Human Gait Analysis using Artificial Neural Networks

An individual's proof of identity on the basis of gait has initiated inquisitiveness in the realm of computer vision owing to its extraordinary differentiation proficiency even at a remote distance. Biometric systems are vital as they offer trustworthy and effective ways to verify humans. Human gait or an individual's style of walking is a valuable biometric trait, which has lately invited inordinate consideration in applications like video surveillance. Gait recognition intends to tackle the problem of distantly identifying humans by recognizing them based on the manner they walk. This study aims to propose and develop a system of gait recognition for identifying humans using artificial neural networks (ANNs). In this study, a publicly available CASIA gait database was used, and gait recognition algorithm was applied to identify humans. Classification was done via ANNs. MATLAB was used to implement this research work. It was observed that the developed system was able to appropriately identify humans through gait recognition. When four databases were considered, the recognized ID was from database 2, which means that out of four databases, human gait was correctly recognized in ID 2 with a total time of 28.6713 seconds. The results of this work prove to be quite promising, which implies that if the count of databases is increased, then the developed system is able to correctly extract features and appropriately identify humans within a stipulated time.