資源描述：
《TFTLCDMura缺陷機(jī)器視覺檢測方法畢昕.pdf》由會(huì)員上傳分享，免費(fèi)在線閱讀，更多相關(guān)內(nèi)容在行業(yè)資料-天天文庫。
1、第46卷第12期機(jī)械工程學(xué)報(bào)Vol.46No.122010年6月JOURNALOFMECHANICALENGINEERINGJun.2010DOI：10.3901/JME.2010.12.013*TFT-LCDMura缺陷機(jī)器視覺檢測方法畢昕丁漢(上海交通大學(xué)機(jī)械與動(dòng)力工程學(xué)院上海200240)摘要：針對液晶顯示器(Liquidcrystaldisplay，LCD)制程中Mura缺陷檢測的重要性和人工檢測的弊端，研究TFT-LCDMura缺陷的機(jī)器視覺自動(dòng)檢測方法?；趪H半導(dǎo)體設(shè)備與材料組織(SemiconductorEquipme
2、ntandMaterialsInternational，SEMI)標(biāo)準(zhǔn)中Mura缺陷的測量規(guī)范和LCD視覺檢測試驗(yàn)平臺(tái)，針對Mura缺陷邊緣模糊、對比度低、圖像中存在重復(fù)紋理背景和整體的亮度不均勻等特點(diǎn)，分別研究基于實(shí)值Gabor小波濾波的紋理背景抑制方法、基于同態(tài)變換和獨(dú)立分量分析的亮度不均勻校正方法、基于主動(dòng)輪廓模型和水平集方法的缺陷分割以及基于SEMI標(biāo)準(zhǔn)的缺陷量化方法，綜合幾個(gè)方面的研究，建立Mura缺陷自動(dòng)檢測流程。檢測試驗(yàn)證明，所提出方法能較好地抑制紋理背景、校正背景亮度不均勻和莫爾條紋，準(zhǔn)確的分割缺陷并進(jìn)行量化評定。該方
3、法適用于Mura缺陷的自動(dòng)檢測，檢測方法與人的視覺特性相似，具有較好的魯棒性。對于50個(gè)帶有Mura缺陷的LCD樣本，有48個(gè)樣本被成功檢測。關(guān)鍵詞：Mura缺陷Gabor濾波獨(dú)立分量分析主動(dòng)輪廓模型水平集中圖分類號(hào)：TP274.3MachineVisionInspectionMethodofMuraDefectforTFT-LCDBIXinDINGHan(SchoolofMechanicalEngineering,ShanghaiJiaoTongUniversity,Shanghai200240)Abstract：Theautoma
4、ticmachinevisioninspectionwayisstudiedfortheMuradefectofTFT-LCD,aimingattheimportanceofdefectinspectionandtheshortcomingofmanualinspectioninliquidcrystaldisplay(LCD)process.Muraislocallightnessvariationwithlowcontrast,blurrycontour,unevenbrightnessandtexturedbackground.
5、BasedontheSemiconductorEquipmentandMaterialsInternational(SEMI)standardforMuraandtheLCDvisioninspectionplatform,theinspectionalgorithmsareresearched,includingthetexturedbackgroundsuppressionmethodusingrealGaborfiltering,theadjustmentofbrightnessunevennesswithhomomorphic
6、transformandindependentcomponentanalysis,theMurasegmentationusingactivecontourmodelandlevelsetmethodandtheMuraquantificationbasedonSEMIstandard.Theautomaticinspectionprocessissetupbysynthesizingtheresearchesproposedabove.Theinspectionexperimentsshowthattheproposedmethod
7、cansuppressthetexturedbackground,eliminatetheunevennessandmoirefringeinbackground,accuratelysegmentdefectsandcarryoutquantitativeevaluation.TheproposedmethodisapplicabletoautomaticinspectionofMuradefectwithgoodrobustnessandsimilartovisioncharacteristicofhumaneyes.And,fo
8、r50LCDsamples,48samplesareinspectedaccurately.Keywords：MuradefectGaborfilteringIndependentcomponentanalysisAct
