Batch-Mode Active-Learning Methods for the Interactive Classification of Remote Sensing Images

This paper investigates different batch-mode active-learning (AL) techniques for the classification of remote sensing (RS) images with support vector machines. This is done by generalizing to multiclass problem techniques defined for binary classifiers. The investigated techniques exploit different...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on geoscience and remote sensing Ročník 49; číslo 3; s. 1014 - 1031
Hlavní autoři: Demir, B, Persello, C, Bruzzone, L
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York, NY IEEE 01.03.2011
Institute of Electrical and Electronics Engineers
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Active learning (AL)
Algorithms
Applied geophysics
Classification
Classification algorithms
Criteria
Earth sciences
Earth, ocean, space
Exact sciences and technology
hyperspectral images
Hyperspectral imaging
image classification
Internal geophysics
Labeling
Machine learning
query functions
Query processing
Redundancy
Remote sensing
remote sensing (RS)
Support vector machines
support vector machines (SVMs)
Training
Uncertainty
very high spatial resolution images
algorithms
image classification
accuracy
remote sensing
query functions
aluminum
remote sensing (RS)
classification
very high spatial resolution images
Active learning (AL)
spatial resolution
strategy
uncertainties
hyperspectral images
high resolution
support vector machines (SVMs)
ISSN:0196-2892, 1558-0644
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:This paper investigates different batch-mode active-learning (AL) techniques for the classification of remote sensing (RS) images with support vector machines. This is done by generalizing to multiclass problem techniques defined for binary classifiers. The investigated techniques exploit different query functions, which are based on the evaluation of two criteria: uncertainty and diversity. The uncertainty criterion is associated to the confidence of the supervised algorithm in correctly classifying the considered sample, while the diversity criterion aims at selecting a set of unlabeled samples that are as more diverse (distant one another) as possible, thus reducing the redundancy among the selected samples. The combination of the two criteria results in the selection of the potentially most informative set of samples at each iteration of the AL process. Moreover, we propose a novel query function that is based on a kernel-clustering technique for assessing the diversity of samples and a new strategy for selecting the most informative representative sample from each cluster. The investigated and proposed techniques are theoretically and experimentally compared with state-of-the-art methods adopted for RS applications. This is accomplished by considering very high resolution multispectral and hyperspectral images. By this comparison, we observed that the proposed method resulted in better accuracy with respect to other investigated and state-of-the art methods on both the considered data sets. Furthermore, we derived some guidelines on the design of AL systems for the classification of different types of RS images.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ObjectType-Article-2
ObjectType-Feature-1
content type line 23
ISSN:0196-2892
1558-0644
DOI:10.1109/TGRS.2010.2072929