Gait recognition using independent component analysis

Authors:
Jiwen Lu;Erhu Zhang;Zhigang Zhang;Yanxue Xue
Affiliations:
Department of Information Science, Xi'an University of Technology, Xi'an, Shaanxi, China;Department of Information Science, Xi'an University of Technology, Xi'an, Shaanxi, China;Department of Information Science, Xi'an University of Technology, Xi'an, Shaanxi, China;Department of Information Science, Xi'an University of Technology, Xi'an, Shaanxi, China
Venue:
ISNN'05 Proceedings of the Second international conference on Advances in neural networks - Volume Part II
Year:
2005

Citing 5
Cited 3

Independent component analysis: algorithms and applications

Neural Networks
Automatic gait recognition using area-based metrics

Pattern Recognition Letters
Silhouette Analysis-Based Gait Recognition for Human Identification

IEEE Transactions on Pattern Analysis and Machine Intelligence
On automated model-based extraction and analysis of gait

FGR' 04 Proceedings of the Sixth IEEE international conference on Automatic face and gesture recognition
Fast and robust fixed-point algorithms for independent component analysis

IEEE Transactions on Neural Networks

Appearance-Based gait recognition using independent component analysis

ICNC'06 Proceedings of the Second international conference on Advances in Natural Computation - Volume Part I
Gait recognition using hidden markov model

ICNC'06 Proceedings of the Second international conference on Advances in Natural Computation - Volume Part I
Gait recognition using wavelet descriptors and independent component analysis

ISNN'06 Proceedings of the Third international conference on Advnaces in Neural Networks - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a new method for automatic gait recognition using independent component analysis (ICA). Firstly, a simple background subtraction algorithm is introduced to segment the moving figures accurately and to achieve binary silhouettes. Secondly, these 2D binary silhouettes are converted into associated sequences of 1D signals and ICA is applied to get the independent components of each 2D binary silhouettes. For the sake of reducing computation cost, a fast and robust fixed-point algorithm named FastICA is adopted. A criterion that not all ICs are useful for recognition is demonstrated and a method of IC selection is put forward. Lastly, the nearest neighbor (NN) classifier for recognition is chosen. This algorithm is tested on small MUD gait database and the NLPR gait database and experimental results show that our method has encouraging recognition accuracy.