以密度為基礎之改良型快速分群演算法及其於偏光板瑕疵檢測之應用

Development of an Improved Rapid Density-Based Clustering Algorithm and Its Application on Polarizer Defect Inspection

蔡明忠(Ming-Jong Tsai) ； 吳宗諭(Chung-Yu Wu) ； 田芬寧(Fen-Ning Tien)

《技術學刊》 24卷4期 (2009/12) Pp. 267-274

https://doi.org/10.29507/JT.200912.0007

摘要

本研究目的爲開發即時偏光板瑕疵區域檢測系統，使用線性馬達平台移送偏光板成品，以固定之掃描頻率觸發8k線型掃描攝影機擷取影像，並且在擷取影像的同時，同步處理部分已經擷取到的影像進行瑕疵區域檢測。在瑕疵區域檢測的流程中，首先使用適應性門檻值進行瑕疵影像分割，再使用本論文所提出的一種以密度爲基礎之改良型快速分群演算法(RDBSCAN)，經實驗證明能快速的針對瑕疵影像進行分群處理與位置範圍標記。最後將影像處理與瑕疵標記程序以多執行緒的方式交由雙核心CPU處理，建立即時檢測之功能。經過實驗結果得知，本研究之雛型系統在檢測平台爲70mm/s的移動速度下，單一CCD每秒可連續處理寬約57mm偏光板影像之瑕疵檢測與分群。

關鍵字

偏光板 ； 線型CCD ； 即時瑕疵檢測 ； 以密度爲基礎之快速分群演算法RDBSCAN

並列摘要

This study focuses on developing a real-time polarizer defect inspection system. A polarizer is put on the table driven by a linear motor. An 8k line scan camera is used to scan the polarizer images with constant speed. The scanned images are synchronously processed for further defect detection. During the image processing, an adaptive thresholding method is used to segment the scanned images. Subsequently, this study proposes an improved rapid density-based clustering algorithm (Rapid Density-Based Clustering Applications with Noise: RDBSCAN) to shorten the time used by using Density-Based Clustering Applications with Noise. From the experimental results, it can be seen that the proposed method can rapidly cluster the defective images and correctly mark the defective regions. Finally, the pc-based system employed multi-threading processing technology for image processing and defect marking with a dual core processor to achieve a real-time inspection. From the experimental results, this prototype system with single line CCD can continuously inspect a 60 mm wide polarizer at a velocity of 70 mm/s and finish the inspection and clustering.

並列關鍵字

polarizer ； line CCD ； real-time defect detection ； rapid density-based clustering applications with noise RDBSCAN