Comparison of accuracy and efficiency of five digital image classification algorithms

dc.contributor.authorStory, Michael Haunen
dc.contributor.departmentGeographyen
dc.date.accessioned2014-03-14T21:33:35Zen
dc.date.adate2010-04-12en
dc.date.available2014-03-14T21:33:35Zen
dc.date.issued1987en
dc.date.rdate2010-04-12en
dc.date.sdate2010-04-12en
dc.description.abstractAccuracies and efficiencies of five algorithms for computer classification of multispectral digital imagery were assessed by application to imagery of three test sites (Roanoke, VA., Glade Spring, VA., and Topeka, KA.) A variety of land cover features and two types of image data (Landsat MSS and Thematic Mapper) were represented. Classification algorithms were selected from the General Image Processing System (GIPSY) at the Spatial Data Analysis Laboratory at Virginia Polytechnic Institute and State University, Blacksburg, Virginia and represent a range of available techniques including: a) AMOEBA (an unsupervised clustering technique with a spatial constraint) b) ISODATA (a hybrid minimum distance classifier) c) BOXDEC (a discrete parallelepiped classifier) d) BCLAS (a Bayesian classifier) e) HYPBOX (a combined parallelepiped-Bayesian classifier) Two sets of training data, developed for each study site were combined with each technique and applied to each study site. Parallelepiped classifiers provided the highest classification accuracies but failed to categorize all pixels. The number of classified pixels could be altered by the method of selecting training data and/or adjusting the threshold variable. The minimum distance classifiers were most accurate when the spectral sub-class training data were used. Use of the land cover class training data provided the most accurate results for the Bayesian techniques and decreased the CPU requirements for all of the techniques. The most important consideration for accurate and efficient classification is to select the classification algorithm that matches the data structure of the training data.en
dc.description.degreeMaster of Scienceen
dc.format.extentviii, 145 leavesen
dc.format.mediumBTDen
dc.format.mimetypeapplication/pdfen
dc.identifier.otheretd-04122010-083611en
dc.identifier.sourceurlhttp://scholar.lib.vt.edu/theses/available/etd-04122010-083611/en
dc.identifier.urihttp://hdl.handle.net/10919/42034en
dc.publisherVirginia Techen
dc.relation.haspartLD5655.V855_1987.S867.pdfen
dc.relation.isformatofOCLC# 17346828en
dc.rightsIn Copyrighten
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/en
dc.subject.lccLD5655.V855 1987.S867en
dc.subject.lcshAlgorithmsen
dc.subject.lcshImage processing -- Digital techniquesen
dc.subject.lcshRemote sensingen
dc.titleComparison of accuracy and efficiency of five digital image classification algorithmsen
dc.typeThesisen
dc.type.dcmitypeTexten
thesis.degree.disciplineGeographyen
thesis.degree.grantorVirginia Polytechnic Institute and State Universityen
thesis.degree.levelmastersen
thesis.degree.nameMaster of Scienceen

Files

Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
LD5655.V855_1987.S867.pdf
Size:
82.13 MB
Format:
Adobe Portable Document Format
Description:

Collections