Band Selection for Hyperspectral Image Classification Using Mutual Information
By Baofeng Guo, Steve R. Gunn, Robert I. Damper, James D. B. Nelson. IEEE Geoscience and Remote Sensing Letters, 2006
402 citations recorded by the source corpus.
Subfields: Atmospheric Science, Ecology, Media Technology
View Paper: https://www.semanticscholar.org/paper/4f86767fe009961e0b8295f3d2e1ceae34335f69
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
- Jon Atli Benediktsson
- Pedram Ghamisi
- Antonio J. Plaza
- Xudong Kang
- Jocelyn Chanussot
- Shutao Li
- Qian Du
- Danfeng Hong
In Ecology
- Qian Du
- Jon Atli Benediktsson
- Pedram Ghamisi
- Jocelyn Chanussot
- Jochem Verrelst
- Xudong Kang
- Michael E. Schaepman
- Antonio J. Plaza
In Media Technology
- Jon Atli Benediktsson
- Antonio J. Plaza
- Jocelyn Chanussot
- Pedram Ghamisi
- Shutao Li
- Danfeng Hong
- Xudong Kang
- Qian Du
Citations in the corpus
- Deep Learning for Classification of Hyperspectral Data: A Comparative Review (2019, neutral): “, using principal component analysis (PCA) [14] or mutual information [15].”
- Earth system science related imaging spectroscopy — an assessment (2009, background): “Listings, hits and regression model are in an amount of available bands—even down to the level of multispectral systems (Chang & Du, 1999; Chang, 1999; Guo et al., 2006).”
- A Novel Ranking-Based Clustering Approach for Hyperspectral Band Selection (2016, methodology): “As for the ranking-based UBS methods, it first quantifies the importance of each band according to a certain criterion, such as nonGaussianity [19], [29], variance [25], mutual information [30], etc.”
- Feature Extraction for Hyperspectral Imagery: The Evolution From Shallow to Deep: Overview and Toolbox (2020, background): “While the latter, BS, which aims at screening out the representative and informative spectral bands, is unfolded with mutual information-based BS [54], rough set, and fuzzy C-means [55], to name a few.”
- Kernel Principal Component Analysis for the Classification of Hyperspectral Remote Sensing Data over Urban Areas (2009, background): “• Band selection using information theory: A collection of ba nds are selected according to their mutual information [14].”
- Hyperspectral Band Selection: A Review (2019, methodology): “Treating a band image and the corresponding reference map as random vectors, the MI criterion [32] was used to evaluate the relative utility of each band for classification.”
- Evaluation of random forest and adaboost tree-based ensemble classification and spectral band selection for ecotope mapping using airborne hyperspectral imagery (2008, methodology): “Many methods have been proposed for band selection (Chang et al., 1999; Guo et al., 2006; Jia & Richards, 1994; Kaewpijit et al., 2003, Lee & Landgrebe, 1997; Melgani & Bruzzone, 2004) but some suggested using a basket of different methods instead of using one method.”