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

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.

Human Gait Recognition Based on Multiple Feature Combination and Parameter Optimization Algorithms

“…With the advancement of measurement technology and recognition algorithms, support vector machine (SVM), linear discriminant analysis (LDA), and extreme learning machine (ELM) are widely utilized for pattern recognition [25][26][27][28]. Wang et al [29] identified multiple gait patterns and compared the classification performance of SVM and neural networks.…”

Combined Regularized Discriminant Analysis and Swarm Intelligence Techniques for Gait Recognition

“…Gait recognition methods [3] can be categorized as model-free (appearance-based) [2,[4][5][6][7][8][9][10][11][12] and model-based [13][14][15][16][17][18][19][20][21][22]. Most gait recognition studies are based on model-free approaches that employ the whole motion pattern of the human body.…”

“…It is also worth noting that most of them can only achieve correct results from a specific point of view, usually side view [4,5,[7][8][9]16]. The recent research on model-free methods has focused on eliminating these drawbacks [6,[10][11][12]. Model-based methods infer gait signature directly by modeling the underlying kinematics of human motion.…”

“…This is a traditional approach that is based on a clear separation between the descriptors and classifier model. On the other hand, in the papers of recent years, the introduction of new classification methods such as deep learning [11,20,22] or hybrid methods [12], in which the description and classification steps cannot be easily distinguished, is increasingly visible. In [20], the authors utilized a 3D convolutional neural network (CNN) and long short-term memory neural networks for training the classification models.…”

“…The proposed method can extract spatial and temporal information more effectively than other methods regarding gait as a template or sequence. In turn, in the paper [12], the authors used a hybrid approach and combine the improved local coupled extreme learning machine and PSO for the classification process. A Gabor filter was used to extract gait features from the GEI and linear discriminant analysis was used to dimensionality reduction.…”