Spectral and Spatial Classification of Hyperspectral Data Using SVMs and Morphological Profiles

By Mathieu Fauvel, Jon Atli Benediktsson, Jocelyn Chanussot, Johannes R. Sveinsson. IEEE Transactions on Geoscience and Remote Sensing, 2008

1,156 citations recorded by the source corpus.

Subfields: Atmospheric Science, Media Technology, Ocean Engineering

View Paper: https://www.semanticscholar.org/paper/3ef69a362b1525846d1c4d7b11aa9472208473e3

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 Media Technology

In Ocean Engineering

Citations in the corpus

Spectral–Spatial Feature Tokenization Transformer for Hyperspectral Image Classification (2022, neutral): “For the optimal extraction of image spatial features, a variety of mathematical morphological operators have been developed, such as morphological profile (MP) [28], extended MP (EMP) [29], and extended multiattribute profile (EMAP) [30].”
Local Binary Patterns and Extreme Learning Machine for Hyperspectral Imagery Classification (2015, background): “, opening and closing), which is widely used for modeling structural information, was introduced in [10].”
Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks (2016, methodology): “In [20], a method was introduced based on the fusion of morphological operators and support vector machine (SVM), which leads to high classification”
A Survey on Spectral–Spatial Classification Techniques Based on Attribute Profiles (2015, methodology): “However, they can influence the shape of the structures and can introduce fake objects in the image [32].”
Medical hyperspectral imaging: a review (2014, background): “144 Due to its strong theoretical foundation, good generalization capability, low sensitivity to the curse of dimensionality, 145 and ability to find global classification solutions, SVM is usually preferred by many researchers over other classification paradigms.”
Deep Learning-Based Classification of Hyperspectral Data (2014, methodology): “In [32], the proposed method based on the fusion of morphological information and original data followed by SVM provides good classification results.”
A new deep convolutional neural network for fast hyperspectral image classification (2017, background): “In this sense, support vectormachines (SVMs) (Scholkopf and Smola, 2001) and multinomial logistic regression (MLR) (Böhning, 1992) have been proved to be very useful for the supervised classification of hyperspectral images due to their ability to deal with large input spaces (Melgani and Bruzzone, ”
Semi-supervised hyperspectral image segmentation (2009, methodology): “improve the classification accuracy, some methods have integrated spatial (contextual) information [7, 8, 10].”
A Survey of Active Learning Algorithms for Supervised Remote Sensing Image Classification (2011, background): “The complexity of the problem, the limited temporal and financial resources, as well as the high intraclass variance can make an algorithm fail if it is trained with a suboptimal dataset.”
Spectral–spatial classification of hyperspectral images using deep convolutional neural networks (2015, methodology): “…accuracies in terms of OA, AA and κ coefficient than those obtained by an SVM-based classifier trained with extended morphological profiles (SVM/EMP) (Fauvel et al. 2008), quadratic discriminant analysis with the MLL spatial prior (QDAMLL), logistic discriminant analysis with the MLL spatial prior…”
A Spectral-Spatial-Dependent Global Learning Framework for Insufficient and Imbalanced Hyperspectral Image Classification (2021, methodology): “Traditional hyperspectral image classiﬁcation usually carries out feature extraction first and then classifies HSI by various classifiers, such as multinomial logistic regression (MLR), maximum likelihood classification (MLC), and support vector machine (SVM) [10, 11].”