Gender recognition from face images using a geometric descriptor

Marcos Vinicius Mussel Cirne, Hélio Pedrini

Abstract: Gender recognition from face images is a challenging problem with applications in various knowledge domains, such as biometrics, security and surveillance, human-computer interaction, among others. In this work, we propose and evaluate a novel method for gender recognition based on a geometric descriptor constructed from a pre-defined face shape model. The proposed approach, tested on four different face datasets, achieved superior results for most cases when compared to other methods based on geometric descriptors.