Gender and age groups classifications for semantic annotation of videos

Yaprakkaya G., ÇİÇEKLİ F. N., ULUSOY İ.

25th International Symposium on Computer and Information Sciences, ISCIS 2010, London, England, 22 - 24 September 2010, vol.62 LNEE, pp.227-230, (Full Text) identifier

  • Publication Type: Conference Paper / Full Text
  • Volume: 62 LNEE
  • Doi Number: 10.1007/978-90-481-9794-1_44
  • City: London
  • Country: England
  • Page Numbers: pp.227-230
  • Keywords: Adaboost, Age Group Classification, DCT Mod2 Features, Face Tracking, Gender Classification, LBP features, Random Forest
  • Middle East Technical University Affiliated: Yes

Abstract

This paper presents a combination of methods for gender identification and age group classification for semantic annotation of videos. The system has two different running modes as 'Training Mode' and 'Classification Mode'. The gender classifier achieves over 96% accuracy and the age group classifier achieves over 87% accuracy in age group classification. © 2011 Springer Science+Business Media B.V.