Use of spatio-temporal modeling for age invariant face recognition

In this research we propose a novel method for face recognition based on Anthropometric features gathered from landmark points on a face over time. Age invariant face recognition enables matching of an image obtained at a point in time against an image of the same individual obtained at an earlier point in time and thus has important applications, notably in law enforcement. We investigate four different types of models built on different levels of data granularity. At the global level a model is built on training data that encompasses the entire set of available individuals, whereas at the local level data from homogeneous sub-populations are used and finally at the individual level a personalized model is built for each individual. Our empirical results show that the local and personalized models perform best when rated on Rank-1 accuracy and recognition time.