| DEMO_PCACOMP | |
Demo on image compression using PCA
Description:
The PCA model is trained to model rectangular non-overlapping
patches of a specified input image. The compression phase
involves representation of the image patches in the lower
dimesional space trained by the PCA. The decompression consists
of reconstruction of the image patches from their low dimensional
representation.
Note: This demo requires Images toolbox.
See also
PCA, LINPROJ, PCAREC.
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:
06-jun-2004, VF