印刷電路板內層之自動缺陷偵測與分類系統

Abstract

本論文實現了一套結合缺陷偵測與分類的自動化缺陷分類系統。缺陷偵測的部分，我們必須先利用MAD的方法將待測影像與參考影像對齊，其中參考影像為不包含缺陷的影像。MAD是利用計算兩張影像重疊區域的平均誤差來找出兩張影像之間的平移量，進而對齊待測影像與參考影像。接著，我們將對齊後的待測影像與對齊後的參考影像相減，以獲得缺陷的區域。最後考量到在相減影像中會有一些微小的雜訊，我們設定一個閥值來過濾這些較小的雜訊。 缺陷分類的部分，我們必須找出每一個缺陷的外輪廓，並從外輪廓中抽取出「邊界狀態轉換次數」與「邊界狀態」兩個特徵，除此之外，我們也從影像相減的過程中抽取出「缺陷狀態」的特徵。藉由這三種不同的特徵，我們可以將缺陷分成以下八類：斷開(open)、缺口(mouse bite)、針孔(pinhole)、缺少導體(missing conductor)、短路(short)、突出(spur)、缺洞(missing hole)與多餘的銅(excess copper)。

In this thesis, we implement an automatic defect classification system that combines the detection and classification of the defect on a PCB inner layer. In defect detection part, at first, we have to use the MAD method to align the test images to the reference image which contains no defects. MAD method computes the mean absolute distortion of the two images overlapping area to find the displacement between these two images. Then we subtract the aligned test image from aligned reference images to obtain defects. Finally, there are some noises with small size in the subtracted image. Therefore, we remove these noises by setting a threshold. In defect classification part, we have to find the outer boundary of each defect and then we extract two features, “number of state transition,” and “boundary state,” from the outer boundary. Moreover, we also extract the “defect state” feature in the image subtraction process. By using these three different features, we can classify defects into the following eight types: “open,” “mouse bite,” “pinhole,” “missing conductor,” “short,” “spur,” “missing hole,” and “excess copper.”