Classification of hyperspectral images by using extended morphological attribute profiles and independent component analysis

Mauro Dalla Mura; Alberto Villa; Jon Atli Benediktsson; Jocelyn Chanussot; Lorenzo Bruzzone

doi:10.1109/LGRS.2010.2091253

Classification of hyperspectral images by using extended morphological attribute profiles and independent component analysis

Mauro Dalla Mura
, Alberto Villa
, Jon Atli Benediktsson
, Jocelyn Chanussot
, Lorenzo Bruzzone

University of Iceland

University of Iceland

Research output: Contribution to journal › Article › peer-review

Abstract

In this letter, a technique based on independent component analysis (ICA) and extended morphological attribute profiles (EAPs) is presented for the classification of hyperspectral images. The ICA maps the data into a subspace in which the components are as independent as possible. APs, which are extracted by using several attributes, are applied to each image associated with an extracted independent component, leading to a set of extended EAPs. Two approaches are presented for including the computed profiles in the analysis. The features extracted by the morphological processing are then classified with an SVM. The experiments carried out on two hyperspectral images proved the effectiveness of the proposed technique.

Original language	English
Article number	5664759
Pages (from-to)	542-546
Number of pages	5
Journal	IEEE Geoscience and Remote Sensing Letters
Volume	8
Issue number	3
DOIs	https://doi.org/10.1109/LGRS.2010.2091253
Publication status	Published - May 2011

Bibliographical note

Funding Information: Manuscript received July 19, 2010; revised October 14, 2010; accepted October 25, 2010. Date of publication December 9, 2010; date of current version April 22, 2011. This work was supported in part by the European community’s Marie Curie Research Training Networks Program, Hyperspectral Imaging Network (HYPER-I-NET), under Contract MRTN-CT-2006-035927 and in part by the Research Fund of the University of Iceland and the University of Trento.

Other keywords

Attribute filters
decision fusion
extended attribute profile (EAP)
independent component analysis (ICA)
mathematical morphology
remote sensing

Access to Document

10.1109/LGRS.2010.2091253

Cite this

@article{1e670c765766429ea0a2fbdb036333d4,

title = "Classification of hyperspectral images by using extended morphological attribute profiles and independent component analysis",

abstract = "In this letter, a technique based on independent component analysis (ICA) and extended morphological attribute profiles (EAPs) is presented for the classification of hyperspectral images. The ICA maps the data into a subspace in which the components are as independent as possible. APs, which are extracted by using several attributes, are applied to each image associated with an extracted independent component, leading to a set of extended EAPs. Two approaches are presented for including the computed profiles in the analysis. The features extracted by the morphological processing are then classified with an SVM. The experiments carried out on two hyperspectral images proved the effectiveness of the proposed technique.",

keywords = "Attribute filters, decision fusion, extended attribute profile (EAP), independent component analysis (ICA), mathematical morphology, remote sensing",

author = "\{Dalla Mura\}, Mauro and Alberto Villa and Benediktsson, \{Jon Atli\} and Jocelyn Chanussot and Lorenzo Bruzzone",

note = "Funding Information: Manuscript received July 19, 2010; revised October 14, 2010; accepted October 25, 2010. Date of publication December 9, 2010; date of current version April 22, 2011. This work was supported in part by the European community{\textquoteright}s Marie Curie Research Training Networks Program, Hyperspectral Imaging Network (HYPER-I-NET), under Contract MRTN-CT-2006-035927 and in part by the Research Fund of the University of Iceland and the University of Trento.",

year = "2011",

month = may,

doi = "10.1109/LGRS.2010.2091253",

language = "English",

volume = "8",

pages = "542--546",

journal = "IEEE Geoscience and Remote Sensing Letters",

issn = "1545-598X",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "3",

}

TY - JOUR

T1 - Classification of hyperspectral images by using extended morphological attribute profiles and independent component analysis

AU - Dalla Mura, Mauro

AU - Villa, Alberto

AU - Benediktsson, Jon Atli

AU - Chanussot, Jocelyn

AU - Bruzzone, Lorenzo

N1 - Funding Information: Manuscript received July 19, 2010; revised October 14, 2010; accepted October 25, 2010. Date of publication December 9, 2010; date of current version April 22, 2011. This work was supported in part by the European community’s Marie Curie Research Training Networks Program, Hyperspectral Imaging Network (HYPER-I-NET), under Contract MRTN-CT-2006-035927 and in part by the Research Fund of the University of Iceland and the University of Trento.

PY - 2011/5

Y1 - 2011/5

N2 - In this letter, a technique based on independent component analysis (ICA) and extended morphological attribute profiles (EAPs) is presented for the classification of hyperspectral images. The ICA maps the data into a subspace in which the components are as independent as possible. APs, which are extracted by using several attributes, are applied to each image associated with an extracted independent component, leading to a set of extended EAPs. Two approaches are presented for including the computed profiles in the analysis. The features extracted by the morphological processing are then classified with an SVM. The experiments carried out on two hyperspectral images proved the effectiveness of the proposed technique.

AB - In this letter, a technique based on independent component analysis (ICA) and extended morphological attribute profiles (EAPs) is presented for the classification of hyperspectral images. The ICA maps the data into a subspace in which the components are as independent as possible. APs, which are extracted by using several attributes, are applied to each image associated with an extracted independent component, leading to a set of extended EAPs. Two approaches are presented for including the computed profiles in the analysis. The features extracted by the morphological processing are then classified with an SVM. The experiments carried out on two hyperspectral images proved the effectiveness of the proposed technique.

KW - Attribute filters

KW - decision fusion

KW - extended attribute profile (EAP)

KW - independent component analysis (ICA)

KW - mathematical morphology

KW - remote sensing

UR - https://www.scopus.com/pages/publications/79955521136

U2 - 10.1109/LGRS.2010.2091253

DO - 10.1109/LGRS.2010.2091253

M3 - Article

SN - 1545-598X

VL - 8

SP - 542

EP - 546

JO - IEEE Geoscience and Remote Sensing Letters

JF - IEEE Geoscience and Remote Sensing Letters

IS - 3

M1 - 5664759

ER -

Classification of hyperspectral images by using extended morphological attribute profiles and independent component analysis

Abstract

Bibliographical note

Other keywords

Access to Document

Fingerprint

Cite this