Classification of hyperspectral remote sensing images with support vector machines

By Farid Melgani, Lorenzo Bruzzone. IEEE Transactions on Geoscience and Remote Sensing, 2004

4,077 citations recorded by the source corpus.

Subfields: Atmospheric Science, Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/2badd8953397d757693859918cf9318fe7ec5e3b

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

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Deep Learning for Classification of Hyperspectral Data: A Comparative Review (2019, neutral): “Classification is then processed in a standard way, by using common statistical models: decision trees and random forests [22], SVMs [23], [24], and so on.”
Deep Learning-Based Classification of Hyperspectral Data (2014, methodology): “In [21], a promising classification method, support vector machine (SVM), is introduced for hyperspectral data classification.”
A Multilevel Context-Based System for Classification of Very High Spatial Resolution Images (2006, methodology): “However, other multiclass strategies could be considered (see [ 22 ]).”
Spectral–Spatial Hyperspectral Image Classification With Edge-Preserving Filtering (2014, background): “Digital Object Identifier 10.1109/TGRS.2013.2264508 images [6], e.g., random forests [7], [8], neural networks [9], [10], AdaBoost [11], support vector machines (SVMs) [12], sparse representation [13], [14], and active learning [15]–[17] methods.”
Multisource Remote Sensing Data Classification Based on Convolutional Neural Network (2018, methodology): “Numerous classification methods using HSI data have been developed [11]–[15].”
Deep Convolutional Neural Networks for Hyperspectral Image Classification (2015, methodology): “In the current literatures, support vector machine (SVM) [5, 6] has been viewed as an efficient and stable method for hyperspectral classification tasks, especially for the small training sample sizes.”
Exploring Models and Data for Remote Sensing Image Caption Generation (2017, background): “However, the studies of the remote sensing images are still concentrate on scene classification [5], [16]–[19], object recognition [20], [21], and segmentation [22]–[25].”
A Novel Transductive SVM for Semisupervised Classification of Remote-Sensing Images (2006, methodology): “According to the analysis presented in Section II, in all experiments, we considered an OAA multiclass architecture [ 12 ], [24].”
Medical hyperspectral imaging: a review (2014, methodology): “SVM has been proved to perform well for classifying hyperspectral data.(137) In the processing of medical hyperspectral data, SVM has also been explored for various classification tasks.”
Statistics of real-world hyperspectral images (2011, background): “Hyperspectral images, meaning those that provide a dense spectral sampling at each pixel, have proven useful in many domains, including remote sensing [2, 3, 5, 22, 35], medical diagnosis [10, 29, 33], and biometrics [31], and it seems likely that they can simplify the analysis of everyday scenes as”
Hyperspectral and Multispectral Data Fusion: A comparative review of the recent literature (2017, methodology): “Support vector machines (SVMs) [83] and rotation forests (RoFs) [84] were adopted as classifiers because of their good performance for classifying HS data with a small number of training samples [85], [86].”
A deep learning framework for hyperspectral image classification using spatial pyramid pooling (2016, methodology): “SVM-based hyperspectral image classi ﬁ cation algorithms were the state-of-the-art techniques for a long time (Melgani and Bruzzone 2004).”
Noise Reduction in Hyperspectral Imagery: Overview and Application (2018, methodology): “Base Classifier Index HSI 2D-Wavelet 3D-Wavelet FORPDN LRMR NAILRMA HyRes ELM OA 79.55 79.31 81.25 79.07 83.55 84.63 80.72 AA 82.4 81.91 83.47 81.94 85.13 86.16 82.88 K 0.7783 0.7753 0.7964 0.7728 0.8214 0.8331 0.7906 SVM OA 80.18 80.29 80.22 79.97 79.49 79.92 80.46 AA 83.05 82.87 82.97 82.65 82.28 ”
Assessing object-based classification: advantages and limitations (2009, background): “…(SVM), in all classifications for its generally good performance in dealing with a large number of features without heavily relying on feature selection (Melgani and Bruzzone 2004, Huang et al. 2009), although some studies have shown that SVM can benefit from feature selection (Navot et al .”