[IJCNN 2012] Steel Defect Classification with Max-Pooling Convolutional Neural Networks

[IJCNN 2012] Steel Defect Classification with Max-Pooling Convolutional Neural Networks

ID：40702394

大小：1.04 MB

頁數(shù)：6頁

時(shí)間：2019-08-06

[IJCNN 2012] Steel Defect Classification with Max-Pooling Convolutional Neural Networks_第1頁
[IJCNN 2012] Steel Defect Classification with Max-Pooling Convolutional Neural Networks_第2頁
[IJCNN 2012] Steel Defect Classification with Max-Pooling Convolutional Neural Networks_第3頁
[IJCNN 2012] Steel Defect Classification with Max-Pooling Convolutional Neural Networks_第4頁
[IJCNN 2012] Steel Defect Classification with Max-Pooling Convolutional Neural Networks_第5頁
資源描述：

《[IJCNN 2012] Steel Defect Classification with Max-Pooling Convolutional Neural Networks》由會員上傳分享，免費(fèi)在線閱讀，更多相關(guān)內(nèi)容在學(xué)術(shù)論文-天天文庫。

1、SteelDefectClassi?cationwithMax-PoolingConvolutionalNeuralNetworksJonathanMasci,UeliMeier,DanCiresan,GabrielFricoutJurgenSchmidhuber¨ArcelorMittalIDSIA,USIandSUPSIMaizieresResearchSA,`Galleria2,6928Manno-Lugano,FranceSwitzerlandfgabriel.fricout@arcelormittal.comgfjona

2、than,ueli,dan,juergeng@idsia.chAbstract—WepresentaMax-PoolingConvolutionalNeuralsi?cation.Thesystemisusuallybasedonasetofhand-Networkapproachforsupervisedsteeldefectclassi?cation.Onawiredpipelineswithpartialornoself-adjustableparametersclassi?cationtaskwith7defects,co

3、llectedfromarealproductionwhichmakesthe?ne-tuningprocessofthisindustrialsystemsline,anerrorrateof7%isobtained.ComparedtoSVMcumbersome,requiringmuchmorehumaninterventionthanclassi?erstrainedoncommonlyusedfeaturedescriptorsourbestnetperformsatleasttwotimesbetter.Notonly

4、wedoobtaindesired.Inthisworkwefocusonthetwolastpipelinestagesmuchbetterresults,buttheproposedmethodalsoworksdirectlyandproposeanapproachbasedonMax-PoolingConvolutionalonrawpixelintensitiesofdetectedandsegmentedsteeldefects,NeuralNetworks(MPCNN)[1],[2],[3],[4],[5],that

5、learnavoidingfurthertimeconsumingandhardtooptimizead-hocthefeaturesdirectlyfromlabeledimagesusingsupervisedpreprocessing.learning.Weshowthattheproposedmethodachievesstate-of-the-artresultsonrealworlddataandcompareourapproachI.INTRODUCTIONtoclassi?erstrainedonclassicfe

6、aturedescriptors.MachinevisionbasedsurfaceinspectiontechnologieshaveThereisnotmuchliteratureaboutsteeldefectdetectiongainedalotofinterestfromvariousindustriestoautomatein-[6].However,inabroadercontexttheproblemcanbespectionsystems,andtosigni?cantlyimproveoverallproduc

7、tviewedasdefectdetectionintexturedmaterialwhichhasquality.Atypicalindustryadoptingthesere?nedinspectionreceivedconsiderableattentionincomputervision[7],[8],toolsistherolledsteelstripmarket.Real-timevisualinspec-[9].Inclassicalapproaches,featureextractionisperformedtio

8、nofproductionlinesiscrucialtoprovideaproductwithusingthe?lter-bankparadigm,resultinginanarchitectureeverfewersurfacedefects.

當(dāng)前文檔最多預(yù)覽五頁，下載文檔查看全文

此文檔下載收益歸作者所有

當(dāng)前文檔最多預(yù)覽五頁，下載文檔查看全文
溫馨提示：
1. 部分包含數(shù)學(xué)公式或PPT動畫的文件，查看預(yù)覽時(shí)可能會顯示錯(cuò)亂或異常，文件下載后無此問題，請放心下載。
2. 本文檔由用戶上傳，版權(quán)歸屬用戶，天天文庫負(fù)責(zé)整理代發(fā)布。如果您對本文檔版權(quán)有爭議請及時(shí)聯(lián)系客服。
3. 下載前請仔細(xì)閱讀文檔內(nèi)容，確認(rèn)文檔內(nèi)容符合您的需求后進(jìn)行下載，若出現(xiàn)內(nèi)容與標(biāo)題不符可向本站投訴處理。
4. 下載文檔時(shí)可能由于網(wǎng)絡(luò)波動等原因無法下載或下載錯(cuò)誤，付費(fèi)完成后未能成功下載的用戶請聯(lián)系客服處理。