logo

Journals Books
Advanced Search
Sign in Register

中文

SCIENCE CHINA Information Sciences
Download PDF
SCIENCE CHINA Information Sciences, Volume 61 , Issue 5 : 058105(2018) https://doi.org/10.1007/s11432-016-9174-0

Modern physiognomy: an investigation on predicting personality traits and intelligence from the human face

Rizhen QIN 1,3, Wei GAO 1,3, Huarong XU 4, Zhanyi HU 1,2,3,*
More info
  • ReceivedNov 26, 2016
  • AcceptedJun 21, 2017
  • PublishedNov 17, 2017
Previous Table of Contents Next
Share
Rating

Abstract

There is no abstract available for this article.


Acknowledgment

This work was supported by Strategic Priority Research Program of the CAS (Grant No. XDB02070002) and National Natural Science Foundation of China (Grant Nos. 61421004, 61333015).


References

[1] Ballew C C, Todorov A. Predicting political elections from rapid and unreflective face judgments. Proc Natl Acad Sci USA, 2007, 104: 17948-17953 CrossRef PubMed ADS Google Scholar

[2] Oosterhof N N, Todorov A. The functional basis of face evaluation. Proc Natl Acad Sci USA, 2008, 105: 11087-11092 CrossRef PubMed ADS Google Scholar

[3] Carney D R, Colvin C R, Hall J A. A thin slice perspective on the accuracy of first impressions. J Res Personality, 2007, 41: 1054-1072 CrossRef Google Scholar

[4] Wolffhechel K, Fagertun J, Jacobsen U P, et al. Interpretation of appearance: the effect of facial features on first impressions and personality. Plos One, 2014, 9: 127--140. Google Scholar

[5] Perceived Intelligence Is Associated with Measured Intelligence in Men but Not Women. PLoS ONE, 2014, 9: e81237 CrossRef PubMed ADS Google Scholar

[6] Rojas M, Masip D, Todorov A, et al. Automatic prediction of facial trait judgments: appearance vs. structural models. Plos One, 2011, 6: 1--12. Google Scholar

[7] Qin R Z. Predicting personality traits from the human face (in Chinese). Dissertation for Master's Degree. Beijing: University of Chinese Academy of Sciences, 2016. Google Scholar

  • Table 1   Personality traits prediction by classification and regression methods
    Gender Male Female
    feature Classification Dim. Regression Dim. Classification Dim. Regression Dim.
    Parzen ($\surd$) 30 Linear 2 Parzen ($\surd$) 30 Linear 2
    DTree 30 Ridge 2 DTree 15 Ridge 2
    Structural KNN 20 Lasso 2 KNN 30 Lasso 2
    NaiveB 5 Pinv 2 NavieB 30 Pinv 2
    RF 20 KNN 2 RF 20 KNN 10
    SVM ($\surd$) 5 SVM ($\surd$) 5
    Parzen ($\surd$) 5 Linear 2 Parzen ($\surd$) 15 Linear 2
    DTree 20 Ridge 2 DTree 5 Ridge 2
    Appearance KNN 10 Lasso 20 KNN 10 Lasso ($\surd$) 15
    NaiveB 5 Pinv 2 NavieB 5 Pinv 2
    RF 20 KNN 30 RF 30 KNN 2
    SVM ($\surd$) 5 SVM 20