Automated Human Recognition by Gait using Neural Network

Abstract

We describe a new method for recognizing humans by their gait using back-propagation neural network. Here, the gait motion is described as rhythmic and periodic motion, and a 2D stick figure is extracted from gait silhouette by motion information with topological analysis guided by anatomical knowledge. A sequential set of 2D stick figures is used to represent the gait signature that is primitive data for the feature extraction based on motion parameters. Then, a back-propagation neural network algorithm is used to recognize humans by their gait patterns. In experiments, higher gait recognition performances have been achieved.