- 學位論文
應用機器視覺於高亮度LED外觀瑕疵自動檢測系統開發
Development of Auto-Detection System for High Brightness LED Surface Defect with Machine Vision.
摘要
對於目前的LED廠商而言，最重要的目標之一是提高LED的良率，以降低生產成本並增加公司獲利，為了增加良率，多數的公司都設有檢查部門，主要是當製程進行到某一個階段時進行人工的瑕疵分類工作。為了降低人為因素以及增加瑕疵分類的速度，以達到全檢的目標，整個檢查系統自動化是必須的。 本論文的目標即是發展一個自動化瑕疵檢測系統。藉由融合各種數位影像處理技巧等方法，針對檢查機台所拍攝的瑕疵影像進行自動即時分類，以利產品良率的提升。此系統可以對四種常見的瑕疵影像(Pad瑕疵、Mesa線瑕疵、歪斜瑕疵、發光區瑕疵)進行偵測及分類，讓瑕疵分類達到自動化、即時化，以上的瑕疵影像皆由廠商提供。 經由最後的實驗測試結果可知，輸入了1549顆晶粒的實際照片，『高亮度LED瑕疵影像辨識系統』的辨識率可達98%以上，表示整套系統針對以上的4種瑕疵影像是可以精準的分類出來。此外，系統平均辨識一張晶粒影像不需要30毫秒的時間，代表系統能快速的分辨瑕疵。
並列摘要
For current Light Emitting Diode (LED) manufacturer, one of the most important goals is to enhance the yield rate and reduce the production cost. To enhance the yield rate, most companies have set up the inspection departments to manually perform the task of defect classification. A fully automatic inspection system is required in order to reduce the effects due to human factors, to accelerate the speed of processing, and to achieve the goal of a full inspection. The purpose of this study is to provide an automatic defect recognition system. In this study, we consult theories of digital image processing techniques. We want our system to automatically classify defect images shot by inspection machines, with the intension of increasing the yield rate of products. We devised a “Defect Recognition System for High Brightness Light Emitting Diode” in the study. This system is able to automatically classify four common defect images, providing a real-time automatic defect detection and classification. The above-mentioned defect images are all offered by a panel company. The experimental results show that, among the 1549 chip pictures offered by a listed panel company in Taiwan, the “Defect Recognition System for High Brightness Light Emitting Diode” achieves a recognition rate higher than 98%. This means that our system is able to classify the four defect images above promptly. Moreover the developed system is also to classify one chip image within 30 milliseconds, which means that the goal of high-speed defect inspection is achieved.