Research Article
Tensorial Kernel Principal Component Analysis for Action Recognition
Algorithm 1
TKPCA: Kernel Principal Component Analysis of tensor objects.
(1) Tensorial Kernel Function :
| (2) for to do | (3) Compute orthonormal bases from SVD: , | . | (4) Compute by (22). | (5) TKPCA: | (6) Step 1. (Initialization): | (7) Center the input samples by subtracting empirical mean: . | (8) Step 2. (Training): | (9) for to do | (10) for to do | (11) if then | (12) Compute the Kernel Matrix (10): . | (13) Compute the dominant eigenvectors by eign-decomposition (9). | (14) Step 3. (Projection): | (15) For test sample , compute the projections onto each one of the dominant eigenvectors (11), | , . |
|