{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T23:13:37Z","timestamp":1771024417095,"version":"3.50.1"},"reference-count":67,"publisher":"IGI Global","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,7,1]]},"abstract":"<p>Supervised classifiers are commonly employed in remote sensing to extract land cover information, but various factors affect their accuracy. The number of available training samples, in particular, is known to have a significant impact on classification accuracies. Obtaining a sufficient number of samples is, however, not always practical. The support vector machine (SVM) is a supervised classifier known to perform well with limited training samples and has been compared favourably to other classifiers for various problems in pixel-based land cover classification. Very little research on training-sample size and classifier performance has been done in a geographical object-based image analysis (GEOBIA) environment. This paper compares the performance of SVM, nearest neighbour (NN) and maximum likelihood (ML) classifiers in a GEOBIA environment, with a focus on the influence of training-set size. Training-set sizes ranging from 4-20 per land cover class were tested. Classification tree analysis (CTA) was used for feature selection. The results indicate that the performance of all the classifiers improved significantly as the size of the training set increased. The ML classifier performed poorly when few (&lt;10 per class) training samples were used and the NN classifier performed poorly compared to SVM throughout the experiment. SVM was the superior classifier for all training-set sizes although ML achieved competitive results for sets of 12 or more training areas per class.<\/p>","DOI":"10.4018\/ijagr.2014070104","type":"journal-article","created":{"date-parts":[[2014,11,6]],"date-time":"2014-11-06T15:45:55Z","timestamp":1415288755000},"page":"49-67","source":"Crossref","is-referenced-by-count":16,"title":["Impact of Training Set Size on Object-Based Land Cover Classification"],"prefix":"10.4018","volume":"5","author":[{"given":"Gerhard","family":"Myburgh","sequence":"first","affiliation":[{"name":"Department of Geography and Environmental Studies, Stellenbosch University, Stellenbosch, South Africa"}]},{"given":"Adriaan","family":"van Niekerk","sequence":"additional","affiliation":[{"name":"Department of Geography and Environmental Studies, Stellenbosch University, Stellenbosch, South Africa"}]}],"member":"2432","reference":[{"key":"ijagr.2014070104-0","doi-asserted-by":"publisher","DOI":"10.1080\/789610193"},{"key":"ijagr.2014070104-1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-77058-9_2"},{"key":"ijagr.2014070104-2","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2009.2032457"},{"key":"ijagr.2014070104-3","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2006.11.004"},{"key":"ijagr.2014070104-4","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2009.06.004"},{"key":"ijagr.2014070104-5","unstructured":"Blaschke, T., & Lang, S. (2006). Object based image analysis for automated information extraction\u2212a synthesis. Paper presented at the Measuring the Earth II ASPRS Fall Conference, San Antonio, Texas."},{"issue":"11","key":"ijagr.2014070104-6","first-page":"120","article-title":"The OpenCV library.","volume":"25","author":"G.Bradski","year":"2000","journal-title":"Dr. Dobb's Journal of Software Tools for the Professional Programmer"},{"key":"ijagr.2014070104-7","doi-asserted-by":"publisher","DOI":"10.1023\/A:1009715923555"},{"key":"ijagr.2014070104-8","author":"J.Campbell","year":"2006","journal-title":"Introduction to remote sensing"},{"key":"ijagr.2014070104-9","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2005.846154"},{"key":"ijagr.2014070104-10","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2004.827262"},{"key":"ijagr.2014070104-11","doi-asserted-by":"crossref","unstructured":"Chang, C., & Lin, C. (2011). LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems Technology, 2(3), 27:1\u221227:27.","DOI":"10.1145\/1961189.1961199"},{"key":"ijagr.2014070104-12","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511801389"},{"key":"ijagr.2014070104-13","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1967.1053964"},{"key":"ijagr.2014070104-14","doi-asserted-by":"publisher","DOI":"10.1080\/01431160701294661"},{"key":"ijagr.2014070104-15","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2011.11.020"},{"key":"ijagr.2014070104-16","doi-asserted-by":"publisher","DOI":"10.1016\/S0034-4257(01)00295-4"},{"key":"ijagr.2014070104-17","doi-asserted-by":"publisher","DOI":"10.1002\/9780470748992.ch4"},{"key":"ijagr.2014070104-18","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2004.827257"},{"key":"ijagr.2014070104-19","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2004.06.017"},{"key":"ijagr.2014070104-20","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2006.04.001"},{"key":"ijagr.2014070104-21","unstructured":"Fourie, C. (2011). A one-class object-based system for sparse geographic feature identification. Unpublished master\u2019s thesis, Stellenbosch University, South Africa."},{"key":"ijagr.2014070104-22","author":"J.Gao","year":"2009","journal-title":"Digital analysis of remotely sensed imagery"},{"key":"ijagr.2014070104-23","unstructured":"GDAL Development Team. (2010). GDAL \u2013 Geospatial data abstraction library, version 1.70. Open Source Geospatial Foundation. Retrieved August 4, 2011, from http:\/\/www.gdal.org\/"},{"key":"ijagr.2014070104-24","doi-asserted-by":"publisher","DOI":"10.1002\/9780470748992.ch2"},{"key":"ijagr.2014070104-25","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2003.1247313"},{"key":"ijagr.2014070104-26","doi-asserted-by":"crossref","unstructured":"Gualtieri, J. A., & Cromp, R. F. (1998). Support vector machines for hyperspectral remote sensing classification. Paper presented at the 27th AIPR workshop: Advances in computer assisted recognition, Washington DC.","DOI":"10.1117\/12.339824"},{"key":"ijagr.2014070104-27","doi-asserted-by":"publisher","DOI":"10.1002\/9780470503065"},{"key":"ijagr.2014070104-28","unstructured":"Hay, G. J., & Castilla, G. (2006). Object-based image analysis: Strengths, weaknesses, opportunities and threats (SWOT). International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 36, CD-ROM."