International Conference on Image Analysis and Processing

ICIAP 2015: Image Analysis and Processing — ICIAP 2015 pp 15-26

MEG: Multi-Expert Gender Classification from Face Images in a Demographics-Balanced Dataset

  • Modesto Castrillón-Santana
  • Maria De Marsico
  • Michele Nappi
  • Daniel Riccio
Conference paper

DOI: 10.1007/978-3-319-23231-7_2

Volume 9279 of the book series Lecture Notes in Computer Science (LNCS)
Cite this paper as:
Castrillón-Santana M., De Marsico M., Nappi M., Riccio D. (2015) MEG: Multi-Expert Gender Classification from Face Images in a Demographics-Balanced Dataset. In: Murino V., Puppo E. (eds) Image Analysis and Processing — ICIAP 2015. ICIAP 2015. Lecture Notes in Computer Science, vol 9279. Springer, Cham

Abstract

In this paper we focus on gender classification from face images, which is still a challenging task in unrestricted scenarios. This task can be useful in a number of ways, e.g., as a preliminary step in biometric identity recognition supported by demographic information. We compare a feature based approach with two score based ones. In the former, we stack a number of feature vectors obtained by different operators, and train a SVM based on them. In the latter, we separately compute the individual scores from the same operators, then either we feed them to a SVM, or exploit likelihood ratio based on a pairwise comparison of their answers. Experiments use EGA database, which presents a good balance with respect to demographic features of stored face images. As expected, feature level fusion achieves an often better classification performance but it is also quite computationally expensive. Our contribution has a threefold value: 1) the proposed score level fusion approaches, though less demanding, achieve results which are rather similar or slightly better than feature level fusion, especially when a particular set of experts are fused; since experts are trained individually, it is not required to evaluate a complex multi-feature distribution and the training process is more efficient; 2) the number of uncertain cases significantly decreases; 3) the operators used are not computationally expensive in themselves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Modesto Castrillón-Santana
    • 1
  • Maria De Marsico
    • 2
  • Michele Nappi
    • 3
  • Daniel Riccio
    • 4
  1. 1.Universidad de Las Palmas de Gran CanariaLas PalmasSpain
  2. 2.Sapienza University of RomeRomeItaly
  3. 3.University of SalernoFiscianoItaly
  4. 4.University of Naples Federico IINaplesItaly