多光譜圖像分割技術(shù)在防沙治沙關(guān)鍵技術(shù)中的研究與應(yīng)用.pdf

1、天津理工大學(xué)碩士學(xué)位論文多光譜圖像分割技術(shù)在防沙治沙關(guān)鍵技術(shù)中的研究與應(yīng)用姓名：馬京華申請學(xué)位級別：碩士專業(yè)：計算機(jī)應(yīng)用技術(shù)指導(dǎo)教師：王懷彬20081201Abstractneclassificationforlandcoverof11ⅥmultispectralImagingisadifficultproblemallthetimeBecausethereareallkindsoflandCoversanddifferentkinds

2、oflandcovers謝llchangealongwiththetime’Sprocessandspace’Sdistributioncontinuouslylandcovers’reflectionmultispectralimagedatawillaltertooInaddition，mutispectraldataitselfhavethefeatureoftthesainesubs：銣：lce，thedifferentcomp

3、osition；thesamecomposition，thedifferentsubstance’，DatawillalsobenoisedduringcollectionprocessAlldisadvantageswetalkabovemakesometraditionalmethodofclassificationperformpoorlyinaspectofcomputationalcomplexityclassificatio

4、naccuracygeneralizationperformanceButthedesertterrainmulitspectralimageshasanobviousfeatureoftextureSo，themethodwhichcombinestheSVMwiththetexturefeatureisproposedafteranalysingthemainmethodofclassificationandthedigitalfe

5、tureofthemultispectralimagesCansolvetheproblemperfectlyByanalysingtheresultsoftheexperimentswefoundouttheeffectofSVMiSmuchbetterthanothers111etraditionalmethodssuchasBayesianmethodandNeuralNetworksareallbasedontheideaofe

6、xperienceminimizeriskSVMiSbasedonthetheoryofstructuralriskminimizationItismainlyusedinthecontextoflackingsamples，andcansolvemanyproblemsinalargeextentsuchasmodelchoosingproblems，nonlinearproblems，localminimumpointsproble