Clustering-Based Hyperspectral Band Selection Using Information Measures

By Adolfo Martínez Usó, Filiberto Pla, José Martínez Sotoca, Pedro García-Sevilla. IEEE Transactions on Geoscience and Remote Sensing, 2007

520 citations recorded by the source corpus.

Subfields: Atmospheric Science, Biomedical Engineering, Media Technology

View Paper: https://www.semanticscholar.org/paper/59527e01260aeae345713d0e2eb29b3031fb020f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atmospheric Science

1. Antonio J. Plaza
2. Pedram Ghamisi
3. Jon Atli Benediktsson
4. Xudong Kang
5. Jocelyn Chanussot
6. Javier Plaza
7. Juan Mario Haut
8. Mercedes Eugenia Paoletti

In Biomedical Engineering

1. Xudong Kang
2. Jon Atli Benediktsson
3. Pedram Ghamisi
4. Antonio J. Plaza
5. Jocelyn Chanussot
6. Renlong Hang
7. Sen Jia
8. Juan Mario Haut

In Media Technology

1. Antonio J. Plaza
2. Pedram Ghamisi
3. Jon Atli Benediktsson
4. Jocelyn Chanussot
5. Danfeng Hong
6. Javier Plaza
7. Shutao Li
8. Juan Mario Haut

Citations in the corpus

• Deep Pyramidal Residual Networks for Spectral–Spatial Hyperspectral Image Classification (2019, background): “This includes feature extraction [20]–[22], band reduction [23]–[26], data augmentation [27], and active learning techniques [28]–[30], [31].”
• Feature Mining for Hyperspectral Image Classification (2013, methodology): “[82] used a hierarchical clustering structure to group features to minimize the intracluster variance and maximize the intercluster variance.”
• Spectral–Spatial Classification of Hyperspectral Imagery Based on Partitional Clustering Techniques (2009, unknown): “In previous studies, the feature extraction methods appropriate for hyperspectral image analysis, such as the PCA, the ICA, the ISOMAP and clustering-based band selection were considered [39], [42], [50], [51].”
• Feature Extraction for Hyperspectral Imagery: The Evolution From Shallow to Deep: Overview and Toolbox (2020, methodology): “In [32], a hierarchical clustering algorithm was introduced to split and cluster the hyperspectral bands where the representative band for each cluster is selected based on both a mutual information criterion and a divergence-based criterion.”
• Optimal Clustering Framework for Hyperspectral Band Selection (2018, methodology): “About the parameters among them, WaLuDi, UBS, VGBS and E-FDPC are parameter-free so only K is needed to be set.”
• A Novel Ranking-Based Clustering Approach for Hyperspectral Band Selection (2016, background): “Moreover, due to the high correlation among the neighboring bands, which not only increases the computational complexity of the classifiers but also may have a negative impact on the classification accuracy, dimensionality reduction (DR) should be applied as a preprocessing step to discard the redun”