Facial Attractiveness Prediction Integrating Subjective and Consensus Information

doi:10.19678/j.issn.1000-3428.0051535

Abstract

Abstract: In order to predict the personalized aesthetic preferences of specific objects,machine learning and depth learning are combined,and a personalized facial attractiveness evaluation method that integrating consensus and subjective preference information is proposed.Group ratings are collected from the data set to form consensus information,and the prediction model of individual ratings is constructed to reflect subjective information.Combining these two kinds of information and giving full play to the universality of consensus information and the uniqueness of subjective information,a personalized facial attractiveness prediction model is constructed.Experiments on open SCUT-FBP and FaceScrub datasets show that the Pearson correlation coefficient of this method is as high as 0.90 and the residual value is only 0.25.

Key words: feature integration, personalized prediction, facial attractiveness, consensus information, subjective information, Pearson correlation coefficient

摘要： 为对特定对象的个性化审美偏好进行预测，将机器学习与深度学习相结合，提出融合共识性与主观性偏好信息的个性化人脸吸引力评估方法。从数据集中收集群体评分形成共识性信息，构建个人评分预测模型以反映主观性信息。结合这2种信息并发挥共识性信息的普遍性优势以及主观性信息的独特性，从而构建个性化人脸吸引力预测模型。在公开的SCUT-FBP和FaceScrub数据集上进行实验，结果表明，该方法的Pearson相关系数高达0.90，残差值低至0.25。

关键词: 特征融合, 个性化预测, 人脸吸引力, 共识性信息, 主观性信息, Pearson相关系数

CLC Number:

TP391

LI Jinman, WANG Jianming, JIN Guanghao. Facial Attractiveness Prediction Integrating Subjective and Consensus Information[J]. Computer Engineering, 2019, 45(8): 224-229.

李金蔓, 汪剑鸣, 金光浩. 融合主观性与共识性信息的人脸吸引力预测[J]. 计算机工程, 2019, 45(8): 224-229.

