%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%    USF/NIST Gait Challenge data sets Version 1.7 as 128x88x20 tensors       %
%                                                                             %
% Author: Haiping LU                                                          %
% Email : hplu@ieee.org                                                       %
% Affiliation: Department of Electrical and Computer Engineering              %
%              University of Toronto                                          %
% Release date: February 29, 2008                                             %
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

%[Data]%
The gait sample size is 128x88x20. The gait data provided here are obtained 
from the USF/NIST Gait Challenge data sets Version 1.7. through the procedures 
described in Section V.B.2 of the paper "MPCA_TNN08Jan.pdf":
	Haiping Lu, K.N. Plataniotis, and A.N. Venetsanopoulos, 
	"MPCA: Multilinear Principal Component Analysis of Tensor Objects", 
	IEEE Transactions on Neural Networks, 
	Vol. 19, No. 1, Page: 18-39, January 2008.


%[Usages for Gait Recognition]%
Please download the MPCA (and MPCA+LDA) codes provided at the same webpage as 
this data for feature extraction. For matching or recognition, please refer to 
Section IV.C and Section V.B.3 of the paper above.


%[Restriction]%
In all documents and papers reporting research work that uses the data provided
here, the respective author(s) must reference the following paper: 
[1]	Haiping Lu, K.N. Plataniotis, and A.N. Venetsanopoulos, 
	"MPCA: Multilinear Principal Component Analysis of Tensor Objects", 
	IEEE Transactions on Neural Networks, 
	Vol. 19, No. 1, Page: 18-39, January 2008.


%[Comment/Question?]%
Please send your comment or question to hplu@ieee.org