Skip to content
This code implements self-learning classifier using an Autoencoder and a Softmax classifier and attempts to classify crops using hyperspectral data. However our current result do not outperform the state of the art.
MATLAB C Other
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
softmax_exercise
starter-Pines
stl-pines
stl_exercise
My results.png
README.md
stl_exercise.zip

README.md

Learning From Hyperspectral Data

The code presented here is based on code I wrote to complete the excersises that can be found here link. Once I had implemented and tested the solution I extended the auto encoder and softmax classifier to work on hyperspectral data. However, the current solution does not outperform the state of the art.

alt tag

The figure above shows the ground truth

alt tag

The figure above shows the classification results.

alt tag

This figure above shows a visualization of the hidden layers

alt tag alt tag

These figures above show two spectral bands.

You can’t perform that action at this time.