Research Article
Fast Second-Order Orthogonal Tensor Subspace Analysis for Face Recognition
Input: A set of sample matrices with class label information, , . | Output: left and right transformation matrices and . | (1) Initialize with an identity matrix; | (2) Until convergence Do: | (2.1) Form the matrix ; | (2.2) Form the matrix ; | (2.3) Compute the eigenvectors of the pencil | corresponding to the largest eigenvalues. | (2.4) Set ; | (2.5) Form the matrix ; | (2.6) Form the matrix ; | (2.7) Compute the eigenvectors of the pencil | corresponding to the largest eigenvalues. | (2.8) Set ; | End Do |
|