Normally, the gait of each person has individual style so it can be used for human identification. In this paper, the gait recognition using shape trace transform is presented for human identification. First step, gait recognition using shape trace transform used the silhouettes input. The gait period could be estimated by computing the median of the walking step width of the three consecutive maxima. After that, the silhouettes in one period are transformed by trace transform. Next, the trace transform pictures in one period are calculated for finding the average trace transform. The average trace transform images are defined the threshold value for finding the shape trace transform which have significance different. Finally, the shape context and Euclidean distance are used for identification. The results of gait recognition using trace transform can identify the person by their gait.