欢迎来到天天文库
浏览记录
ID:236483
大小:168.49 KB
页数:11页
时间:2017-07-11
《一种有效地自动图像增强方法-外文文献翻译》由会员上传分享,免费在线阅读,更多相关内容在行业资料-天天文库。
1、附录A:外文文献AnEffectiveAutomaticImageEnhancementMethodABSTRACTOtsumethodispropertodealwithtwoconditions:(1)twoormoreclasseswithdistintivegray-valuesrespectively;(2)classeswithoutdistinctivegray-values,butwithsimilarareas.However,whenthegray-valuedifferencesamongclassesarenotsodistinc
2、t,andtheobjectissmallrelativetobackgroud,theseparabilitiesamongclassesareinsufficient.Inordertoovercometheaboveproblem,thispaperpresentsanimprovedspatiallow-passfilterwithaparameterandpresentsanunsupervisedmethodofautomaticparameterselectionforimageenhancementbasedonOtsumethod.Th
3、ismethodcombinesimageenhancementwithimagesegmentationasoneprocedurethroughadiscriminantcriterion.Theoptimalparameterofthefilterisselectedbythediscriminantcriteriongiventomaximizetheseparabilitybetweenobjectandbackground.Theoptimalthresholdforimagesegmentationiscomputedsimultaneou
4、sly.Themethodisusedtodetectthesurfacedefectofcontainer.Experimentsillustratethevalidityofthemethod.KEYWORDSimageprocessing;automatedimageenhancement;imagesegmentation;automatedvisualinspection1IntroductionAutomatedvisualinspectionofcrackedcontainer(AVICC)isapracticalapplicationof
5、machinevisiontechnology.Torealizeourgoal,fouressentialoperationsmustbedealtwith–imagepreprocessing,objectdetection,featuredescriptionandfinalcrackedobjectclassification.Imageenhancementistoprovidearesultmoresuitablethanoriginalimageforspecificapplications.Inthispapertheobjectiveo
6、fenhancement,followedbyimagesegmentation,istoobtainanimagewithahighercontentabouttheobjectinterestingwithlesscontentaboutnoiseandbackground.Gonzalez[1]discussesthatimageenhancementapproachesfallintotwomaincategories,inthatspatialdomainandfrequencydomainmethods.Burton[2]appliesima
7、geaveragingtechniquetofacerecognitionsystem,makingitabletorecognisefamiliarfaceseasilyacrosslargevariationsinimagequality.Centeno[3]proposesanadaptiveimageenhancementalgorithm,whichreversetheprocessingorderofimageenhancementandsegmentationinordertoavoidsharpeningnoiseandblurringb
8、orders.Munteanu[4]appliesartificialintel
此文档下载收益归作者所有