Walking Behavior Based Human Recognition System

Abstract

In the recent period with the growing need for surveillance system, people looking for suitable method to identify person. Depending on the features of biometric that can specify human identity by using identification and verification functions. The verification process is done by compare the biometric features such as, fingerprint, iris, face recognition, etc., with a record stored previously. While the identification process is performed by find the best match between the biometric features and all records kept in a database. Walking behavior recognition is the only biometric that can specify an individual identity at distance that relying on walking behavior features such as step length, angle of hip and knee, etc. In this paper we propose a biometric based human identification system depending on walking behavior characteristic which is vertical hip angle, horizontal hip angle and slop of thigh that extract from captured picture of person. A database of numerous people has been used. A database has been constructed using SQL server software environment in which person identification performed with high efficiency. The outcome of the proposal system reflects flexibility in term of inserting, searching, updating, deleting and matching.