RefDoc
Haut

Faire une nouvelle recherche
Make a new search
Lancer la recherche


Titre du document / Document title

An Experimental Comparison of Semi-supervised Learning Algorithms for Multispectral Image Classification

Auteur(s) / Author(s)

ENMEI TU (1) ; JIE YANG (1) ; JIANGXIONG FANG (1) ; ZHENGHONG JIA (2) ; KASABOV Nikola (3) ;

Affiliation(s) du ou des auteurs / Author(s) Affiliation(s)

(1) Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University and the Key Laboratory of System Control and Information Processing, Ministry of Education, Shanghai, 200240, CHINE
(2) Xinjiang University, School of Information Science and Engineering, Urumqi, 830046, CHINE
(3) Knowledge Engineering and Discovery Research Institute, Auckland University of Technology, NOUVELLE-ZELANDE

Résumé / Abstract

Semi-Supervised Learning (SSL) method has recently caught much attention in the fields of machine learning and computer vision owing to its superiority in classifying abundant unlabelled samples using a few labeled samples. The goal of this paper is to provide an experimental efficiency comparison between graph based SSL algorithms and traditional supervised learning algorithms (e.g., support vector machines) for multispectral image classification. This research shows that SSL algorithms generally outperform supervised learning algorithms in both classification accuracy and anti-noise ability. In the experiments carried out on two data sets (hyperspectral image and Landsat image), the mean overall accuracies (OAs) of supervised learning algorithms are 15 percent and 86 percent, while the mean OAS of SSL algorithms are 26 percent and 99 percent. To overcome the polynomial complexity of SSL algorithms, we also developed a linear-complexity algorithm by employing multivariate Taylor Series Expansion (TSE) and Woodbury Formula.

Revue / Journal Title

Photogrammetric engineering and remote sensing    ISSN  0099-1112   CODEN PERSDV 

Source / Source

2013, vol. 79, no4, pp. 347-357 [11 page(s) (article)] (1 p.1/4)

Langue / Language

Anglais

Editeur / Publisher

American Society for Photogrammetry and Remote Sensing, Bethesda, MD, ETATS-UNIS  (1975) (Revue)

Mots-clés anglais / English Keywords

Polynomial

;

Landsat satellite

;

Space remote sensing

;

Landsat

;

Hyperspectral imagery

;

Ability

;

noise

;

accuracy

;

Research

;

Support vector machine

;

efficiency

;

Tagging

;

samples

;

Computer vision

;

artificial intelligence

;

Field

;

Method

;

Learning

;

classification

;

Image

;

Multispectral detection

;

Learning algorithm

;

Supervision

;

testing

;

experimental studies

;

Mots-clés français / French Keywords

Polynôme

;

Satellite Landsat

;

Télédétection spatiale

;

LANDSAT

;

Imagerie hyperspectrale

;

Aptitude

;

Bruit

;

Précision

;

Recherche

;

Machine vecteur support

;

Efficacité

;

Marquage

;

Echantillon

;

Vision ordinateur

;

Intelligence artificielle

;

Champ

;

Méthode

;

Apprentissage

;

Classification

;

Image

;

Détection multispectrale

;

Algorithme apprentissage

;

Supervision

;

Expérimentation

;

Etude expérimentale

;

Mots-clés espagnols / Spanish Keywords

Polinomio

;

Satélite Landsat

;

Teledetección espacial

;

Imaginería hiperespectral

;

Aptitud

;

Precisión

;

Investigación

;

Máquina vector soporte

;

Marcación

;

Visión ordenador

;

Campo

;

Método

;

Aprendizaje

;

Clasificación

;

Imagen

;

Detección multiespectral

;

Algoritmo aprendizaje

;

Supervisión

;

Localisation / Location

INIST-CNRS, Cote INIST : 3289, 35400050249052.0030

Nº notice refdoc (ud4) : 27162818



Faire une nouvelle recherche
Make a new search
Lancer la recherche
Bas