车牌识别外文文献翻译中英文Word文档下载推荐.docx
- 文档编号:409546
- 上传时间:2023-04-28
- 格式:DOCX
- 页数:17
- 大小:19.13KB
车牌识别外文文献翻译中英文Word文档下载推荐.docx
《车牌识别外文文献翻译中英文Word文档下载推荐.docx》由会员分享,可在线阅读,更多相关《车牌识别外文文献翻译中英文Word文档下载推荐.docx(17页珍藏版)》请在冰点文库上搜索。
英文原文
LicensePlateRecognitionBasedOnPriorKnowledge
QianGao,XinnianWangandGongfuXie
Abstract-Inthispaper,anewalgorithmbasedonimprovedBP(backpropagation)neuralnetworkforChinesevehiclelicenseplaterecognition(LPR)isdescribed.Theproposedapproachprovidesasolutionforthevehiclelicenseplates(VLP)whichweredegradedseverely.Whatitremarkablydiffersfromthetraditionalmethodsistheapplicationofpriorknowledgeoflicenseplatetotheprocedureoflocation,segmentationandrecognition.Colorcollocationisusedtolocatethelicenseplateintheimage.Dimensionsofeachcharacterareconstant,whichisusedtosegmentthecharacterofVLPs.TheLayoutoftheChineseVLPisanimportantfeature,whichisusedtoconstructaclassifierforrecognizing.Theexperimentalresultsshowthattheimprovedalgorithmiseffectiveundertheconditionthatthelicenseplatesweredegradedseverely.
IndexTerms-Licenseplaterecognition,priorknowledge,vehiclelicenseplates,neuralnetwork.
I. INTRODUCTION
VehicleLicense-Plate(VLP)recognitionisaveryinterestingbutdifficultproblem.Itisimportantinanumberofapplicationssuchasweight-and-speed-limit,redtrafficinfringement,roadsurveysandparksecurity[1].VLPrecognitionsystemconsistsoftheplatelocation,thecharacterssegmentation,andthecharactersrecognition.Thesetasksbecomemoresophisticatedwhendealingwithplateimagestakeninvariousinclinedanglesorundervariouslighting,weatherconditionandcleanlinessoftheplate.Becausethisproblemisusuallyusedinreal-timesystems,itrequiresnotonlyaccuracybutalsofastprocessing.MostexistingVLPrecognitionmethods[2],[3],[4],[5]reducethecomplexityandincreasetherecognitionratebyusingsomespecificfeaturesoflocalVLPsandestablishingsomeconstrainsontheposition,distancefromthecameratovehicles,andtheinclinedangles.Inaddition,neuralnetworkwasusedtoincreasetherecognitionrate[6],[7]butthetraditionalrecognitionmethodsseldomconsiderthepriorknowledgeofthelocalVLPs.Inthispaper,weproposedanewimprovedlearningmethodofBPalgorithmbasedonspecificfeaturesofChineseVLPs.TheproposedalgorithmovercomesthelowspeedconvergenceofBPneuralnetwork[8]andremarkableincreasestherecognitionrateespeciallyundertheconditionthatthelicenseplateimagesweredegradeseverely.
II. SPECIFICFEATURESOFCHINESEVLPS
A.Dimensions
Accordingtotheguidelineforvehicleinspection[9],alllicenseplatesmustberectangularandhavethedimensionsandhaveall7characterswritteninasingleline.Underpracticalenvironments,thedistancefromthecameratovehiclesandtheinclinedanglesareconstant,soallcharactersofthelicenseplatehaveafixedwidth,andthedistancebetweenthemediumaxesoftwoadjoiningcharactersisfixedandtheratiobetweenwidthandheightisnearlyconstant.Thosefeaturescanbeusedtolocatetheplateandsegmenttheindividualcharacter.B.Colorcollocationoftheplate
TherearefourkindsofcolorcollocationfortheChinesevehiclelicenseplate.ThesecolorcollocationsareshownintableI.
TABLEI
Moreover,militaryvehicleandpolicewagonplatescontainaredcharacterwhichbelongstoaspecificcharacterset.Thisfeaturecanbeusedtoimprovetherecognitionrate.
C.LayoutoftheChineseVLPS
ThecriterionofthevehiclelicenseplatedefinesthecharacterslayoutofChineselicenseplate.AllstandardlicenseplatescontainChinesecharacters,numbersandletterswhichareshowninFig.l.ThefirstoneisaChinesecharacterwhichisanabbreviationofChinese
provinces.ThesecondoneisaletterrangingfromAtoZexcepttheletterI.Thethirdandfourthonesarelettersornumbers.Thefifthtoseventhonesarenumbersrangingfrom0to9only.Howeverthefirstortheseventhonesmayberedcharactersinspecialplates(asshowninFig.l).Aftersegmentationprocesstheindividualcharacterisextracted.Takingadvantageofthelayoutandcolorcollocationpriorknowledge,theindividualcharacterwillenteroneoftheclasses:
abbreviationsofChineseprovincesset,lettersset,lettersornumbersset,numberset,specialcharactersset.
(a) Typicallayout
(b) Specialcharacter
Fig.lThelayoutoftheChineselicenseplate
III. THEPROPOSEDALGORITHM
Thisalgorithmconsistsoffourmodules:
VLPlocation,charactersegmentation,characterclassificationandcharacterrecognition.ThemainstepsoftheflowchartofLPRsystemareshowninFig.2.
Firstlythelicenseplateislocatedinaninputimageandcharactersaresegmented.Theneveryindividualcharacterimageenterstheclassifiertodecidewhichclassitbelongsto,andfinallytheBPnetworkdecideswhichcharacterthecharacterimagerepresents.
