查詢結果分析
相關文獻
- 以T[feb4]統計量為基礎之小波特徵多變量處理模式應用於表面瑕疵之檢測
- A Fast and Efficient Competitive Learning Design Algorithm Based on Weight Vector Training in Transform Domain
- Fractal Extraction from a Mixed FBM Signal Using Discrete Wavelet Transforms
- Computer-Aided Fetus Analysis and Diagnosis System Using Fetal Heart Rate
- 應用小波理論於生產策略之快速回應系統
- The Global Minimum of Scalar Quantization Errors by Discrete Wavelet Transforms in Image Compression
- Wavelet Transforms for Speech Signal Processing
- 應用小波係數編碼之四分樹結構
- 強健型離散小波轉換於水下響聲之偵測
- 植基於EZW之程式實際設計與執行
頁籤選單縮合
題名 | 以T[feb4]統計量為基礎之小波特徵多變量處理模式應用於表面瑕疵之檢測=A T[feb4] Statistics Based Wavelet Characteristic Multivariate Processing Model Applied to Automated Inspection of Surface Defects |
---|---|
作者姓名(中文) | 林宏達; 陳志松; |
作者姓名(外文) | Lin, Hong-dar; Chen, Chih-sung; |
書刊名 | 工業工程學刊 |
卷期 | 21:2 2004.03[民93.03] |
頁次 | 頁121-135 |
分類號 | 494.568 |
語文 | chi |
關鍵詞 | 表面瑕疵檢測; Hotelling T[feb4]多變量統計量; 小波轉換; 閥值切割技術; Ripple-texture defect detection; Hotelling T[feb4]multivariate statistics; Wavelet transformation; Threshold techniques; |
中文摘要 | 本研究提出應用品質管制技術中Hotelling多變量管制圖之T2統計量於表面瑕疵之檢測,發展小波特徵多變量處理模式(Wavelet Characteristic Multivariate Processing model, WCMP),並以表層障蔽型半導性瓷片(SBL)上一種常見的水紋紋路瑕疵為檢測對象。而本研究則應用T2統計量可整合多個影像特徵之特性,整合彩色影像之多個紋路特徵以降低水紋瑕疵檢測之誤判率,所提WCMP模式使用小波特徵作為影像之特徵值,並以T2能量值之變化突顯異常瑕疵之存在,且後續搭配不同檢測之需要發展Mode-Double與Mode-Triple兩種閥值切割技術以確定瑕疵之位置。本研究提出之WCMP方法相較於其他紋路分析方法較具彈性,且有處理速度快之特性,而實驗結果也發現WCMP模式具有93.75%之SBL瓷片水紋瑕疵判斷檢測率,其搭配Mode-Double或Mode-Triple閥值切割方法切割水紋瑕疵,具有高達90%之水紋瑕疵位置偵測正確率。 |
英文摘要 | Ripple-textures are common defects because of steam left on Surface Barrier Layer (SBL) chip surfaces. Ripple-texture defects influence not only appearances of SBLs, but also the electronic properties of the products. The reasons why the inspection of ripple-texture defects cannot be done automatically are: (1) the ripple-texture defect is semiopaque; (2) the ripple-texture is an unstructured texture; (3) edge gray levels of the ripple-texture defect are changed gradually. It is not only difficult to find the ripple-texture by artificial inspection, but also easy to make wrong judgments due to human subjectivity and eye fatigues. This study applies multivariate T2 statistics to automatic inspection of surface ripple texture defects. We propose a WCMP (Wavelet Characteristic Multivariate Processing) model, based on the Wavelet characteristics and multivariate processing, for detecting the ripple texture defects. Modified threshold techniques are also presented for locating the defects. Experimental results indicate that the proposed methods can detect 93.75% images with ripple-texture defects and reach above 90% correct segmentation of the ripple-texture defect regions. |
本系統之摘要資訊系依該期刊論文摘要之資訊為主。