A new search algorithm for feature selection in hyperspectral remote sensing images

By Sebastiano Bruno Serpico, Lorenzo Bruzzone. IEEE Transactions on Geoscience and Remote Sensing, 2001

347 citations recorded by the source corpus.

Subfields: Atmospheric Science, Ecology, Media Technology

View Paper: https://www.semanticscholar.org/paper/c94dec3fc99c4a653afb935d00246f788689c341

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 Ecology

In Media Technology

Citations in the corpus

Classification of hyperspectral remote sensing images with support vector machines (2004, methodology): “Among the search strategies proposed in the literature, it is worth mentioning the basic sequential forward selection (SFS) [10], the more effective sequential forward floating selection [11], and the steepest ascent (SA) techniques [12].”
Fusion of Hyperspectral and LIDAR Remote Sensing Data for Classification of Complex Forest Areas (2008, background): “, sequential forward floating selection (SFFS) [45], steepest ascent [46]), which find a suboptimal solution with a reduced computational cost.”
Feature Mining for Hyperspectral Image Classification (2013, background): “[126] G. Camps-Valls and L. Bruzzone, Kernel Methods for Remote Sensing Data Analysis.”
Clustering-Based Hyperspectral Band Selection Using Information Measures (2007, methodology): “Digital Object Identifier 10.1109/TGRS.2007.904951 This reduction in the hyperspectral representation could be done using feature extraction [1]–[4] or feature selection techniques [5], [6].”
Feature Selection for Classification of Hyperspectral Data by SVM (2010, background): “A wide variety of feature selection methods have been applied to remotely sensed data [30] [31] [32] [33].”
Hyperspectral Band Selection: A Review (2019, methodology): “Aside from simple searching strategies such as the sequential forwardfloating search [21], the branch-and-bound search [57], the steep ascent search, and the constrained search [58], [59], evolutionary algorithms have been adopted for band searching, such as particle swarm optimization (PSO) [21], [”
Distance metrics and band selection in hyperspectral processing with applications to material identification and spectral libraries (2004, methodology): “Moreover, the monotonicity of these familiar quantities has enabled efficient, exhaustive search approaches to identify the optimal subset through branch and bound techniques [6], although even these methods become impractical when the number of features approaches the number of bands in hyperspectr”
Investigation of the random forest framework for classification of hyperspectral data (2005, background): “Alternatively, the input space can be transformed into a reduced feature space via feature selection [5] or feature extraction.”
Hyperspectral Imaging-Based Classification and Wavebands Selection for Internal Defect Detection of Pickling Cucumbers (2013, methodology): “2010), sequential forward selection (Serpico and Bruzzone 2001), and relatively new methods like minimum redundancy–maximum relevance (MRMR) (Peng et al.”
Band Selection for Hyperspectral Image Classification Using Mutual Information (2006, methodology): “Many band-selection techniques have been proposed, such as search-based methods [3]–[6], transform-based methods [7], [8], and informationbased methods [6], [9].”
Tree Species Classification in Boreal Forests With Hyperspectral Data (2013, background): “Among all of the search algorithms present in the literature, such as the branch and bound [26], the steepest ascent [27], and the sequential”
Kernel Principal Component Analysis for the Classification of Hyperspectral Remote Sensing Data over Urban Areas (2009, methodology): “Example of supervised features extraction algorithms are: • Sequential forward/backward selection methods and the imp roved versions of them: these methods select some bands from the original data set [11]–[13].”
Toward an Optimal SVM Classification System for Hyperspectral Remote Sensing Images (2006, methodology): “Based on AVIRIS data, such an analysis was carried out in the original hyperdimensional feature space as well as in hyper-subspaces of various dimensionalities obtained with the feature selection technique described in [8].”
Classification and Segmentation of Satellite Orthoimagery Using Convolutional Neural Networks (2016, background): “There are a number of works that use feature selection methods to select bands from hyperspectral images [69–71].”
A Novel Ranking-Based Clustering Approach for Hyperspectral Band Selection (2016, background): “, feature extraction [9], [10] and band (or feature) selection [11], [12].”