Learning to recognize gender using experince

Abstract

Automatic facial analysis abilities are commonly integratedin a system by a previous off-line learning stage. In this pa-per we argue that a facial analysis system would improve itsfacial analysis capabilities based on its own experience simi-larly to the way a biological system, i.e. the human system,does throughout the years. The approach described, focusedon gender classification, updates its knowledge according tothe classification results. The presented gender experiments suggest that this approach is promising, even when just a short simulation of what for humans would take years of acquisition experience was performed.