Linear Versus Nonlinear PCA for the Classification of Hyperspectral Data Based on the Extended Morphological Profiles

By Giorgio A. Licciardi, Prashanth Reddy Marpu, Jocelyn Chanussot, Jon Atli Benediktsson. IEEE Geoscience and Remote Sensing Letters, 2012

362 citations recorded by the source corpus.

Subfields: Atmospheric Science, Ecology, Media Technology

View Paper: https://www.semanticscholar.org/paper/9220b70397ead8924d9028b89648c2ee5f5f8126

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. Shutao Li
2. Pedram Ghamisi
3. Jon Atli Benediktsson
4. Yushi Chen
5. Xudong Kang
6. Qian Du
7. Antonio J. Plaza
8. Xuanlin Xiang

In Ecology

1. Shutao Li
2. Qian Du
3. Pedram Ghamisi
4. Xudong Kang
5. Yushi Chen
6. Xiuping Jia
7. Saurabh Prasad
8. Rob Heylen

In Media Technology

1. Shutao Li
2. Pedram Ghamisi
3. Jon Atli Benediktsson
4. Yushi Chen
5. Xudong Kang
6. Antonio J. Plaza
7. Qian Du
8. Leyuan Fang

Citations in the corpus

• Deep Learning for Hyperspectral Image Classification: An Overview (2019, neutral): “[13], [14], independent component analysis (ICA) [15], and linear discriminant analysis (LDA) [16].”
• Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks (2016, methodology): “In this set of experiments, CNN was compared with the PCA, factor analysis (FA), and locally linear embedding (LLE) in order to investigate the potential of CNN for hyperspectral spectral FE.”
• A Review of Nonlinear Hyperspectral Unmixing Methods (2014, positive): “Note that this technique can be augmented to behave as a fuzzy classifier as well [131], and can be used on extended morphological profiles instead of reflectance data for classification purposes also [133].”
• Hyperspectral Unmixing Overview: Geometrical, Statistical, and Sparse Regression-Based Approaches (2012, neutral): “To achieve flexibility, some have resorted tomachine learning strategies such as neural networks [64]–[70], to nonlinearly reduce dimensionality or learn model parameters in a supervised fashion from a collection of examples (see [35] and references therein).”
• Hyperspectral and LiDAR Data Fusion: Outcome of the 2013 GRSS Data Fusion Contest (2014, background): “In recent years, various techniques have been developed for effective feature extraction (FE), feature selection, semi-supervised, active learning, and ensemble classification of hyperspectral imagery [1]–[11].”
• PCA-Based Edge-Preserving Features for Hyperspectral Image Classification (2017, methodology): “Some classical signal analysis tools, such as the principal component analysis (PCA) [15], [19], [20], the independent component analysis (ICA) [16], singular spectrum analysis (SSA) [21], and the manifold learning [17] methods, have been successfully applied for feature extraction of HSIs.”
• A Review on Deep Learning in UAV Remote Sensing (2021, methodology): “The classic approach to address high dimensionality is by applying a Principal Component Analysis (PCA) [120].”
• Spectral–Spatial Feature Tokenization Transformer for Hyperspectral Image Classification (2022, methodology): “In addition, several methods for dimension reduction and spectral information extraction have also been developed, including the principal component analysis (PCA) [22], [23], the independent component analysis (ICA) [24], and the linear discriminant analysis (LDA) [25]–[27].”
• A survey: Deep learning for hyperspectral image classification with few labeled samples (2021, methodology): “For the approaches based on dimension reduction, principle component analysis [17], independent component analysis [18], linear discriminant analysis [19], and low-rank [20] are widely used.”