Kernel-based methods for hyperspectral image classification

By Gustau Camps-Valls, Lorenzo Bruzzone. IEEE Transactions on Geoscience and Remote Sensing, 2005

1,515 citations recorded by the source corpus.

Subfields: Analytical Chemistry, Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/9b416ec0b8a787ed4f0cd2dcc00cf083d47104c6

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Analytical Chemistry

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Hyperspectral Remote Sensing Data Analysis and Future Challenges (2013, methodology): “In this context, kernel methods such as the support vector machine (SVM) have been widely used in order to deal effectively with the Hughes phenomenon [85], [86].”
Hyperspectral Image Classification—Traditional to Deep Models: A Survey for Future Prospects (2021, positive): “These multi-scale spatial features are fused together and further joined with PCS extracted spectral features for final classification via SVM.”
Big Data for Remote Sensing: Challenges and Opportunities (2016, methodology): “Here, we used popular classifiers such as the support vector machine (SVM) [50]–[52], backpropagation neural networks [53], [54], and the k -nearest neighbor classifier [28].”
Transform Coding Techniques for Lossy Hyperspectral Data Compression (2007, methodology): “In developing the signatures and carrying out the classification, we have closely followed the approach outlined in [35] .”
Semi-Supervised Graph-Based Hyperspectral Image Classification (2007, methodology): “This has been also observed in [12] and [50] and can be explained because grass, pasture, trees, and woods are homogeneous areas which Fig.”
Hyperspectral Image Classification With Independent Component Discriminant Analysis (2011, methodology): “pared in [17] a number of these methods.”
Unsupervised Deep Feature Extraction for Remote Sensing Image Classification (2015, background): “However, a number of (critical) free parameters are to be tuned; regularization is an important issue, which is mainly addressed by limiting the network’s structure heuristically; and only shallow structures are considered mainly due to the limitations on computational resources and efficiency of…”
A Review of Nonlinear Hyperspectral Unmixing Methods (2014, methodology): “While kernels have been used in hyperspectral image processing for target detection [134] and image classification [135]–[137], this idea has recently been exploited in several unmixing applications as well.”
Mean Map Kernel Methods for Semisupervised Cloud Classification (2010, methodology): “SVMs are accurate nonlinear robust classifiers [17]–[19], which have been successfully used in RS data classification [20], [21].”
SVM- and MRF-Based Method for Accurate Classification of Hyperspectral Images (2010, methodology): “Most classiﬁcation methods process each pixel independently without considering the correlations between spatially adjacent pixels (so-called pixelwise classiﬁers) [2], [3].”
SVM-Based Fuzzy Decision Trees for Classification of High Spatial Resolution Remote Sensing Images (2012, background): “SVM is another valuable classifier with increasing interest during the past years for the classification of multispectal and hyperspectral images [21], [22].”
Monitoring Land-Cover Changes: A Machine-Learning Perspective (2016, background): “The existing nonlinear classification approaches that have attempted to handle the diversity or multimodality within the data by making use of kernel-based methods include [10] and [14].”
A review of neural networks in plant disease detection using hyperspectral data (2018, background): “Generally, it happens where the ratio of number of training pixels or the number of spectral bands are above the minimum value to achieve statistical fit [149].”
Deep Pyramidal Residual Networks for Spectral–Spatial Hyperspectral Image Classification (2019, methodology): “Support vector machines (SVMs) and kernel-based methods [13], statistical procedures as principal”