Abstract
Human gait has been shown to be unique and could be treated as a useful signature for human identification. Nevertheless there are still some problems when using the gait for human identification. In this thesis, we focus on the improvement of the clothing-variation problem. First, we model the characteristics of human gait which suffers no clothing-variation as the normal case model. Next, we detect and remove the clothing-variation parts of a gait based on this model. The process of removing the clothing-variation using the normal case model is called the normal case subtraction. The experimental results show that our proposed normal case subtraction outperforms other existing approaches of solving the clothing-variation problem in human identification.