Human gait recognition subject to different covariate factors in a multi-view environment

Gait recognition provides the opportunity to identify different walking styles of people without physical intervention. However, covariates such as changing clothes and carrying conditions may influence accuracy. Our objective was patterns for through analyzing images from publicly available data set CASIA-B on gait. On dataset, proposed method evaluated by using GEI (gait energy image) inputs normal walking, clothes, in a multi-view environment. A support vector machine (SVM) histogram oriented gradients (HOG) were applied classify human gait order meet objectives. Observations show that, under consideration mean individual accuracies, accuracy is following order: clothing > walk at 90° angle. Measurement 87.9% achieved coat-wearing measurement 83.33% all mentioned covariates. The covariate stated useful especially season like winter.