Toggle Main Menu Toggle Search

Open Access padlockePrints

An analysis of automatic gender classification

Lookup NU author(s): Dr Quoc Vuong

Downloads

Full text for this publication is not currently held within this repository. Alternative links are provided below where available.


Abstract

Different researches suggest that inner facial features are not the only discriminative features for tasks such as person identification or gender classification. Indeed, they have shown an influence of features which are part of the local face context, such as hair, on these tasks. However, object-centered approaches which ignore local context dominate the research in computational vision based facial analysis. In this paper, we performed an analysis to study which areas and which resolutions are diagnostic for the gender classification problem. We first demonstrate the importance of contextual features in human observers for gender classification using a psychophysical "bubbles" technique. The success rate achieved without internal facial information convinced us to analyze the performance of an appearance-based representation which takes into account facial areas and resolutions that integrate inner features and local context. © Springer-Verlag Berlin Heidelberg 2007.


Publication metadata

Author(s): Castrillón-Santana M, Vuong QC

Editor(s): L. Rueda, D. Mery, & J. Kittler

Publication type: Book Chapter

Publication status: Published

Book Title: Progress in Pattern Recognition, Image Analysis and Applications

Year: 2007

Volume: 4756

Pages: 271-280

Print publication date: 01/01/2007

Series Title: Lecture Notes in Computer Science

Publisher: Springer Verlag

Place Published: Heidelberg, Germany

URL: http://dx.doi.org/10.1007/978-3-540-76725-1

DOI: 10.1007/978-3-540-76725-1

Notes: Proceedings of the 12th Iberoamericann Congress on Pattern Recognition, CIARP 2007, Valparaiso, Chile, November 13-16, 2007.

Library holdings: Search Newcastle University Library for this item

ISBN: 9783540767244


Actions

Link to this publication


Share