Gait Recognition via Independent Component Analysis Based on Support Vector Machine and Neural Network

Abstract

Abstract. This paper proposes a method of automatic gait recognition using Fourier descriptors and independent component analysis (ICA) for the purpose of human identification at a distance. Firstly, a simple background generation algorithm is introduced to subtract the moving figures accurately and to obtain binary human silhouettes. Secondly, these silhouettes are described with Fourier descriptors and converted into associated one-dimension signals. Then ICA is applied to get the independent components of the signals. For reducing the computational cost, a fast and robust fixed-point algorithm for calculating ICs is adopted and a criterion how to select ICs is put forward. Lastly, the nearest neighbor (NN), support vector machine (SVM) and backpropagation neural network (BPNN) classifiers are chosen for recognition and this method is tested on the small UMD gait database and the NLPR gait database. Experimental results show that our method has encouraging recognition accuracy.

Review on Vision-Based Gait Recognition: Representations, Classification Schemes and Datasets

“…Zhang et al (2005;Yoo et al, 2008;Xiao and Yang, 2008) employed back propagation neural network in gait recognition. Lee et al (2008) applied an ensemble of neural network to achieve better generalization performance than a single neural network.…”

Human Gait Recognition Based on Kernel Independent Component Analysis

“…Second, components that are as independent as possible are obtained when ICA is performed. Lu et al [7] [29] proposed an ICA-based method for gait recognition, they adopted the FastICA algorithm [8] to calculate the independent components (IC) and evaluated their method on MUD and NLPR database. In this paper we use the FastICA algorithm in contrast to our method with their performance on two larger databases as is shown in section 4.…”