• DocumentCode
    2813736
  • Title

    Estimation of subjective age based on facial images of others: Comparative studies of the Americans and the Japanese

  • Author

    Azuma, Yasuhiro ; Konishi, Masato ; Miyamoto, Naoyuki ; Fujisawa, Takashi X. ; Nagata, Noriko ; Kosaka, Akio

  • Author_Institution
    Sch. of Sci. & Technol., Kwansei Gakuin Univ., Sanda, Japan
  • fYear
    2011
  • fDate
    9-11 Feb. 2011
  • Firstpage
    1
  • Lastpage
    6
  • Abstract
    We designed a method for estimating the subjective age of a person; using this method, one evaluates one´s own age by estimating whether a person shown in a facial image looks older or younger than oneself. Thus far, experiments have shown that Japanese people tend to underestimate their subjective age. In this study, we conducted an international comparative study to focus on the socio-psychological effects that may influence the underestimation of subjective age. Experiments were performed in which American and Japanese participants viewed American facial images; in addition, the American participants viewed Japanese facial images. Through these experiments, it was confirmed that the underestimation of age occurs despite differences in Japanese and American societies and cultures; however, the tendency of underestimation of age is not related to facial images but to social and cultural factors that influence the participants. Moreover, we carried out experiments of conventional look age estimates and compared the results to those of the subjective age estimates.
  • Keywords
    estimation theory; face recognition; social aspects of automation; Japanese people; cultural factors; facial images; socio-psychological effects; subjective age; subjective age estimation; Analysis of variance; Approximation methods; Computers; Estimation; Linear regression; Logistics; facial images; non-linear regression analysis; subjective age;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Frontiers of Computer Vision (FCV), 2011 17th Korea-Japan Joint Workshop on
  • Conference_Location
    Ulsan
  • Print_ISBN
    978-1-61284-677-4
  • Electronic_ISBN
    978-1-61284-676-7
  • Type

    conf

  • DOI
    10.1109/FCV.2011.5739734
  • Filename
    5739734