Skip to main content

Research Repository

Advanced Search

Crop classification by a support vector machine with intelligently selected training data for an operational application

Mathur, Ajay; Foody, Giles M.

Crop classification by a support vector machine with intelligently selected training data for an operational application Thumbnail


Authors

Ajay Mathur

GILES FOODY giles.foody@nottingham.ac.uk
Professor of Geographical Information



Abstract

The accuracy of supervised classification is dependent to a large extent on the training data used. The aim is often to capture a large training set to fully describe the classes spectrally, commonly with the requirements of a conventional statistical classifier in-mind. However, it is not always necessary to provide a complete description of the classes, especially if using a support vector machine (SVM) as the classifier. A SVM seeks to fit an optimal hyperplane between the classes and uses only some of the training samples that lie at the edge of the class distributions in feature space (support vectors). This should allow the definition of the most informative training samples prior to the analysis. An approach to identify informative training samples was demonstrated for the classification of agricultural classes in south-western part of Punjab state, India. A small, intelligently selected, training data set was acquired in the field with the aid of ancillary information. This data set contained the data from training sites that were predicted before the classification to be amongst the most informative for a SVM classification. The intelligent training collection scheme yielded a classification of comparable accuracy, ~91%, to one derived using a larger training set acquired by a conventional approach. Moreover, from inspection of the training sets it was apparent that the intelligently defined training set contained a greater proportion of support vectors (0.70), useful training sites, than that acquired by the conventional approach (0.41). By focusing on the most informative training samples, the intelligent scheme required less investment in training than the conventional approach and its adoption would have reduced total financial outlay in classification production and evaluation by ~26%. Additionally, the analysis highlighted the possibility to further reduce the training set size without any significant negative impact on classification accuracy.

Citation

Mathur, A., & Foody, G. M. (2008). Crop classification by a support vector machine with intelligently selected training data for an operational application. International Journal of Remote Sensing, 29(8), https://doi.org/10.1080/01431160701395203

Journal Article Type Article
Publication Date Jan 1, 2008
Deposit Date Jun 14, 2013
Publicly Available Date Jun 14, 2013
Journal International Journal of Remote Sensing
Print ISSN 0143-1161
Electronic ISSN 1366-5901
Publisher Taylor and Francis
Peer Reviewed Peer Reviewed
Volume 29
Issue 8
DOI https://doi.org/10.1080/01431160701395203
Public URL https://nottingham-repository.worktribe.com/output/1015966
Publisher URL http://www.tandfonline.com/doi/full/10.1080/01431160701395203
Additional Information This is an Author's Accepted Manuscript of an article published in International Journal of Remote Sensing: Mathur, A. & Foody, G.M., Crop classification by support vector machine with intelligently selected training data for an operational application, International Journal of Remote Sensing, 29(8), (2008), copyright Taylor & Francis, available online at: http://www.tandfonline.com/10.1080/01431160701395203

Files





You might also like



Downloadable Citations