Generalized Composite Kernel Framework for Hyperspectral Image Classification

By Jun Yu Li, Prashanth Reddy Marpu, Antonio J. Plaza, José M. Bioucas-Dias, Jon Atli Benediktsson. 2013

474 citations recorded by the source corpus.

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

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 Ecology

In Media Technology

In Remote Sensing

Citations in the corpus

Advances in Hyperspectral Image and Signal Processing: A Comprehensive Overview of the State of the Art (2017, methodology): “Therefore, the approach has been modified to deal with convex combinations of kernels through generalized composite kernels (GCK) [122], the results of which are shown in Table 4, and multiple-kernel learning [123].”
A Survey on Spectral–Spatial Classification Techniques Based on Attribute Profiles (2015, methodology): “In [51], various supervised and unsupervised FE methods were compared when EMAPs were built using corresponding features and classified using RF and SVM classifiers.”
Hyperspectral Image Classification With Deep Learning Models (2018, methodology): “Rigorous experiments were conducted based on six publicly available hyperspectral image data sets, and our experimental results confirm the superiority of these deep learning methods when compared to traditional machine learning methods, such as LORSAL, MFL, GCK, SVM-3-D, and SVM-CK.”
Diverse Region-Based CNN for Hyperspectral Image Classification (2018, background): “With high spectral resolution, HSI has unique advantages for finer classification [11], [12], because it can uncover and reveal subtle spectral characteris-”
Spectral–Spatial Hyperspectral Image Classification via Multiscale Adaptive Sparse Representation (2014, methodology): “In [15] and [16], the spectral and spatial information of each HSI pixel is combined via a composite kernel approach.”
Unsupervised Spectral–Spatial Feature Learning With Stacked Sparse Autoencoder for Hyperspectral Imagery Classification (2015, background): “[10] propose generalized composite kernel machines for hyperspectral image classification.”
Deep Learning for Hyperspectral Image Classification: An Overview (2019, background): “For example, in [19] and [20], extended morphological”
Classification of Hyperspectral Images by Exploiting Spectral–Spatial Information of Superpixel via Multiple Kernels (2015, methodology): “In [23, 24], the extended morphological profiles (EMP) is used to exploit the spatial information, which can effectively improve the estimation.”
Learning and Transferring Deep Joint Spectral–Spatial Features for Hyperspectral Classification (2017, background): “The MP features can also be combined with spectrum through linearly concatenation [5] or composite kernel learning [6].”
Classification of Hyperspectral Image Based on Double-Branch Dual-Attention Mechanism Network (2019, background): “Two types of low-level features, morphological profiles [14] and Gabor feature [15], were designed to represent the spatial information.”
Multisource Remote Sensing Data Classification Based on Convolutional Neural Network (2018, background): “With the advantage of distinguishing subtle spectral difference, classiﬁcation tasks with HSI have been applied in various ﬁelds, including deforestation, land cover mapping, and mineral exploration [1]–[5].”
Spectral–Spatial Residual Network for Hyperspectral Image Classification: A 3-D Deep Learning Framework (2018, unknown): “publications [3], [15].”
Hyperspectral Remote Sensing Data Analysis and Future Challenges (2013, methodology): “Recently, composite kernels have been generalized in [98], using the MLR METRIC LDA QDA LogDA SVM MLR MLRsub”
HSI-BERT: Hyperspectral Image Classification Using the Bidirectional Encoder Representation From Transformers (2020, background): “[4], which can balance the use of spectral and spatial information without any weighting parameter [2].”
Hyperspectral Image Classification Using Deep Pixel-Pair Features (2017, background): “Taking advantage of the rich spectral information, classification using hyperspectral data has been developed for a variety of applications [1]–[6], such as landuse land-cover mapping, mineral exploration, water pollution detection, etc.”
Spectral-Spatial Attention Networks for Hyperspectral Image Classification (2019, background): “[10] constructed a family of generalized composite kernels by utilizing spectral and spatial information from HSI data.”
Multiple Feature Learning for Hyperspectral Image Classification (2015, methodology): “The resulting generalized CK (GCK)-based MLR can combine multiple kernels without any restriction of convexity.”