transactions on Image processing, vol. 11, no. 4, pp. 467-476, 2002.
[10]T. Ahonen, A. Hadid, and M. Pietikainen, "Face description with local binary patterns: Application to face recognition," IEEE transactions on pattern analysis and machine intelligence, vol. 28, no. 12, pp. 2037-2041, 2006.
[11]F. Gao and H. Ai, "Face age classification on consumer images with gabor feature and fuzzy lda method," in International Conference on Biometrics, 2009, pp. 132-141: Springer.
[12]S. E. Choi, Y. J. Lee, S. J. Lee, K. R. Park, and J. Kim, "Age estimation using a hierarchical classifier based on global and local facial features," Pattern Recognition, vol. 44, no. 6, pp. 1262-1281, 2011.
[13]C. Cortes and V. Vapnik, "Support-vector networks," Machine learning, vol. 20, no. 3, pp. 273-297, 1995.
[14]W.-L. Chao, J.-Z. Liu, and J.-J. Ding, "Facial age estimation based on label-sensitive learning and age-oriented regression," Pattern Recognition, vol. 46, no. 3, pp. 628-641, 2013.
[15]E. Eidinger, R. Enbar, and T. Hassner, "Age and gender estimation of unfiltered faces," IEEE Transactions on Information Forensics and Security, vol. 9, no. 12, pp. 2170-2179, 2014.
[16]L. Wolf, T. Hassner, and Y. Taigman, "Descriptor based methods in the wild," in Workshop on faces in'real-life'images: Detection, alignment, and recognition, 2008.
[17]B. A. Golomb, D. T. Lawrence, and T. J. Sejnowski, "Sexnet: a neural network identifies sex from human faces," in NIPS, 1990, vol. 1, p. 2.
[18]B. Moghaddam and M.-H. Yang, "Learning gender with support faces," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 5, pp. 707-711, 2002.
[19]S. Baluja and H. A. Rowley, "Boosting sex identification performance," International Journal of computer vision, vol. 71, no. 1, pp. 111-119, 2007.
[20]N. Sun, W. Zheng, C. Sun, C. Zou, and L. Zhao, "Gender classification based on boosting local binary pattern," in International Symposium on Neural Networks, 2006, pp. 194-201: Springer.
[21]J.-G. Wang, J. Li, W.-Y. Yau, and E. Sung, "Boosting dense SIFT descriptors and shape contexts of face images for gender recognition," in Computer Vision and Pattern Recognition Workshops (CVPRW), 2010 IEEE Computer Society Conference on, 2010, pp. 96-102: IEEE.
[22]Z. Yang, M. Li, and H. Ai, "An experimental study on automatic face gender classification," in Pattern Recognition, 2006. ICPR 2006. 18th International Conference on, 2006, vol. 3, pp. 1099-1102: IEEE.
[23]J. Chen et al., "WLD: A robust local image descriptor," IEEE transactions on pattern analysis and machine intelligence, vol. 32, no. 9, pp. 1705-1720, 2010.
[24]P. J. Phillips, H. Wechsler, J. Huang, and P. J. Rauss, "The FERET database and evaluation procedure for face-recognition algorithms," Image and vision computing, vol. 16, no. 5, pp. 295-306, 1998.
[25]C. Perez, J. Tapia, P. Estévez, and C. Held, "Gender classification from face images using mutual information and feature fusion," International Journal of Optomechatronics, vol. 6, no. 1, pp. 92-119, 2012.
[26]C. Shan, "Learning local binary patterns for gender classification on real-world face images," Pattern Recognition Letters, vol. 33, no. 4, pp. 431-437, 2012.
[27]E. Learned-Miller, G. B. Huang, A. RoyChowdhury, H. Li, and G. Hua, "Labeled faces in the wild: A survey," in Advances in Face Detection and Facial Image Analysis: Springer, 2016, pp. 189-248.
[28]A. Krizhevsky, I. Sutskever, and G. E. Hinton, "Imagenet classification with deep convolutional neural networks," in Advances in neural information processing systems, 2012, pp. 1097-1105.
[29]G. Levi and T. Hassner, "Age and gender classification using convolutional neural networks," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2015, pp. 34-42.
[30]G. Antipov, S.-A. Berrani, and J.-L. Dugelay, "Minimalistic CNN-based ensemble model for gender prediction from face images," Pattern recognition letters, vol. 70, pp. 59-65, 2016.
[31]K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition," arXiv preprint arXiv:1409.1556, 2014.
[32]O. M. Parkhi, A. Vedaldi, and A. Zisserman, "Deep Face Recognition," in BMVC, 2015, vol. 1, no. 3, p. 6.
[33]A. Krizhevsky and G. Hinton, "Learning multiple layers of features from tiny images," 2009.
[34]D. T. Larose, "k‐Nearest Neighbor Algorithm," Discovering Knowledge in Data: An Introduction to Data Mining, pp. 90-106, 2005.
[35]A. Y. Ng and M. I. Jordan, "On discriminative vs. generative classifiers: A comparison of logistic regression and naive bayes," Advances in neural information processing systems, vol. 2, pp. 841-848, 2002.
[36]J. Snyman, Practical mathematical optimization: an introduction to basic optimization theory and classical and new gradient-based algorithms. Springer Science & Business Media, 2005.
[37]L. Breiman, "Random forests," Machine learning, vol. 45, no. 1, pp. 5-32, 2001.
[38]K. Fukushima and S. Miyake, "Neocognitron: A new algorithm for pattern recognition tolerant of deformations and shifts in position," Pattern recognition, vol. 15, no. 6, pp. 455-469, 1982.
[39]Y. LeCun et al., "Handwritten digit recognition with a back-propagation network," in Advances in neural information processing systems, 1990, pp. 396-404.
[40]A. L. Maas, A. Y. Hannun, and A. Y. Ng, "Rectifier nonlinearities improve neural network acoustic models," in Proc. ICML, 2013, vol. 30, no. 1.
[41]N. Srivastava, G. E. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, "Dropout: a simple way to prevent neural networks from overfitting," Journal of Machine Learning Research, vol. 15, no. 1, pp. 1929-1958, 2014.
[42]Y. Jia et al., "Caffe: Convolutional architecture for fast feature embedding," in Proceedings of the 22nd ACM international conference on Multimedia, 2014, pp. 675-678: ACM.
[43]P. Viola and M. Jones, "Rapid object detection using a boosted cascade of simple features," in Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on, 2001, vol. 1, pp. I-I: IEEE.
[44]A. C. Gallagher and T. Chen, "Understanding images of groups of people," in Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on, 2009, pp. 256-263: IEEE.
[45]B. Breiman, F. Leo, O. Jerome-H, and S. Richard-A, "Classification and regression trees," 1998.
[46]FIPA. (2011). Folds for gender evaluation on LFW. Available: http://fipa.cs.kit.edu/download/LFW-gender-folds.dat
[47]S. Jia and N. Cristianini, "Learning to classify gender from four million images," Pattern Recognition Letters, vol. 58, pp. 35-41, 2015.
[48]G. Huang, M. Mattar, H. Lee, and E. G. Learned-Miller, "Learning to align from scratch," in Advances in Neural Information Processing Systems, 2012, pp. 764-772.
[49]R. Kohavi, "A study of cross-validation and bootstrap for accuracy estimation and model selection," in Ijcai, 1995, vol. 14, no. 2, pp. 1137-1145: Stanford, CA.
[50]J. Mansanet, A. Albiol, and R. Paredes, "Local deep neural networks for gender recognition," Pattern Recognition Letters, vol. 70, pp. 80-86, 2016.