基于bp神经网络的车型识别中英文翻译资料要点

基于bp神经网络的车型识别中英文翻译资料要点

ID:11640643

大小:1.54 MB

页数:74页

时间:2018-07-13

基于bp神经网络的车型识别中英文翻译资料要点_第1页
基于bp神经网络的车型识别中英文翻译资料要点_第2页
基于bp神经网络的车型识别中英文翻译资料要点_第3页
基于bp神经网络的车型识别中英文翻译资料要点_第4页
基于bp神经网络的车型识别中英文翻译资料要点_第5页
资源描述:

《基于bp神经网络的车型识别中英文翻译资料要点》由会员上传分享,免费在线阅读,更多相关内容在教育资源-天天文库

1、湖南科技大学智能控制理论论文姓名:_____________学院:_____________班级:_____________学号:_____________72LicensePlateRecognitionBasedOnPriorKnowledgeAbstractInthispaper,anewalgorithmbasedonimprovedBP(backpropagation)neuralnetworkforChinesevehiclelicenseplaterecognition(LPR)isdescribed.Theproposedapproachprovidesasol

2、utionforthevehiclelicenseplates(VLP)whichweredegradedseverely.Whatitremarkablydiffersfromthetraditionalmethodsistheapplicationofpriorknowledgeoflicenseplatetotheprocedureoflocation,segmentationandrecognition.Colorcollocationisusedtolocatethelicenseplateintheimage.Dimensionsofeachcharacterarecon

3、stant,whichisusedtosegmentthecharacterofVLPs.TheLayoutoftheChineseVLPisanimportantfeature,whichisusedtoconstructaclassifierforrecognizing.TheexperimentalresultsshowthattheimprovedalgorithmiseffectiveundertheconditionthatthelicenseplatesweredegradedseverelyVehicleLicense-Plate(VLP)recognitionisa

4、veryinterestingbutdifficultproblem.Itisimportantinanumberofapplicationssuchasweight-and-speed-limit,redtrafficinfringement,roadsurveysandparksecurity[1].VLPrecognitionsystemconsistsoftheplatelocation,thecharacterssegmentation,andthecharactersrecognition.Thesetasksbecomemoresophisticatedwhendeal

5、ingwithplateimagestakeninvariousinclinedanglesorundervariouslighting,weatherconditionandcleanlinessoftheplate.Becausethisproblemisusuallyusedinreal-timesystems,itrequiresnotonlyaccuracybutalsofastprocessing.MostexistingVLPrecognitionmethods[2],[3],[4],[5]reducethecomplexityandincreasetherecogni

6、tionratebyusingsomespecificfeaturesoflocalVLPsandestablishingsomeconstrainsontheposition,distancefromthecameratovehicles,andtheinclinedangles.Inaddition,neuralnetworkwasusedtoincreasetherecognitionrate[6],[7]butthetraditionalrecognitionmethodsseldomconsiderthepriorknowledgeofthelocalVLPs.Inthis

7、paper,weproposedanewimprovedlearningmethodofBPalgorithmbasedonspecificfeaturesofChineseVLPs.TheproposedalgorithmovercomesthelowspeedconvergenceofBPneuralnetwork[8]andremarkableincreasestherecognitionrate72especiallyundertheconditi

当前文档最多预览五页,下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页,下载文档查看全文
温馨提示:
1. 部分包含数学公式或PPT动画的文件,查看预览时可能会显示错乱或异常,文件下载后无此问题,请放心下载。
2. 本文档由用户上传,版权归属用户,天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容,确认文档内容符合您的需求后进行下载,若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误,付费完成后未能成功下载的用户请联系客服处理。