Improving Hyperspectral Pixel Classification With Unsupervised Training Data Selection
View/ Open
Impact
Scholar |
Other documents of the author: Rajadell Rojas, Olga; García-Sevilla, Pedro; Viet Cuong Dinh; Duin, Robert P. W.
Metadata
Show full item recordcomunitat-uji-handle:10234/9
comunitat-uji-handle2:10234/43662
comunitat-uji-handle3:10234/43643
comunitat-uji-handle4:
INVESTIGACIONMetadata
Title
Improving Hyperspectral Pixel Classification With Unsupervised Training Data SelectionDate
2014Publisher
Institute of Electrical and Electronics Engineers (IEEE)ISSN
1545-598XBibliographic citation
Geoscience and Remote Sensing Letters, IEEE Volume:11 , Issue: 3, p. 656-660Type
info:eu-repo/semantics/articlePublisher version
http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6587766Version
info:eu-repo/semantics/acceptedVersionSubject
Abstract
An unsupervised method for selecting training data is suggested here. The method is tested by applying it to hyperspectral land-use classification. The data set is reduced using an unsupervised band selection method ... [+]
An unsupervised method for selecting training data is suggested here. The method is tested by applying it to hyperspectral land-use classification. The data set is reduced using an unsupervised band selection method and then clustered with a nonparametric cluster technique. The cluster technique provides centers of the clusters, and those are the samples selected to compose the training set. Both the band selection and the clustering are unsupervised techniques. Afterward, an expert labels those samples, and the rest of unlabeled data can be classified. The inclusion of the selection step, although unsupervised, allows to select automatically the most suitable pixels to build the classifier. This reduces the expert effort because less pixels need to be labeled. However, the classification results are significantly improved in comparison with the results obtained by a random selection of training samples, in particular for very small training sets. [-]
Is part of
Geoscience and Remote Sensing Letters, IEEE, 2014, vol. 11, no 3Rights
This item appears in the folowing collection(s)
- INIT_Articles [754]