Gait Recognition Under Different Clothing Conditions Via Deterministic Learning
Abstract
Dear Editor, This letter deals with the robustness problem of gait recognition method against maximum number of clothing conditions. By selecting four kinds of time-varying silhouette features, gait dynamics underlying different individuals' gait features is effectively modeled by radial basis function (RBF) neural networks through deterministic learning. This kind of dynamics information has little sensitivity to the variance between gait patterns under different clothing conditions. In order to eliminate the effect of clothing differences, the training patterns under different clothing conditions further constitute a uniform training dataset, containing all kinds of gait dynamics under different clothing conditions. A rapid recognition scheme is presented on published gait databases. Extensive experiments demonstrate the efficacy of the proposed method.