A.Preprocessingthelicenseplate
1)VLPLocation
Thisprocesssufficientlyutilizesthecolorfeaturesuchascolorcollocation,colorcentersanddistributionintheplateregion,whicharedescribedinsectionII.Thesecolorfeaturescanbeusedtoeliminatethedisturbanceofthefakeplate'
sregions.TheflowchartoftheplatelocationisshowninFig.3.
Fig.3Theflowchartoftheplatelocationalgorithm
Theregionswhichstructureandtexturesimilartothevehicleplateareextracted.Theprocessisdescribedasfollowed:
Here,theGaussianvarianceissettobelessthanW/3(Wisthecharacterstrokewidth),soIPgetsitsmaximumvalueMatthecenterofthestroke.Afterconvolution,binarizationisperformedaccordingtoathresholdwhichequalsT*M(T<
0.5),Medianfilterisusedtopreservetheedgegradientandeliminateisolatednoiseofthebinaryimage.AnN*Nrectanglemedianfilterisset,andNrepresentstheoddintegermostlyclosetoW.
Morphologyclosingoperationcanbeusedtoextractthecandidateregion.Theconfidencedegreeofcandidateregionforbeingalicenseplateisverifiedaccordingtotheaspectratioandareas.Here,theaspectratioissetbetween1.5and4forthereasonofinclination.Thepriorknowledgeofcolorcollocationisusedtolocateplateregionexactly.ThelocatingprocessofthelicenseplateisshowninFig.4.
2)Charactersegmentation
Thispartpresentsanalgorithmforcharactersegmentationbasedonpriorknowledge,usingcharacterwidth,fixednumberofcharacters,theratioofheighttowidthofacharacter,andsoon.TheflowchartofthecharactersegmentationisshowninFig.5.
Firstly,preprocessthelicensetheplateimage,suchasunevenilluminationcorrection,contrastenhancement,inclinecorrectionandedgeenhancementoperations;
secondly,eliminatingspacemarkwhichappearsbetweenthesecondcharacterandthethirdcharacter;
thirdly,mergingthesegmentedfragmentsofthecharacters.InChina,allstandardlicenseplatescontainonly7characters(seeFig.1).Ifthenumberofsegmentedcharactersislargerthanseven,themergingprocessmustbeperformed.TableIIshowsthemergingprocess.Finally,extractingtheindividualcharacter'
imagebasedonthenumberandthewidthofthecharacter.Fig.6showsthesegmentationresults,(a)Theinclineandbrokenplateimage,(b)theinclineanddistortplateimage,(c)theseriousfadeplateimage,(d)thesmutlicenseplateimage.
whereNfisthenumberofcharactersegments,MaxFisthenumberofthelicenseplate,andiistheindexofeachcharactersegment.
Themediumpointofeachsegmentedcharacterisdeterminedby:
(3)
whereliS
istheinitialcoordinatesforthecharactersegment,and2iSisthefinalcoordinateforthecharactersegment.Thedistancebetweentwoconsecutivemediumpointsiscalculatedby:
(4)
Fig.6Thesegmentationresults
B.Usingspecificpriorknowledgeforrecognition
ThelayoutoftheChineseVLPisanimportantfeature(asdescribedinthesectionII),whichcanbeusedtoconstructaclassifierforrecognizing.Therecognizingprocedureadoptedconjugategradientdescentfastlearningmethod,whichisanimprovedlearningmethodofBPneuralnetwork[10].Conjugategradientdescent,whichemploysaseriesoflinesearchesinweightorparameterspace.Onepicksthefirstdescentdirectionandmovesalongthatdirectionuntiltheminimuminerrorisreached.Theseconddescentdirectionisthencomputed:
thisdirectionthe'
'
conjugatedirection"
istheonealongwhichthegradientdoesnotchangeitsdirectionwillnot'
spoil"
thecontributionfromthepreviousdescentiterations.Thisalgorithmadoptedtopology625-35-NasshowninFig.7.Thesizeofinputvalueis625(25*25)andinitialweightsarewithrandomvalues,desiredoutputvalueshavethesamefeaturewiththeinputvalues.
AsFig.7shows,thereisathree-layernetworkwhichcontainsworkingsignalfeedforwardoperationandreversepropagationoferrorprocesses.Thetargetparameteristandthelengthofnetworkoutputvectorsisn.Sigmoidisthenonlineartransferfunction,weightsareinitializedwithrandomvalues,andchangedinadirectionthatwillreducetheerrors.
Thealgorithmwastrainedwith1000imagesofdifferentbackgroundandilluminationmostofwhichweredegradeseverely.Afterpreprocessingprocess,theindividualcharactersarestored.Allcharactersusedfortrainingandtestinghavethesamesize(25*25).Theintegratedprocessforlicenseplaterecognitionconsistsofthefollowingsteps:
1) Featureextracting
Thefeaturevectorsfromseparatedcharacterimageshavedirecteffectsontherecognitionrate.Manymethodscanbeusedtoextractfeatureoftheimagesamples,e.g.statisticsofdataatvertica
- 配套讲稿:
如PPT文件的首页显示word图标,表示该PPT已包含配套word讲稿。双击word图标可打开word文档。
- 特殊限制:
部分文档作品中含有的国旗、国徽等图片,仅作为作品整体效果示例展示,禁止商用。设计者仅对作品中独创性部分享有著作权。
- 关 键 词:
- 车牌 识别 外文 文献 翻译 中英文
![提示](https://static.bingdoc.com/images/bang_tan.gif)