An Improved Gait Recognition Method Using Modified Gait Energy Image
DOI:
https://doi.org/10.24203/9y6dt475Keywords:
gait recognition, MGEI, view detection, principal component analysis, linear discriminate analysisAbstract
Gait recognition is a valuable technology for remote and concealed identity authentication, widely applied in intelligent video monitoring. Existing gait recognition algorithms fall into two categories: appearance-based methods and model-based methods. While gait features differ from static biometric features like faces or fingerprints, they exhibit significant and robust characteristics over a gait cycle. Gait Energy Image (GEI) is a commonly used feature in gait recognition, synthesizing gait images into a single representative image. In this study, we propose an improved gait recognition method that addresses the impact of viewpoint variations, clothing, and carried objects. The method uses modified GEI (MGEI) and view detection and combins two-dimensional principal component analysis and linear discriminant analysis for feature extraction. Experimental results demonstrate the effectiveness of the proposed method in reducing the influence of view variations and achieving robust gait recognition.
References
Yang Qi, Xue Dingyu, “Gait Recognition Based on Sparse Representation and Segmented Frame Difference Energy Image,” J. Information and Control. China.vol.1, pp.27-32,2013.
K. Annbuselvi, N. Santhi, S. Sivakumar, “Role of Feature Extraction Techniques : PCA and LDA for Appearance Based Gait Recognition,” J. International Journal of Computer Sciences and Engineering. Vol.6 , pp. 38-44, 2018.
Liao R.， Li Z.，Bhattacharyya S.S.，York G, “PoseMapGait: A model-based gait recognition method with pose estimation maps and graph convolutional networks” J. Neurocomputing. Vol.501 , pp. 514-528, 2022.
Boulgouris N V, Hatzinakos D, Plataniotis K N, “Gait recognition: a challenging signal processing technology for biometric identification,” J. Signal Processing Magazine IEEE, vol.22,pp.78-90,2005.
LI Lin-jie,GU Guang-hua,WANG Cheng-ru,ZHANG Chun-feng, “Features Fusion Gait Ｒecognition by Combining Energy Image and Canonical Correlation Analysis,” J. Journal of Chinese Computer Systems. China.vol.11,pp.2558-2561,2014.
Xu D, Huang Y, Zeng Z, et al, “Human Gait Recognition Using Patch Distribution Feature and Locality-Constrained Group Sparse Representation,” IEEE Transl on Image Processing, vol.21,pp.316 – 326,December 2011.
Boulgouris N V, Chi Z X, “Gait Recognition Using Radon Transform and Linear Discriminant Analysis,” J. IEEE Trans Image Process, vol.16,pp.731-740, 2007.
Wang Kejun, Yan Tao, Lü Zhuowen, “Feature level fusion method based on the coupled metric learning and its application in gait recognition,” J. Journal of Southeast University ( Natural Science Edition),China.vol. S1,pp.7-11, 2013.
Yang Q, Xue D, “Gait Recognition Based on Sparse Representation and Segmented Frame Difference Energy Image,” J. Information & Control, vol.42pp.27-32,2013.
Huang D Y, Lin T W, Hu W C, et al, “ Gait recognition based on Gabor wavelets and modified gait energy image for human identification,” J. Journal of Electronic Imaging, 2013,vol.22,pp.6931-6946.
Yang Q, Xue D, “Gait Recognition Based on Sparse Representation and Segmented Frame Difference Energy Image,” J.Information & Control, 2013,vol.42,pp.27-32.
BEN Xianye, ZHANG Peng, PAN Tingting, WANG Kejun, “ Performance analysis of matrix gait recognition under linear interpolation framework,” J. CAAI Transactions on Intelligent Systems, 2013, vol.5,pp.415-425.
MA Q Y l, “ Moment Gait Energy Image Based Human Recognition at a Distance,” J. Acta Electronica Sinica, 2012, vol.35,pp.2078-2082.
Lin C L, Wang K J, Li Y, “ Behavior classification algorithm based on enhanced gait energy image and two-dimensional locality preserving projection,” J. Journal of Computer Applications, 2011,vol.31,pp.721-720.
LIUZhi-yong, FENGGuo-can,CHENWei-fu, “ Gait Recognition Based on Local Binary Pattern and Discriminant Common Vector,” J. Computer Science, 2013, vol.9, pp.262-265.
Li Ping, “ Gait Recognition Method Based on n Haar Wavelet and Fused HMMs ,” J. Computer Applications and Software, 2013,vol.3, pp.244-246.
Jia J, Ruan Q, “ Gait recognition basded on Contourlet Transform and Collaborative Representation,” C.ICSP, IEEE, pp.952-957, 2014.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 jing li
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
The articles published in International Journal of Computer and Information Technology (IJCIT) is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
