Novel hyperbolic clustering-based band hierarchy (HCBH) for effective unsupervised band selection of hyperspectral images
Authors:
- He SunHSHe Sun
- Lei ZhangLZLei Zhang
- Jinchang RenJRJinchang Ren
- Hua HuangHHHua Huang
- 13 May 2022
- journal article
- research article
- Published by Elsevier in Pattern Recognition
- Vol. 130
Abstract
No abstract availableKeywords
This publication has 31 references indexed in Scilit:
- Semi-supervised dimensionality reduction of hyperspectral imagery using pseudo-labelsPattern Recognition, 2018
- Fast and Robust Self-Representation Method for Hyperspectral Band SelectionIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017
- Unsupervised feature selection based on maximum information and minimum redundancy for hyperspectral imagesPattern Recognition, 2016
- Unsupervised Hyperspectral Band Selection by Dominant Set ExtractionIEEE Transactions on Geoscience and Remote Sensing, 2015
- A Novel Ranking-Based Clustering Approach for Hyperspectral Band SelectionIEEE Transactions on Geoscience and Remote Sensing, 2015
- Novel Two-Dimensional Singular Spectrum Analysis for Effective Feature Extraction and Data Classification in Hyperspectral ImagingIEEE Transactions on Geoscience and Remote Sensing, 2015
- Novel Folded-PCA for improved feature extraction and data reduction with hyperspectral imaging and SAR in remote sensingISPRS Journal of Photogrammetry and Remote Sensing, 2014
- Spherical and Hyperbolic Embeddings of DataIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Spectral–Spatial Hyperspectral Image Classification With Edge-Preserving FilteringIEEE Transactions on Geoscience and Remote Sensing, 2013
- Feature Selection for Classification of Hyperspectral Data by SVMIEEE Transactions on Geoscience and Remote Sensing, 2010