Hyperspectral Image Classification Based on Sparse Modeling of Spectral Blocks

  title={Hyperspectral Image Classification Based on Sparse Modeling of Spectral Blocks},
  author={Saeideh Ghanbari Azar and Saeed Meshgini and Tohid Yousefi Rezaii and Soosan Beheshti},

A three layer spatial-spectral hyperspectral image classification model using guided median filters

An efficient, three-layer hyperspectral image classification model by utilizing spectral/spatial features and a new proximity-based 2D edge preserving order-statistic filtering called Guided Median Filter (GMF) is introduced with weights assigned to each neighboring pixel.

Dual-Concentrated Network With Morphological Features for Tree Species Classification Using Hyperspectral Image

A dual-concentrated network with morphological features (DNMF) is proposed to solve the dilemma of forest tree species classification and achieves clearly better classification performance over other competitive baselines.

Wide and Deep Fourier Neural Network for Hyperspectral Remote Sensing Image Classification

A wide and deep Fourier network to learn features efficiently by using pruned features extracted in the frequency domain by composed of multiple wide Fourier layers to extract hierarchical features layer-by-layer efficiently.

Wide Sliding Window and Subsampling Network for Hyperspectral Image Classification

A wide sliding window and subsampling network (WSWS Net) for HSI classification based on layers of transform kernels with sliding windows and subsAMpling (W SWS) that can learn higher level spatial and spectral features efficiently and be trained easily by only computing linear weights with least squares.

Tensor Dictionary Self-Taught Learning Classification Method for Hyperspectral Image

A tensor-based dictionary self-taught learning (TDSL) classification method to provide some insight into these challenges of precise object classification based on Hyperspectral imagery with limited training data is proposed.

Dynamic Wide and Deep Neural Network for Hyperspectral Image Classification

The experimental results showed that the proposed DWDNN had the highest test accuracies compared to both the typical machine learning methods such as support vector machine (SVM), multilayer perceptron (MLP), radial basis function (RBF), and the recently proposed deep learning methods including the 2D convolutional neural network (CNN) and the 3D CNN designed for HSI classification.

A Pseudo-Label Guided Artificial Bee Colony Algorithm for Hyperspectral Band Selection

A pseudo-label guided artificial bee colony band selection algorithm with hypergraph clustering (HC-ABC) to remove redundant and noise bands and can obtain a band subset with high classification accuracy for all the three classifiers, KNN, Random Forest, and SVM.

Deep plug-and-play prior for hyperspectral image restoration



Spatial-Aware Dictionary Learning for Hyperspectral Image Classification

A structured dictionary-based model for hyperspectral data that incorporates both spectral and contextual characteristics of spectral samples and is capable of finding representations that may effectively be used for classification of multispectral resolution samples is presented.

Feature extraction of hyperspectral images using wavelet and matching pursuit

  • P. Hsu
  • Environmental Science
  • 2007

Hyperspectral Image Classification Using Dictionary-Based Sparse Representation

Experimental results show that the proposed sparsity-based algorithm for the classification of hyperspectral imagery outperforms the classical supervised classifier support vector machines in most cases.

Learning Discriminative Sparse Representations for Modeling, Source Separation, and Mapping of Hyperspectral Imagery

Results when the data have been significantly undersampled and then reconstructed are presented, still retaining high-performance classification, showing the potential role of compressive sensing and sparse modeling techniques in efficient acquisition/transmission missions for hyperspectral imagery.

Low-rank group inspired dictionary learning for hyperspectral image classification

Contextual Online Dictionary Learning for Hyperspectral Image Classification

A contextual online dictionary learning (DL) method for HSIs classification is proposed, which learns a dictionary over the whole image rather than few labeled pixels, and can effectively and efficiently improve the adaptive representation capability of different pixels with an online learning mechanism.

Hyperspectral Image Classification Via Shape-Adaptive Joint Sparse Representation

A new shape-adaptive joint sparse representation classification (SAJSRC) method is proposed for hyperspectral images (HSIs) classification. The proposed method adaptively explores the spatial

Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks

This paper proposes a 3-D CNN-based FE model with combined regularization to extract effective spectral-spatial features of hyperspectral imagery and reveals that the proposed models with sparse constraints provide competitive results to state-of-the-art methods.

Hyperspectral image classification via a random patches network