强激光与粒子束
彊激光與粒子束
강격광여입자속
HIGH POWER LASER AND PARTICLEBEAMS
2009年
7期
1097-1100
,共4页
方黎勇%李柏林%王凯%雷华堂%陈黎丽
方黎勇%李柏林%王凱%雷華堂%陳黎麗
방려용%리백림%왕개%뢰화당%진려려
缺陷识别%ICT切片图像%拟合椭圆%轮廓匹配%分枝
缺陷識彆%ICT切片圖像%擬閤橢圓%輪廓匹配%分枝
결함식별%ICT절편도상%의합타원%륜곽필배%분지
defect recognition%slicie images of industrial computerized tomography%ellipse fitting%contour matching%branching
现有的工业计算机断层成像(ICT)图像缺陷识方法中,多采用对单张图像进行孤立评判方法,此类方法未能考虑到单张图像在相邻层图像信息关联性,因而易将孤立的噪音视为缺陷,造成误判.为解决这一问题,提出一种基于序列ICT切片图像自动识别方法,该方法将识别过程分为两步:单张图像的潜在缺陷提取和相邻层图像缺陷的匹配.第一步运用传统方法识别出每张图像中所有潜在缺陷;第二步根据真缺陷在相邻层具有匹配关系而伪缺陷则相对孤立的特点,通过分步匹配的方法确定每张图像上所有潜在缺陷在相邻层图像上的匹配关系,区分出真伪缺陷.最后通过实例验证表明:利用该方法可以有效得提高真缺陷得识别率,降低误判率.
現有的工業計算機斷層成像(ICT)圖像缺陷識方法中,多採用對單張圖像進行孤立評判方法,此類方法未能攷慮到單張圖像在相鄰層圖像信息關聯性,因而易將孤立的譟音視為缺陷,造成誤判.為解決這一問題,提齣一種基于序列ICT切片圖像自動識彆方法,該方法將識彆過程分為兩步:單張圖像的潛在缺陷提取和相鄰層圖像缺陷的匹配.第一步運用傳統方法識彆齣每張圖像中所有潛在缺陷;第二步根據真缺陷在相鄰層具有匹配關繫而偽缺陷則相對孤立的特點,通過分步匹配的方法確定每張圖像上所有潛在缺陷在相鄰層圖像上的匹配關繫,區分齣真偽缺陷.最後通過實例驗證錶明:利用該方法可以有效得提高真缺陷得識彆率,降低誤判率.
현유적공업계산궤단층성상(ICT)도상결함식방법중,다채용대단장도상진행고립평판방법,차류방법미능고필도단장도상재상린층도상신식관련성,인이역장고립적조음시위결함,조성오판.위해결저일문제,제출일충기우서렬ICT절편도상자동식별방법,해방법장식별과정분위량보:단장도상적잠재결함제취화상린층도상결함적필배.제일보운용전통방법식별출매장도상중소유잠재결함;제이보근거진결함재상린층구유필배관계이위결함칙상대고립적특점,통과분보필배적방법학정매장도상상소유잠재결함재상린층도상상적필배관계,구분출진위결함.최후통과실례험증표명:이용해방법가이유효득제고진결함득식별솔,강저오판솔.
The current automated defect recognition of industrial computerized tomography(ICT) slice images is mostly carried out in individual image.Certain false detections would exist for some isolated noises can not be wiped off without considering the information of neighbor layer images.To solve this problem,a new automated defect recognition method is presented based on a two-step analysis of consecutive slice images.First,all potential defects are segmented using a classic method in each image.Second,real defects and false defects are recognized by all potential defect matching of neighbor layer images in two steps based on the continuity of real defects characteristic and the non-continuity of false defects between the neighbor images.The method is verified by experiments and results prove that the real defects can be detected with high probability and false detections can be reduced effectively.