|
In this application the classification of spectra of retinal images can be examined.
The classification is based on one-dimensional self-organizing maps.
User can choose an image and the desired number of units in map ("10"-"60").
A color-coded RGB image and a histogram over the units will be shown as result. The color-coded
image is generated by finding the closest unit to each spectrum in the spectral image and replacing
the spectrum by the RGB-triplet assigned to that unit.
In this application the original spectral images have been used as training data such as the training data has consisted of all spectra of these three images. |
Main
Some Material
Images
RGB channels
Spectral channels
Eigenvectors and inner product images
Retinal Images A
Retinal Images B
Classification of spectra
Images under blackbody radiator
RGB models
Color-defective vision
Chicken vision simulation
Effect of Illumination
Spectral image reconstruction
Applets
Useful Material
RGB channels Spectral channels Eigenvectors and inner product images Retinal Images A Retinal Images B Classification of spectra Images under blackbody radiator RGB models Color-defective vision Chicken vision simulation Effect of Illumination Spectral image reconstructionRetinal Images A