Abstract：At present,facial beauty prediction is facing the problems,in which data is insufficient,the face image is hard to classify,and the deep feature lacks research.To solve these problems,a solution to facial beauty prediction research based on double activation layer depth convolution feature is proposed.Firstly,we use the method of data augmentation and face alignment to increase the number of samples in training set and improve the data quality of database.Secondly,we propose a double activation layer (DAL) to design a CNN model that is more suitable for facial beauty prediction.Experimental results based on 2000 test set show that the method proposed is superior to the traditional method of facial beauty prediction both in classification and regression.In addition,the proposed method achieves better results and real time performance than the state-of-art CNN model,in which rank-1 recognition rate is 61.1% and the Pearson correlation coefficient is 0.8546.Consequently,the DAL method plays an important role in deep facial prediction learning,which can be widely used in face recognition and image processing.
甘俊英, 翟懿奎, 黄聿, 曾军英, 姜开永. 基于双激活层深度卷积特征的人脸美丽预测研究[J]. 电子学报, 2019, 47(3): 636-642.
GAN Jun-ying, ZHAI Yi-kui, HUANG Yu, ZENG Jun-ying, JIANG Kai-yong. Research of Facial Beauty Prediction Based on Deep Convolutional Features Using Double Activation Layer. Acta Electronica Sinica, 2019, 47(3): 636-642.
[1] Redi M,Rasiwasia N,Aggarwal G,Jaimes A.The beauty of capturing faces:rating the quality of digital portraits[A].IEEE International Conference and Workshops on Automatic Face and Gesture Recognition[C].Ljubljana,Slovenia:IEEE,2015.1-8.
[2] Eisenthal Y,Dror G,Ruppin E.Facial attractiveness:beauty and the machine[J].Neural Computation,2006,18(1):119-142.
[3] Mao H Y,Jin L W,Du M.Automatic classification of Chinese female facial beauty using support vector machine[A].Proceedings of the IEEE International Conference on Systems,Man and Cybernetics[C].Texas:IEEE,2009.4842-4846.
[4] Gan J Y,Li L C,Zhai Y K,et al.Deep self-taught learning for facial beauty prediction[J].Neurocomputing,2014,144(1):295-303.
[5] Gan J Y,Zhai Y K,Wang B.Unconstrained facial beauty prediction based on multi-scale k-means[J].Chinese Journal of Electronics,2017,26(3):548-556.
[6] Gray D,Yu K,Xu W,Gong Y.Predicting facial beauty without landmark[J].European Conference on Computer Vision,2010,6316(4):434-447.
[7] Xie D,Liang L,Jin L W,et al.SCUT-FBP:a benchmark dataset for facial beauty perception[A].International Conference on Systems,Man,and Cybernetics[C].Kowloon:IEEE,2015.1821-1826.
[8] Xu J,Jin L W,Liang L,et al.A new humanlike facial attractiveness predictor with cascaded fine-tuning deep learning model[J].Computer Science,2015,70(1):45-79.
[9] Chen F,Xiao X,Zhang D.Data-driven facial beauty analysis:prediction,retrieval and manipulation[J].IEEE Transactions on Affective Computing,2018,9(2):205-216.
[10] Lecun Y,Bottou L,Bengio Y,et al.Gradient-based learning applied to document recognition[J],Proceedings of the IEEE,1998,86(11):2278-2324.
[11] Parkhi O M,Vedaldi A,Zisserman A.Deep face recognition[A].British Machine Vision Conference[C].Swansea:BMVA Press,2015.41.1-41.12.
[12] Krizhevsky A,Sutskever I,Hinton G E.Imagenet classification with deep convolutional neural networks[A].Neural Information Processing Systems[C].Nevada:Curran Associates Inc,2012.1097-1105.
[13] Levi G,Hassner T.Emotion recognition in the wild via convolutional neural networks and mapped binary patterns[A].Proceedings of the 2015 ACM on International Conference on Multimodal Interaction[C].Seattle:ACM New York,2015.503-510.
[14] Liu X,Li S,Kan M,et al.Agenet:deeply learned regressor and classifier for robust apparent age estimation[A].International Conference on Computer Vision Workshop[C].Santiago:IEEE,2015.258-266.
[15] Glorot X,Bordes A,Bengio Y.Deep sparse rectifier neural networks[J].Journal of Machine Learning Research,2011,15(1):315-323.
[16] Goodfellow I J,Wardefarley D,Mirza M,et,al.Maxout networks[J].JMLR WCP,2013,28(3):1319-1327.
[17] Wu X,He R,Sun Z.A lightened CNN for deep face representation[J].Computer Science,2015,1(1):109-117.
[18] Dantone M,Gall J,Fanelli G,et al.Real-time facial feature detection using conditional regression forests[A].Computer Vision and Pattern Recognition[C].Rhode Island:IEEE,2012.2578-2585.
[19] Jia Y Q,Shelhamer,Evan,Donahue.Caffe:convolutional architecture for fast feature embedding[A].ACM International Conference on Multimedia[C].Orlando:ACM New York,2014.675-678.
[20] Lin M,Chen Q,Yan S.Network in network[J].Computer Science,2013,1(1):85-97.
[21] Sun Y,Chen Y,Wang X,et al.Deep learning face representation by joint identification verification[A].Advances in Neural Information Processing[C].Quebec:IEEE,2014.1988-1996.
[22] Szegedy C,Liu W,Jia Y,et al.Going deeper with convolutions[A].Computer Vision and Pattern Recognition[C].Boston:IEEE,2015.1-9.
[23] Simonyan K,Zisserman A.Very deep convolutional networks for large-scale image recognition[J].Computer Science,2014,1(1):1-14.
2019, Vol. 47 
