Human Gait identification System

Abstract

Few biometrics can be used to recognize a person from distance without need for direct sharing or cooperation of that person, gait (walking behavior) is one of them. Walking behavior (gait) recognition includes specifying person identity by analyzing his walking style (walking manner). In this paper, a human gait identification system depending on extracted features, which are vertical hip, horizontal hip angle and slop of thigh. The first step of the proposed system is detecting the binary silhouette of a walking individual from the uploaded videos. Then, the gait cycle is allocated using aspect ratio method. Finally, the required features from each frame in gait cycle are extracted. Different image processing operation have been performed to extract the required features. The outcome of the proposal system reflects flexibility in term of inserting, searching, updating, deleting and matching. The proposed system is tested in terms of offered functions, human recognition and noise effects. The obtained results show the efficient performance of the system and high ability of covering the error caused by surrounding conditions. The system is evaluated using the matching rate with the threshold of 70%. The adding noise can degrade the matching rate, particularly for high variance values. This is because of the increasing of noise values that might be the reason of moving the object irregularly while capturing or unexpected changing in the effected surrounding conditions.