Introduction

Abstract

Aunique advantage of gait as a biometrie is that it offers potential for recognition at a distance or at low resolution or when other biometrics might not be perceivable. Consider an image from a surveillance camera as in Fig. 1.1: the subject’s face can be obscured, their hands are at too low a resolution for recognition by shape; it would be pointless even to attempt to recognize subjects by iris or fingerprint pattern. In many scene-of-crime data, the situation is exacerbated by poor quality video data or by poor illumination. In contrast a subject’s gait is often readily apparent in an image sequence. Identity can be concealed in a covert way quite easily, one does not assume that every customer entering a bank wearing a scarf over their face is about to rob it. Gait recognition can handle this and might even answer the question as to whether the subject is actually a “him”, or whether it is likely that the subject was in fact female.