The Human Gait Recognition using an Enhanced Convolutional Neural Network

gait recognition

Abstract

Gait is a soft biometric with unique advantages compared to other biometrics. Soft biometric are features that can be extracted remotely and do not require human interaction. The force of gait, is that it does not require cooperative subjects and it is recognizable from low-resolution surveillance videos. This paper presents a proposed framework for gait recognition by building the required dataset. In this work, nine gait attributes are extracted, and recognition is done using an Enhanced Convolutional Neural Network (ECNN). The proposed model achieved an accuracy of 89.583%.