| Summary: | Recognising people by their gait is an emergent biometric. Until recently there was evaluation by few techniques on relatively small databases though with encouraging results. The potential of gait as a biometric has further been encouraged by the considerable amount of evidence available, especially in medicine and literature. This evident potential motivated development of new databases, new technique and more rigorous evaluation procedures. We describe the new techniques we have developed and their evaluation on our database to gain insight into the potential for gait as a biometric. We also describe some of our new approaches aimed to aid generalization capability for deployment of gait recognition. We show on these new and much larger databases, how our novel techniques continue to provide encouraging results for gait as a biometric, let alone as a human identifier, with especial regard for recognition at a distance.
|
|---|
