DocumentCode
1947962
Title
Notice of Retraction
Gait recognition using the temporal information of leg angles
Author
Weihua He ; Ping Li
Author_Institution
Key Lab. of Optoelectron. Technol. & Syst. of the Educ. Minist. of China, Chongqing Univ., Chongqing, China
Volume
5
fYear
2010
fDate
9-11 July 2010
Firstpage
78
Lastpage
83
Abstract
Notice of Retraction
After careful and considered review of the content of this paper by a duly constituted expert committee, this paper has been found to be in violation of IEEE´s Publication Principles.
We hereby retract the content of this paper. Reasonable effort should be made to remove all past references to this paper.
The presenting author of this paper has the option to appeal this decision by contacting TPII@ieee.org.
Gait recognition is of increasing interest recently. A gait recognition method using the temporal information of leg angles is proposed, based on the fact that changes of leg angles can reflect main trait of a man´s moving. First the pendulum model is referred to for extracting leg parts, and least-square method is used for boundary fitting, to obtain the temporal information of angle about thigh and shin. Then, the acquired temporal information is expanded in Fourier series form, in consideration of walking activity´s periodic property. Genetic algorithm is subsequently adopted to search for the harmonic coefficients, which are normalized to produce the gait signature. Finally, NN and ENN classifiers are both applied to do the sorting task. Experimental results on CMU database show that the proposed method has high recognition rates. Furthermore, self-occlusion problem, which may often be encountered in gait recognition, is well handled by this method.
After careful and considered review of the content of this paper by a duly constituted expert committee, this paper has been found to be in violation of IEEE´s Publication Principles.
We hereby retract the content of this paper. Reasonable effort should be made to remove all past references to this paper.
The presenting author of this paper has the option to appeal this decision by contacting TPII@ieee.org.
Gait recognition is of increasing interest recently. A gait recognition method using the temporal information of leg angles is proposed, based on the fact that changes of leg angles can reflect main trait of a man´s moving. First the pendulum model is referred to for extracting leg parts, and least-square method is used for boundary fitting, to obtain the temporal information of angle about thigh and shin. Then, the acquired temporal information is expanded in Fourier series form, in consideration of walking activity´s periodic property. Genetic algorithm is subsequently adopted to search for the harmonic coefficients, which are normalized to produce the gait signature. Finally, NN and ENN classifiers are both applied to do the sorting task. Experimental results on CMU database show that the proposed method has high recognition rates. Furthermore, self-occlusion problem, which may often be encountered in gait recognition, is well handled by this method.
Keywords
Fourier series; gait analysis; genetic algorithms; gesture recognition; search problems; temporal databases; CMU database; Fourier series; Genetic algorithm; boundary fitting; class exemplar; gait recognition; gait signature; leg angle; nearest neighbor classifier; pendulum method; temporal information; Analytical models; Artificial neural networks; Biological system modeling; Databases; Irrigation; Receivers; Thigh; angle; biometrics; gait recognition; genetic algorithm; periodicity;
fLanguage
English
Publisher
ieee
Conference_Titel
Computer Science and Information Technology (ICCSIT), 2010 3rd IEEE International Conference on
Conference_Location
Chengdu
Print_ISBN
978-1-4244-5537-9
Type
conf
DOI
10.1109/ICCSIT.2010.5564509
Filename
5564509
Link To Document