• Stars
    star
    119
  • Rank 297,930 (Top 6 %)
  • Language
    MATLAB
  • License
    MIT License
  • Created over 4 years ago
  • Updated about 3 years ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

This Toolbox includes Hyperspectral Feature Extraction Techniques including Unsupervised, Supervised, and Deep Feature Extraction

Hyperspectral-Shallow-Deep-Feature-Extraction-Toolbox (HyFTech)

HyFTech is a Matlab/Python toolbox, which includes Hyperspectral Feature Extraction Techniques including Unsupervised, Supervised, and Deep Feature Extraction approaches. This toolbox supports a review paper accepted in IEEE Geoscience and Remote Sensing Magazine entitled "Feature Extraction for Hyperspectral Imagery: The Evolution from Shallow to Deep". The link to the paper:

https://arxiv.org/abs/2003.02822

The paper provides a detailed and organized overview of hyperspectral feature extraction techniques, categorized into two general sections: shallow feature extraction techniques (further categorized into supervised and unsupervised) and deep feature extraction techniques. Each section provides a critical overview of the state-of-the-art that is mainly rooted in the signal and image processing, statistical inference, and machine (deep) learning fields. The toolbox also includes the Random Forest classifier plus training and test samples used for the Houston 2013 hyperspectral Dataset. The hyperspectral data can be downloaded here (http://hyperspectral.ee.uh.edu/?page_id=459). The shallow and deep feature extraction techniques given in HyFTech is listed below:

Shallow Unsupervised Feature Extraction:

1- PCA: Principal Component Analysis

2- MSTV: Multi-scale Structural Total Variation

3- OTVCA: Orthogonal Total Variation Component Analysis

4- LPP: Locality Preserving Projection

Shallow Supervised Feature Extraction:

5- LDA: Linear Discriminant Analysis

6- CGDA: Collaborative Graph-based Discriminant Analysis

7- LSDR: Least-Squares Dimension Reduction

8- JPlay: Joint & Progressive Learning Strategy

Deep Feature Extraction:

9- SAE: Stacked Autoencoder

10- RNN: Recurrent Neural Network

11- CNN: Convolutional Neural Network

12- CAE: Convolutional Autoencoder

13- CRNN: Convolutional RNN

14- PCNN: PCA is applied prior to CNN

More Repositories

1

Unmixing_Tutorial_IEEE_IADF

Codes and data for Unmixing
Jupyter Notebook
44
star
2

HySUPP

An Open-Source Hyperspectral Unmixing Python Package
Python
39
star
3

UnDIP

UnDIP: Hyperspectral Unmixing Using Deep Image Prior
Python
36
star
4

MiSiCNet

MiSiCNet: Minimum Simplex Convolutional Network for Deep Hyperspectral Unmixing
Python
13
star
5

HapkeCNN

Blind Nonlinear Unmixing for Intimate Mixtures Using Hapke Model and Convolutional Neural Network
Python
11
star
6

SUnCNN

Sparse Unmixing Using Unsupervised Convolutional Neural Network
Python
8
star
7

Hyperspectral-Image-Denoising-Matlab-Toolbox

This is hyperspectral image denoising Matlab toolbox contains 2D Wavelet denoising (3D Wavelet), 3D Wavelet Denoising (3D Wavelet), First Order Roughness Penalty DeNoising (FORPDN), and Hyperspectral Restoration (HyRes).
6
star
8

Hyperspectral-Image-Denoising-Toolbox-V2

This toolbox contains the following HSI denoising methods
Python
4
star
9

OTVCA

Hyperspectral Feature Extraction Using Total Variation Component Analysis (OTVCA)
3
star
10

Wavelet-Toolbox-Wavelab_fast-

Wavelab_fast is a fast wavelet toolbox for one, two, and three dimensional signals. Wavelab_fast contains wavelet and undecimated wavelet transforms. Wavelet filters must be selected from wavelab toolbox by using MakeONFilter command or from Rice wavelet toolbox by using daubcqf command. Wavelab_fast is written based on modifying some codes from Wavelab and adding some codes for higher dimensional signals and implementing undecimated wavelet transform using algorithm a trous. The codes provided are much faster than the ones from wavelab for 2D and 3D signals. That has been done by skipping loops on pixels. ***The toolbox is recommended for applying on large 2D and 3D datasets. Also, in the case of having many 1D signals instead of using for loop.*** *** The code can only be used for academic purposes and the code must be cited by its DOI given by RG.*** *** To request for the password please send an email to [email protected]
MATLAB
3
star
11

HyMiNoR

Hyperspectral Mixed Gaussian and Sparse Noise Reduction
2
star
12

SubFus

SubFus is a multisensor remote sensing image classification technique based on subspace sensor fusion.
2
star
13

SSLRA

Hyperspectral Feature Extraction Using Sparse and Smooth Low-Rank Analysis
2
star
14

HySURE

HySURE is a technique for Hyperspectral Subspace Identification using SURE.
1
star
15

FUnmix

Fast Unmixing Using Alternating Method of Multipliers
Python
1
star
16

SUnAA

Sparse Unmixing using Archetypal Analysis
Python
1
star