Gait Recognition Based on the Feature Extraction of Gabor Filter and Linear Discriminant Analysis and Improved Local Coupled Extreme Learning Machine

Hongli Guo,Shuwang Zhou,Youmei Zhang,Bin Li,Wei Li,Xuewen Rong,Yu Zhang,Fengjuan Qiao

doi:10.1155/2020/5393058

Abstract

A gait energy image contains much gait information, which is one of the most effective means to recognize gait characteristics. The accuracy of gait recognition is greatly affected by covariates, such as the viewing angle, occlusion of clothing, and walking speed. Gait features differ somewhat by angles. Therefore, how to improve the recognition accuracy of a cross-view gait is a challenging task. This study proposes a new gait recognition algorithm structure. A Gabor filter is used to extract gait features from gait energy images, since it can extract features of different directions and scales. We use linear discriminant analysis (LDA) to tackle the problem that the feature dimension restricts the process. Finally, the improved local coupled extreme learning machine based on particle swarm optimization is used for the classification process of the extracted features of the gait. The proposed method and other current mainstream algorithms are compared in terms of the recognition accuracy based on the CASIA-A and CASIA-B datasets, and the simulation results show that the proposed algorithm has good performance and performs well at cross-view gait recognition.

Highlights

Identity recognition is a foundation of human social life, and increasing interest in biometrics of recognition algorithms has led to rapid improvements in biometric technologies with better performance
To demonstrate the algorithm’s effectiveness, we compare the dimension-reduction method to principal component analysis (PCA), and the proposed method of gait recognition in this paper is compared with the other current mainstream algorithms based on the CASIA-A and CASIA-B benchmark gait databases of the Institute of Automation, Chinese Academy of Sciences. e simulation results show that the proposed method can improve the recognition accuracy of gait and performs well at cross-view gait recognition
We propose a local coupled extreme learning machine based on particle swarm optimization [34] to improve the performance. is algorithm uses a particle swarm optimization strategy to optimize the four parameters (W, b, d, r) in LC-Extreme learning machine (ELM), so as to improve its accuracy and generalization performance

Summary

Introduction

Identity recognition is a foundation of human social life, and increasing interest in biometrics of recognition algorithms has led to rapid improvements in biometric technologies with better performance. Biometric recognition is identification based on personal physiological or behavioral characteristics [1]. Common biometric recognition technologies include facial, fingerprint, palm print, and iris recognition. Biological patterns and features are usually unique and are impossible to forge or copy [2], so biometric authentication has great advantages over the traditional authentication. A person’s gait, or way of walking, is a complex spatiotemporal biological feature that can be used to distinguish an individual [3], and to realize personal identification [4]. We all have the experience of identifying friends and family through gait information. Unlike biometrics, such as the face, fingerprint, and iris, gait sequences can be collected undisturbed at long distances with minimal cooperation [6]. Gait is difficult to hide or camouflage [7]

Methods

Results

Conclusion