Conference paper
Parameter optimization in the regularized kernel minimum noise fraction transformation
National Space Institute, Technical University of Denmark1
Geodesy, National Space Institute, Technical University of Denmark2
Department of Informatics and Mathematical Modeling, Technical University of Denmark3
Image Analysis and Computer Graphics, Department of Informatics and Mathematical Modeling, Technical University of Denmark4
Based on the original, linear minimum noise fraction (MNF) transformation and kernel principal component analysis, a kernel version of the MNF transformation was recently introduced. Inspired by we here give a simple method for finding optimal parameters in a regularized version of kernel MNF analysis.
We consider the model signal-to-noise ratio (SNR) as a function of the kernel parameters and the regularization parameter. In 2-4 steps of increasingly refined grid searches we find the parameters that maximize the model SNR. An example based on data from the DLR 3K camera system is given.
| Language: | English |
|---|---|
| Publisher: | IEEE |
| Year: | 2012 |
| Pages: | 370-373 |
| Proceedings: | 2012 IEEE International Geoscience and Remote Sensing SymposiumIEEE International Geoscience and Remote Sensing Symposium |
| Series: | Ieee International Geoscience and Remote Sensing Symposium |
| ISBN: | 1467311588 , 1467311596 , 146731160X , 146731160x , 9781467311588 , 9781467311595 and 9781467311601 |
| ISSN: | 21537003 and 21536996 |
| Types: | Conference paper |
| DOI: | 10.1109/IGARSS.2012.6351561 |
| ORCIDs: | Nielsen, Allan Aasbjerg |
Cameras DLR 3K camera system Eigenvalues and eigenfunctions Kernel MNF transformation Noise measurement Optimization Signal to noise ratio geophysical image processing geophysical techniques kernel MNF analysis kernel principal component analysis linear minimum noise fraction transformation optimal parameters optimisation parameter optimization principal component analysis regularization parameter regularized kernel minimum noise fraction transformation signal-to-noise ratio
