Multi-feature adaptive classifiers for SAR image segmentation

Michele Ceccarelli, Alfredo Petrosino

Research output: Contribution to journalArticle

29 Citations (Scopus)

Abstract

We propose a multifeature scheme for terrain classification in SAR image analysis. Different neural classifiers, trained on different features of the same sample space, are combined by using a non-linear ensemble method. The feature extraction modules are chosen in order to discover the textural and contextual characteristics within the neighbourhood of each pixel. Comparisons with classical data fusion techniques and consensus schema are reported.

Original languageEnglish
Pages (from-to)345-363
Number of pages19
JournalNeurocomputing
Volume14
Issue number4
DOIs
Publication statusPublished - 20 Mar 1997
Externally publishedYes

Fingerprint

Data fusion
Image segmentation
Image analysis
Feature extraction
Classifiers
Pixels

Keywords

  • ensemble classification
  • image segmentation
  • neural networks

ASJC Scopus subject areas

  • Artificial Intelligence
  • Cellular and Molecular Neuroscience

Cite this

Multi-feature adaptive classifiers for SAR image segmentation. / Ceccarelli, Michele; Petrosino, Alfredo.

In: Neurocomputing, Vol. 14, No. 4, 20.03.1997, p. 345-363.

Research output: Contribution to journalArticle

Ceccarelli, Michele ; Petrosino, Alfredo. / Multi-feature adaptive classifiers for SAR image segmentation. In: Neurocomputing. 1997 ; Vol. 14, No. 4. pp. 345-363.
@article{88767b6ee59d4fa98bc3eaa9d0643883,
title = "Multi-feature adaptive classifiers for SAR image segmentation",
abstract = "We propose a multifeature scheme for terrain classification in SAR image analysis. Different neural classifiers, trained on different features of the same sample space, are combined by using a non-linear ensemble method. The feature extraction modules are chosen in order to discover the textural and contextual characteristics within the neighbourhood of each pixel. Comparisons with classical data fusion techniques and consensus schema are reported.",
keywords = "ensemble classification, image segmentation, neural networks",
author = "Michele Ceccarelli and Alfredo Petrosino",
year = "1997",
month = "3",
day = "20",
doi = "10.1016/S0925-2312(96)00038-0",
language = "English",
volume = "14",
pages = "345--363",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier",
number = "4",

}

TY - JOUR

T1 - Multi-feature adaptive classifiers for SAR image segmentation

AU - Ceccarelli, Michele

AU - Petrosino, Alfredo

PY - 1997/3/20

Y1 - 1997/3/20

N2 - We propose a multifeature scheme for terrain classification in SAR image analysis. Different neural classifiers, trained on different features of the same sample space, are combined by using a non-linear ensemble method. The feature extraction modules are chosen in order to discover the textural and contextual characteristics within the neighbourhood of each pixel. Comparisons with classical data fusion techniques and consensus schema are reported.

AB - We propose a multifeature scheme for terrain classification in SAR image analysis. Different neural classifiers, trained on different features of the same sample space, are combined by using a non-linear ensemble method. The feature extraction modules are chosen in order to discover the textural and contextual characteristics within the neighbourhood of each pixel. Comparisons with classical data fusion techniques and consensus schema are reported.

KW - ensemble classification

KW - image segmentation

KW - neural networks

UR - http://www.scopus.com/inward/record.url?scp=0031579684&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031579684&partnerID=8YFLogxK

U2 - 10.1016/S0925-2312(96)00038-0

DO - 10.1016/S0925-2312(96)00038-0

M3 - Article

VL - 14

SP - 345

EP - 363

JO - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

IS - 4

ER -