在社交場合中，娃娃臉這種臉部特徵在外表上會具有吸引力而且給人友善的感覺。人們可以很簡單的去判斷一個人是否有娃娃臉，然而，構成娃娃臉的特質十分模糊。在我們的論文中，將去分析人臉上的特徵，並挑選出哪些特徵對於判斷一個人是否具有娃娃臉是有幫助的。我們使用特徵選擇(Feature selection)方法去挑選出最佳的特徵組合以及使用卷積神經網路(Convolutional Neural Network)去自動的學習出特徵來判斷是否為娃娃臉。在實驗當中，我們比較使用心理學的特徵、特徵選擇以及卷積神經網路三種方法的差別，在使用卷積神經網路方法的結果會比其他兩種方法來得更好。

Babyface is a type of face that is usually attractive and friendly in appearance. People can recognize this special face easily. However, the components that compose a babyface remain unclear. In this paper, we analyze the features in a human face and determine which features are useful for determining a babyface. In particular, we use feature selection methods to choose the best combination in discriminative capability and the convolutional neural networks to automatically learn the features. We compare our result with the psychological studies and showed that the features obtained by using the convolutional neural networks technique outperform the other methods under testing.

[1] Berry, Diane S., McArthur, Leslie Z, “Some components and consequences of a babyface.” Journal of Personality and Social Psychology, vol. 48(2), 1985.
[2] Huizhong Chen, Gallagher, A.C., Girod, B., “What’s in a name? First names as facial attributes.” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013.
[3] J. Wang, J. Yang, K. Yu, F. Lv, T. Huang, and Y. Gong, “Locality-constrained linear coding for image classification.” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010.
[4] W. Deng, J. Hu, J. Guo, “Extended SRC: Undersampled face recognition via intraclass variant dictionary.” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34(9), 2012.
[5] Chandrasekaran, V., Sanghavi, S., Parrilo, P.A., Willsky, A.S., “Sparse and low-rank matrix decompositions.” In Proceedings of the Annual Allerton Conference on Communication, Control, and Computing, 2009

[6] Emmanuel J. Candès, X. Li, Y. Ma, John Wright, “Robust principal component analysis?” Journal of the ACM (JACM), vol. 58(3), May, 2011.
[7] Z. Lin, Arvind Ganesh, J. Wright, L. Wu, M. Chen, Y. Ma, “Fast convex optimization algorithms for exact recovery of a corrupted low-rank matrix.” International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, December, 2009.
[8] C. Chang and C. Lin. “Libsvm: a library for support vector machines.” ACM Transactions on Intelligent Systems and Technology (TIST), 2(3):27, 2011.
[9] Leslie Zebrowitz-McArthur, Joann M. Montepare, “Contributions of a babyface and a childlink voice to impressions of Moving and Talking Faces.” Journal of Nonverbal Behavior, vol. 13(3), pp 189-203, 1989.
[10] Lorenz, K., “Die angeborenen formen moglicher erfahrung [The inate forms of potential experience].” Zietschrift fur Tierpsychologie, 1943.
[11] Sterngianz, S. H., Gray, J. L., and Murakami, M., “Adult preferences for infantile facial features: An ethological approach.” Animal Behavior, 25, 108-115., 1977.

[12] Brooks, V., Hochberg, J., “A psychophysical study of cuteness.” Perception and Psychophysics, 1960.
[13] Hildebrant, K. A., Fitzgerald, H. E., “Facial feature determinants of perceived infant attractiveness.” Infant Behavior and Development, 2, 329-339, 1979.
[14] X. Xiong and F. De la Torre, “Supervised descent method and its application to face alignment.” In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013.
[15] Yuan X.M. and Yang J. F., “Sparse and low-rank matrix decomposition via alternating direction methods”, Pacific Journal of Optimization, 9(1), 167–180, 2013.
[16] Michael McCoy, Joel A. Tropp, “Two proposals for robust PCA using semidefinite programming”, Electron. J. Statist., vol. 5, 2011.
[17] McArthur, L. Z., “Judging a book by its cover. A cognitive analysis of the relationship between physical appearance and stereotyping.” Cognitive Social Psychology, pp. 149-211, 1982.
[18] N. Kumar, A. C. Berg, P. N. Belhumeur, and S. K. Nayar, “Attribute and Simile Classifiers for Face Verification.” In Proceedings of IEEE International Conference on Computer Vision (ICCV), Oct, 2009.
[19] Face.com
http://face.com/
[20] Cootes, T. F., Edwards, G. J., Taylor, C. J. “Active appearance models”. ECCV, 1998.
[21] Unsupervised Feature Learning and Deep Learning(UFLDL)
http://ufldl.stanford.edu/wiki/index.php/UFLDL_Tutorial
[22] Caffe
http://caffe.berkeleyvision.org/
[23] Chen, Ke, et al. “Cumulative attribute space for age and crowd density estimation.” In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013.
[24] OpenCV
http://opencv.org/
[25] Imagenet
http://www.image-net.org/
[26] Brown, Gavin, et al. "Conditional likelihood maximisation: a unifying framework for information theoretic feature selection." The Journal of Machine Learning Research 13.1 pp.27-66 , 2012.

[27] Donahue, Jeff, et al. "Decaf: A deep convolutional activation feature for generic visual recognition." arXiv preprint arXiv:1310.1531, 2013.