车牌识别外文翻译文献综述.docx

上传人:b****1 文档编号:263072 上传时间:2022-10-08 格式:DOCX 页数:20 大小:374.57KB
下载 相关 举报
车牌识别外文翻译文献综述.docx_第1页
第1页 / 共20页
车牌识别外文翻译文献综述.docx_第2页
第2页 / 共20页
车牌识别外文翻译文献综述.docx_第3页
第3页 / 共20页
车牌识别外文翻译文献综述.docx_第4页
第4页 / 共20页
车牌识别外文翻译文献综述.docx_第5页
第5页 / 共20页
点击查看更多>>
下载资源
资源描述

车牌识别外文翻译文献综述.docx

《车牌识别外文翻译文献综述.docx》由会员分享,可在线阅读,更多相关《车牌识别外文翻译文献综述.docx(20页珍藏版)》请在冰豆网上搜索。

车牌识别外文翻译文献综述.docx

车牌识别外文翻译文献综述

LicensePlateRecognitionBasedOnPriorKnowledge

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

Categoryoflicenseplate

Colorcollocation

smallhorsepowerplate

bluebackgroundandwhitecharacters

motor truckplate

yellowbackgroundandblackcharacters

military vehicle andpolicewagonplate

blackbackgroundand thewhitecharacters

embassyvehicleplate

whitebackgroundandblackcharacters

Moreover,militaryvehicleandpolicewagonplates containaredcharacterwhichbelongstoaspecificcharacter set.Thisfeaturecanbeusedtoimprovetherecognitionrate.

C.LayoutoftheChineseVLPS

Thecriterionofthevehiclelicenseplatedefinesthe characterslayoutofChineselicense

plate.AllstandardlicenseplatescontainChinesecharacters,numbersandletterswhichareshowninFig.1.ThefirstoneisaChinesecharacterwhichisanabbreviationofChineseprovinces.ThesecondoneisaletterrangingfromAtoZexcepttheletterI.Thethirdandfourthonesarelettersornumbers.Thefifthtoseventhonesarenumbersrangingfrom0to9only.Howeverthefirstortheseventhonesmayberedcharactersinspecialplates(asshowninFig.1).Aftersegmentationprocesstheindividualcharacterisextracted.Takingadvantageofthelayoutandcolorcollocationpriorknowledge,theindividualcharacterwillenteroneoftheclasses:

abbreviationsofChineseprovincesset,lettersset,lettersornumbersset,numberset,specialcharactersset.

Letter

Chinesecharacter

辽BA9083

Number

Letter ornumber

(a)Typicallayout

Letter

Chinesecharacter

辽BB092警

Specialredcharacter

Letter ornumber

(b)Specialcharacter

Fig.1ThelayoutoftheChineselicenseplate

III.THEPROPOSEDALGORITHM

Th

展开阅读全文
相关资源
猜你喜欢
相关搜索

当前位置:首页 > 高中教育 > 初中教育

copyright@ 2008-2022 冰豆网网站版权所有

经营许可证编号:鄂ICP备2022015515号-1