/ / Recommend / Download Citations

URL: http://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0051535

http://www.ecice06.com/EN/Y2019/V45/I8/224

References 35

[1]	WILLIS J,TODOROV A.First impressions:making up your mind after a 100-ms exposure to a face[J].Psychological Science,2010,17(7):592-598.
[2]	LANGLOIS J H,KALAKANIS L,RUBENSTEIN A J,et al.Maxims or myths of beauty? A meta-analytic and theoretical review[J].Psychological Bulletin,2000,126(3):390-423.
[3]	AARABI P,HUGHES D,MOHAJER K,et al.The automatic measurement of facial beauty[C]//Proceedings of IEEE International Conference on Systems,Man,and Cybernetics.Washington D.C.,USA:IEEE Press,2001:2644-2647.
[4]	ALTWAIJRY H,BELONGIE S.Relative ranking of facial attractiveness[C]//Proceedings of 2013 IEEE Workshop on Applications of Computer Vision.Washington D.C.,USA:IEEE Press,2013:117-124.
[5]	ROTHE R,TIMOFTE R,GOOL L V.Some like it hot-visual guidance for preference prediction[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2016:5553-5561.
[6]	YAN Mengjia,DUAN Yuron,DENG Siqi,et al.Facial beauty assessment under unconstrained conditions[C]//Proceedings of International Conference on Electronics,Computers and Artificial Intelligence.Washington D.C.,USA:IEEE Press,2017:1-6.
[7]	EISENTHAL Y,DROR G,RUPPIN E.Facial attractive-ness:beauty and the machine[J].Neural Computation,2006,18(1):119-142.
[8]	MAO Huiyun,JIN Lianwen,DU Minghui.Automatic classifica-tion of Chinese female facial beauty using support vector machine[C]//Proceedings of IEEE International Conference on Systems,Man and Cybernetics.Washington D.C.,USA:IEEE Press,2009:4842-4846.
[9]	毛慧芸.人脸美丽吸引力的特征分析与机器学习[D].广州:华南理工大学,2011.
[10]	陈伊力.基于数据驱动的人脸美化[D].广州:华南理工大学,2012.
[11]	ZHANG D,CHEN Fangmei,XU Yong.Data-driven facial beauty analysis:prediction,retrieval and manipulation[M].Berlin,Germany:Springer,2016.
[12]	GAN Junying,LI Lichen,ZHAI Yikui.Facial beauty prediction model based on self-taught learning and convolutional restricted Boltzmann machine[C]//Proceedings of International Conference on Machine Learning and Cybernetics.Washington D.C.,USA:IEEE Press,2015:844-849.
[13]	GAN Junying,ZHOU Lei,ZHAI Yikui.A study for facial beauty prediction model[C]//Proceedings of International Conference on Wavelet Analysis and Pattern Recognition.Washington D.C.,USA:IEEE Press,2015:8-13.
[14]	李远豪,甘俊英.深度自编码器用于人脸美丽吸引力预测的研究[J].五邑大学学报(自然科学版),2014,28(4):49-54.
[15]	CHOUDHARY G,GANDHI T K.Indexing facial attrac-tiveness and well beings using machine learning[C]//Proceedings of 2016 IEEE Region 10 Humanitarian Technology Conference.Washington D.C.,USA:IEEE Press,2016:1-6.
[16]	GRAY D,YU Kai,XU Wei,et al.Predicting facial beauty without landmarks[C]//Proceedings of European Conference on Computer Vision.Berlin,Germany:Springer,2010:434-447.
[17]	XU Jie,JIN Lianwen,LIANG Lingyu,et al.Facial attractiveness prediction using psychologically inspired convolutional neural network(PI-CNN)[C]//Proceedings of IEEE International Conference on Acoustics,Speech and Signal Processing.Washington D.C.,USA:IEEE Press,2017:1657-1661.
[18]	KALAYCI S,EKENEL H K,GUNES H.Automatic analysis of facial attractiveness from video[C]//Proceedings of IEEE International Conference on Image Processing.Washington D.C.,USA:IEEE Press,2015:4191-4195.
[19]	LU Xi,CHANG Xiaobin,XIE Xiaohua,et al.Facial skin beautification via sparse representation over learned layer dictionary[C]//Proceedings of International Joint Conference on Neural Networks.Washington D.C.,USA:IEEE Press,2016:2534-2539.
[20]	LIU Shu,LI Bo,FAN Yangyu,et al.Facial attractiveness computation by label distribution learning with deep CNN and geometric features[C]//Proceedings of IEEE International Conference on Multimedia and Expo.Washington D.C.,USA:IEEE Press,2017:1344-1349.
[21]	WHITEHILL J,MOVELLAN J R.Personalized facial attractiveness prediction[C]//Proceedings of IEEE International Conference on Automatic Face and Gesture Recognition.Washington D.C.,USA:IEEE Press,2008:1-7.
[22]	DANTCHEVA A,DUGELAY J L.Assessment of female facial beauty based on anthropometric,non-permanent and acquisition characteristics[M].[S.l.]:Kluwer Academic Publishers,2015.
[23]	王少标.基于个性与共性探讨的人脸美化[D].合肥:中国科学技术大学,2016.
[24]	舒畅,丁晓青,方驰.多特征局部与全局融合的人脸识别方法[J].计算机工程,2011,37(19):145-147.
[25]	黄忠,胡敏,刘娟.基于多特征决策级融合的表情识别方法[J].计算机工程,2015,41(10):171-176.
[26]	PEARSON K.Notes on the history of correlation[J].Biometrika,1920,13(1):25-45.
[27]	HAGHIGHAT M,ABDEL-MOTTALEB M,ALHALABI W.Fully automatic face normalization and single sample face recognition in unconstrained environments[J].Expert Systems with Applications,2016,47(5):23-34.
[28]	MAO Huiyun,JIN Lianwen,DU Minghui.Facial beauty classification based on geometric features and c4.5[J].Pattern Recognition and Artificial Intelligence,2010,23(6):809-814.
[29]	XIE Duorui,LIANG Lingyu,JIN Lianwen,et al.SCUT-FBP:a benchmark dataset for facial beauty perception[C]//Proceedings of IEEE International Conference on Systems,Man,and Cybernetics.Washington D.C.,USA:IEEE Press,2015:1821-1826.
[30]	NG H,WINKLER S.A data-driven approach to cleaning large face datasets[C]//Proceedings of IEEE International Conference on Image Processing.Washington D.C.,USA:IEEE Press,2015:343-347.
[31]	SZABO N S,TANAKA R I.Residue arithmetic and its applications to computer technology[J].SIAM Review,2009,11(1):143-150.
[32]	PESARAN M H,SMITH R J.A generalized R2criterion for regression models estimated by the instrumental variables method[J].Econometrica,1994,62(3):705-710.
[33]	LIU Shu,FAN Yangyu,GUO Zhe,et al.2.5d facial attractiveness computation based on data-driven geometric ratios[C]//Proceedings of International Conference on Intelligent Science and Big Data Engineering.Washington D.C.,USA:IEEE Press,2015:564-573.
[34]	WANG Shuyang,SHAO Ming,FU Yun.Attractive or not?:beauty prediction with attractiveness-aware encoders and robust late fusion[C]//Proceedings of ACM International Conference on Multimedia.New York,USA:ACM Press,2014:805-808.
[35]	XU Jie,JIN Lianwen,LIANG Lingyu,et al.A new humanlike facial attractiveness predictor with cascaded fine-tuning deep learning model[J].Computer Science,2015,70(1):45-79.

Please choose a citation manager

Content to export