Fusion of Chaotic Measure Into a New Hybrid Face-Gait System for Human Recognition

In this paper we describe a method to recognize people using face and gait features in a novel yet natural way, using a single camera. We show that frontal-normal motion analysis yields more dynamic information as compared to fronto-parallel motion and allows us to analyse gait in a new way, using nonlinear dynamics of time series normally used in chaos theory. A set of point light sources attached to various points of a walking person allows the walker to be identified. Phase-space analysis of trajectories of these moving light displays (MLDs) provides sufficient information for identification of people by their gait. Using chaotic measures to identify humans by their gait is a significant precedent. To demonstrate the usefulness of this result, we perform face recognition in a nonideal environment and show that by augmenting with gait data, we get better recognition rates, providing a more robust identification scheme