- 學位論文
鈔券印刷瑕疵檢測軟體之開發
Development of Flaw Inspection Software for Banknote Printing
摘要
在現今歐、美、德、日等國的鈔券印製產業中，幾乎都已經使用自動化檢測來取代傳統的人工檢測，而目前我國鈔券檢測主要還是以人工檢測為主。本研究將針對鈔券在平版與凹版印刷過程中，可能產生的瑕疵狀況，主要的瑕疵種類包括:墨點、條痕、油墨髒污、油墨脫落等。針對這些問題，建立一套自動化的光學檢測系統，以期達到減少人力資源，提高生產品質、生產效率及降低生產成本。 本研究透過機械視覺與影像處理技術，經由分析鈔券變動範圍、影像定位平版與凹版印刷的圖案，再利用灰階能階差概念，達到瑕疵自動檢出的目的。經實驗結果顯示本方法可檢測出印刷上產生的瑕疵，平均檢測時間約為0.1秒，比用人工檢測需花上3~4秒要快上許多。未來運用上，除了增強本系統瑕疵檢測之正確性與強健性外，其技術尚可延伸應用於平面型印刷文件的瑕疵檢測。
並列摘要
Today, the Automatic Optical Inspection (AOI) system is wildly used to inspect the quality of paper money in the developed countries like USA, Japan, and Germany. On the other hand, traditional manual inspection is still used in inspecting procedures for the check of banknote in our country. This study focused on offset and the intaglio printing of banknote. During the manufacturing process of banknote, the defects are found. The types of defect can be spots, strip, stain, peeled ink … etc. In this study, an AOI system is developed based on the technology of machine vision, image recognition and processing techniques. Furthermore, the analysis of the banknote’s range change, image orientation offset and the intaglio printing can be performed by the AOI system. Finally, the flaw inspection and recognition can be performed automatically. It is shown that the system only takes about 0.1 seconds for image process in standard of 3~4 seconds by human vision. So we proposed automatic inspection system is better than human vision. It is also expected that such developed system can be applied in flaw inspection of some plate printing.