Gait Recognition has gained attentions recently. It has evidenced by psychological studies that human is able to recognize gait in some level by the way a person walks. As a biometric, gait has the potential to be recognized in public through computer vision techniques. Depth data from RGB-Depth (RGB-D) camera can optimize vision-based gait recognition techniques by locating human joints in three dimensions. This study aims to propose a method to recognize human gait in public by processing skeleton data extracted by Microsoft Kinect. The results of this study can enhance the accuracy of gait recognition and shorten processing time.