移動框法在電路板上IC的檢測

Abstract

本文針對電路板元件上的缺陷檢測，提出一個只須檢測元件影像上少數的點，就可以檢測出電路板元件缺陷的方法，這種方法不僅在檢測速度上表現優異，也可以完整的把缺陷檢測出來。 本文的做法首先設定一個像素寬的長方形檢測方框。只針對檢測方框上的像素作處理，檢測方框上待測影像彩色分類後的類別和樣本類別相同的部份定義為T區段，不同的定義F區段，而T區段和F區段的交接處稱為轉折點，利用T區段、F區段和轉折點的數目來找出缺件、插錯元件或元件缺陷等。若檢測方框提供的資訊不能判斷元件缺陷時，我們移動檢測方框至新位置重新檢測，直到新檢測方框提供的資訊可以判斷元件缺陷為止。本論文因為只檢查檢測方框上的點，所以元件缺陷判斷的做法在檢測速度上會比參考文獻表現優異。

This paper presents a new technique for the inspection of defects on the Surface Mounted Devices (SMD) of assembled PCBs. In order to separate the components and the PCB more effectively, we use color image segmentation based on RGB 3D clustering. This method classifies pixels close to each other in the RGB color space into a same class. On defects Inspection, we developed a moving inspection frame based method, which inspects the image on an one-pixel-wide rectangle frame. The experimental results show that the color image segmentation based on 3D clustering is more effective than the gray-scale based method in separating components for the PCB. Moreover, our moving inspection frame based method is faster than the method presented in earlier researches.