Abstract
In this paper, an improved temporal template called gait history image (GHI) is proposed for human gait representation and recognition. Comparing with other temporal template methods, GHI models gait more comprehensively: Static and dynamic characteristics, as well as spatial and temporal variations, can be represented. The time duration of the GHI template is controlled by a finer period resolution (1/4 of a gait cycle). We use statistical approach to learn the discriminating features from GHIs, and gait recognition experiments were performed on the CASIA and USF gait databases. The methods using GHI template presented better recognition performances than the baseline algorithm and gait energy image (GEI) method.