},{"key":"ijagr.2014070104-29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-77058-9_4"},{"key":"ijagr.2014070104-30","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2009.08.002"},{"key":"ijagr.2014070104-31","author":"P.Hofmann","year":"2008","journal-title":"A method for adapting global image segmentation methods to images of different resolutions. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 38"},{"key":"ijagr.2014070104-32","unstructured":"Hsu, C., Chang, C., & Lin, C. (2010). A practical guide to support vector classification. Retrieved July 21, 2011, from http:\/\/www.csie.ntu.edu.tw\/~cjlin\/papers\/guide\/guide.pdf"},{"key":"ijagr.2014070104-33","doi-asserted-by":"publisher","DOI":"10.1080\/01431160110040323"},{"key":"ijagr.2014070104-34","doi-asserted-by":"publisher","DOI":"10.1016\/S0034-4257(00)00165-6"},{"key":"ijagr.2014070104-35","doi-asserted-by":"publisher","DOI":"10.1109\/34.824819"},{"key":"ijagr.2014070104-36","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2009.06.002"},{"key":"ijagr.2014070104-37","doi-asserted-by":"publisher","DOI":"10.1016\/S0034-4257(03)00130-5"},{"key":"ijagr.2014070104-38","unstructured":"Laliberte, A. S., Browning, D. M., & Rango, A. (2010). Feature selection methods for object-based classification of sub-decimeter digital aerial imagery. Paper presented at the conference on Geographic Object-Based Image Analysis (GEOBIA), Ghent, Belgium."},{"key":"ijagr.2014070104-39","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2011.05.011"},{"key":"ijagr.2014070104-40","doi-asserted-by":"publisher","DOI":"10.14358\/PERS.73.2.197"},{"key":"ijagr.2014070104-41","doi-asserted-by":"publisher","DOI":"10.1109\/EORSA.2008.4620315"},{"key":"ijagr.2014070104-42","doi-asserted-by":"publisher","DOI":"10.1080\/01431160903475266"},{"key":"ijagr.2014070104-43","author":"T. M.Lillesand","year":"2008","journal-title":"Remote sensing and image interpretation"},{"key":"ijagr.2014070104-44","doi-asserted-by":"publisher","DOI":"10.1080\/01431161003743173"},{"key":"ijagr.2014070104-45","doi-asserted-by":"publisher","DOI":"10.1080\/01431160802326081"},{"key":"ijagr.2014070104-46","doi-asserted-by":"publisher","DOI":"10.1080\/01431160600746456"},{"key":"ijagr.2014070104-47","author":"P. M.Mather","year":"2004","journal-title":"Computer processing of remotely-sensed images: An introduction"},{"key":"ijagr.2014070104-48","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2002.1025088"},{"key":"ijagr.2014070104-49","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2004.831865"},{"key":"ijagr.2014070104-50","doi-asserted-by":"publisher","DOI":"10.1109\/ICIECS.2009.5366011"},{"key":"ijagr.2014070104-51","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2003.1293752"},{"key":"ijagr.2014070104-52","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2010.11.001"},{"key":"ijagr.2014070104-53","doi-asserted-by":"publisher","DOI":"10.1007\/s11004-008-9156-6"},{"key":"ijagr.2014070104-54","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2009.11.002"},{"key":"ijagr.2014070104-55","doi-asserted-by":"publisher","DOI":"10.1016\/S0034-4257(03)00132-9"},{"key":"ijagr.2014070104-56","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2003.11.011"},{"key":"ijagr.2014070104-57","doi-asserted-by":"publisher","DOI":"10.1080\/01431160512331314083"},{"key":"ijagr.2014070104-58","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-77242-4","author":"I.Steinwart","year":"2008","journal-title":"Support vector machines"},{"key":"ijagr.2014070104-59","unstructured":"Stephenson, G. R. (2010). A comparison of supervised and rule-based object-orientated classification for forest mapping. Unpublished master\u2019s thesis, Stellenbosch University, South Africa."},{"key":"ijagr.2014070104-60","doi-asserted-by":"publisher","DOI":"10.1016\/j.apgeog.2010.11.007"},{"key":"ijagr.2014070104-61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-77058-9_36"},{"key":"ijagr.2014070104-62","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2010.07.001"},{"key":"ijagr.2014070104-63","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-2440-0"},{"key":"ijagr.2014070104-64","doi-asserted-by":"publisher","DOI":"10.1002\/9780470748992.ch1"},{"key":"ijagr.2014070104-65","doi-asserted-by":"publisher","DOI":"10.1016\/j.proeps.2009.09.179"},{"key":"ijagr.2014070104-66","doi-asserted-by":"publisher","DOI":"10.14358\/PERS.72.7.799"}],"container-title":["International Journal of Applied Geospatial Research"],"original-title":[],"language":"ng","link":[{"URL":"https:\/\/www.igi-global.com\/viewtitle.aspx?TitleId=118259","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T15:30:25Z","timestamp":1747150225000},"score":1,"resource":{"primary":{"URL":"https:\/\/services.igi-global.com\/resolvedoi\/resolve.aspx?doi=10.4018\/ijagr.2014070104"}},"subtitle":["A Comparison of Three Classifiers"],"short-title":[],"issued":{"date-parts":[[2014,7,1]]},"references-count":67,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2014,7]]}},"URL":"https:\/\/doi.org\/10.4018\/ijagr.2014070104","relation":{},"ISSN":["1947-9654","1947-9662"],"issn-type":[{"value":"1947-9654","type":"print"},{"value":"1947-9662","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,7,1]]}}}