Resumen de Combination of Face Regions in Forensic Scenarios
Pedro Tome, Julián Fiérrez Aguilar, Ruben Vera Rodriguez, Javier Ortega García
This article presents an experimental analysis of the combination of different regions of the human face on various forensic scenarios to generate scientific knowledge useful for the forensic experts. Three scenarios of interest at different distances are considered com- paring mugshot and CCTV face images using MORPH and SC face databases. One of the main findings is that inner facial regions combine better in mugshot and close CCTV scenarios and outer facial regions combine better in far CCTV scenarios. This means, that depending of the acquisition distance, the discriminative power of the facial regions change, having in some cases better performance than the full face. This effect can be exploited by considering the fusion of facial regions which results in a very significant improvement of the discriminative performance compared to just using the full face.
