Welcome to the InfoSci Platform
Probabilistic Modeling for Detection and Gender Classification

Probabilistic Modeling for Detection and Gender Classification

Mokhtar Taffar, Serge Miguet, Mohammed Benmohammed
Copyright: © 2014 |Volume: 4 |Issue: 1 |Pages: 10
ISSN: 2155-6997|EISSN: 2155-6989|EISBN13: 9781466653399|DOI: 10.4018/ijcvip.2014010103
Cite Article Cite Article

MLA

Taffar, Mokhtar, et al. "Probabilistic Modeling for Detection and Gender Classification." IJCVIP vol.4, no.1 2014: pp.30-39. http://doi.org/10.4018/ijcvip.2014010103

APA

Taffar, M., Miguet, S., & Benmohammed, M. (2014). Probabilistic Modeling for Detection and Gender Classification. International Journal of Computer Vision and Image Processing (IJCVIP), 4(1), 30-39. http://doi.org/10.4018/ijcvip.2014010103

Chicago

Taffar, Mokhtar, Serge Miguet, and Mohammed Benmohammed. "Probabilistic Modeling for Detection and Gender Classification," International Journal of Computer Vision and Image Processing (IJCVIP) 4, no.1: 30-39. http://doi.org/10.4018/ijcvip.2014010103

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

In this paper, the authors contribute to solve the simultaneous problems of detection and gender classification from any viewpoint. The authors use an invariant model for accurate face localization based on a combination of appearance and geometric. A probabilistic matching of visual traits allows to classify the gender of face even when pose changes. The authors deal with the local invariant features whose performances have already been proved. Each facial feature retained in the detection step will be weighted by a probability to be male or female. This feature contributes to determine the gender of the face. The authors evaluate our model by testing it in experiments on different databases. The experimental results show that the face model performs well to detect face and gives a good gender recognition rate in the presence of viewpoint changes and facial appearance variability.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.