TRAIN_KPCA_DENOIS | ![]() |
Training of kernel PCA model for image denoising.
Description:
The kernel PCA model is trained to describe an input
class of images corrupted by noise [Mika99b]. The training
data contains images corrupted by noise and corresponding
ground truth. The free paramaters of the kernel PCA
are tuned by cross-validation. The objective function
is a sum of squared differences between ground truth
images and reconstructed images. The greedy KPCA algorithm
is used to train the kernel PCA model.
See also
GREEDYKPCA, KPCAREC, KPCA.
About: Statistical Pattern Recognition Toolbox
(C) 1999-2003, Written by Vojtech Franc and Vaclav Hlavac
Czech Technical University Prague
Faculty of Electrical Engineering
Center for Machine Perception
Modifications:
07-jun-2004, VF
06-jun-2004, VF
17-mar-2004, VF