Pattern Recognition 34 (2001) 1601}1612 Nearest-neighbour classi"ers in natural scene analysis Sameer Singh*, John Haddon, Markos Markou Department of Computer Science, University of Exeter, Prince of Wales Road, Exeter, Devon EX 4 4PT, UK Defence Evaluation and Research Agency, Farnborough, UK Received 29 July 1999; accepted 27 March 2000 Abstract Itisnowwell-establishedthat k nearest-neighbourclassi"erso!eraquickandreliablemethodofdataclassi"cation.In thispaperweextendthebasicde"nitionofthestandard k nearest-neighbouralgorithmtoincludetheabilitytoresolve con#ictswhenthehighestnumberofnearestneighboursarefoundformorethanonetrainingclass(model-1).Wealso proposemodel-2ofnearest-neighbouralgorithmthatisbasedon "ndingthenearestaveragedistanceratherthannearest maximum number of neighbours. These new models are explored using image understanding data. The models are evaluatedonpatternrecognitionaccuracyforcorrectlyrecognisingimagetexturedataof "venaturalclasses:grass,trees, sky,riverre#ectingskyandriverre#ecting trees. On noise contaminated test data, the new nearest neighbour models showverypromisingresultsforfurtherstudies.Weevaluatetheirperformancewithincreasingvaluesofneighbours(k) anddiscusstheirfutureinsceneanalysisresearch.CrownCopyright  2001PublishedbyElsevierScienceLtd.onbehalf of Pattern Recognition Society. All rights reserved. Keywords: Scene analysis; Classi"ers; Nearest-neighbour method; Image understanding 1. Introduction A considerable amount of research has been under- taken globally in the last decade for developing intelli- gentimageprocessingsystems.Althougharangeofbasic image processing tools have been around for the last threedecades,inthelastdecadeasharpincreaseincheap computational power has meant that we are able to implement and test our models in real applications. Re- searchhasfocussedonthefollowingissues:thedevelop- ment of image segmentation methods that work in real noisy environments, encoding image component rela- tionships, and developing the technology for intelligent classi"ers. A number of studies have given generic sur- veys in the area. Kodrato! and Moscatelli [1] survey learning in image processing applications discussing * Corresponding author. Tel.: #44-1392-264061; fax: #44- 1392-264067. E-mail addresses: s.singh@exeter.ac.uk (S. Singh), jf } haddon@dera.gov.uk (J. Haddon), m.markou@exeter.ac.uk (M. Markou). learningin2Dshapemodels,learningstrategicknowledge for optimising model matching, learning in automated target recognition, and constraint rules for labelling. Rosenfeld[2]providesanextensivebibliographyofcom- puter vision research areas arranged by subject and Skrzypeketal.[3]discussadecadeofresearchatUCLA ontheapplicationofneuralnetworksinimageprocess- ing.Yamamoto[4]detailsseveralissuesinimageunder- standing including active range "nders, passive stereo sensing, 3D reconstruction, 3D scene analysis, dynamic scene analysis, automatic knowledge acquisition and autonomous vision systems. On defence applications of image understanding, Kohl and Mundy [5] describe a "ve-yearDARPAprogrambetweenCMUandColorado State university and Firschein [6] details a number of defence applications of image understanding. A detailed treatment of DARPA research in USA is given by Simpson [7]. Therearetwokeycomponentstosceneanalysis:image segmentationandclassi"eranalysis.Imagesegmentation is a key step in the understanding and interpretation of natural scenes and several di!erent methods have been used to achieve this. Neural networks and statistical 0031-3203/01/$20.00 CrownCopyright  2001PublishedbyElsevierScienceLtd.onbehalfofPatternRecognitionSociety.Allrights reserved. PII:S0031-3203(00)00099-6