基于机器视觉的收藏币类型识别及币面缺陷检测.docxVIP

MECHANICALENGINEE

MECHANICALENGINEER

MECHANICALENGINEER

MECHANICALENGINEER

MECHANICALENGINEER

MECHANICALENGINEER

MECHANICALENGINEER

MECHANICALENGINEER

MECHANICALENGINEER

MECHANICALENGINEER

MECHANICALENGINEER

MECHANICALENGINEER

MECHANICALENGINEER

MECHANICALENGINEER

MECHANICALENGINEER

MECHANICALENGINEER

机械工程师

MECHANICALENGINEER

12圆园22

12

圆园22年第1期网址：电邮：hrbengineer@163.com

基于机器视觉的收藏币类型识别及币面缺陷检测

罗彰，张从鹏，侯静娴

（北方工业大学机械与材料工程学院，北京100144）

摘要：以开发收藏币币面品相检测系统为目标，研究了图像滤波、变换、类型识别及配准等技术。通过预处理初步分割出币面区域，采用多目标相关性模板匹配法，识别出收藏币类型及币面特征在图像中所处的位置，然后根据匹配结果将目标图像与参考图像进行配准，在配准的基础上进行差分，实现对收藏币币面缺陷区域的提取。再根据不同类型缺陷的灰度、几何、形状特征的不同对缺陷区域进行分类识别，然后统计缺陷区域的面积、坐标等参数。实验数据表明，收藏币币面图像识别配准高效准确，能够有效提取出缺陷区域并准确统计缺陷参数。

关键词：图像处理；图像差分；图像分割；缺陷提取

中图分类号:TP274 文献标志码:粤 文章编号：员园园圆原圆猿猿猿（圆园22）01原园012原园3

CollectibleCoinTypeRecognitionandCoinSurfaceDefectDetectionBasedonMachineVision

LUOZhang, ZHANGCongpeng, HOUJingxian

(CollegeofMechanicalandMaterialEngineering,NorthChinaUniversityofTechnology,Beijing100144,China)

Abstract:Withthegoalofdevelopingacollectioncoinfacedetectionsystem,thispaperstudiesthetechniquesofimagefiltering,transformation,typerecognitionandregistration.Preliminarysegmentationofthecurrencyareathroughimagepreprocessing,thetypeofthecoinandthepositionofthecoinfeatureintheimageareconfirmedbymulti-targetrelevancetemplatematchingmethod.Thenthetargetimageandthereferenceimageareregisteredaccordingtothematchingresults.Theextractionofthedefectareaofthecoinsurfaceofthecollectiblecoinisrealizedbythedifferencebasedontheregistration.Thedefectareaareclassifiedandidentifiedbasedontheregiongray,geometric,andshapecharacteristicsofdifferenttypesofdefects.Thenthearea,coordinatesandotherparametersofthedefectareaarecountedandsaved.Someexperimentsarecarriedout.Theimagerecognitionandregistrationofthecoinfaceofthecollectioncoin