臺灣博碩士論文加值系統

目錄:
中文摘要 I
Abstract III
誌謝 V
目錄 1
圖目錄 3
表目錄 6
第一章 簡介 7
1.1. 藥丸自動光學檢測系統 7
1.2. 智慧影像自動代理操作系統 9
第二章 文獻探討 11
2.1. 自動光學檢測相關技術 11
2.2. 市面上藥丸檢測設備 13
2.3. 市面上常見代操工具 16
2.4. 代操系統相關技術 19
第三章 方法設計 22
3.1 藥丸自動光學檢測系統 22
3.1.1 硬體設備 22
3.1.2 設定階段 25
3.1.3 檢測階段 27
3.1.4 超自動化異常瑕疵偵測方法 36
3.2 智慧影像自動代理操作系統 38
3.1.1 軟體主架構設計 40
3.1.2 代理操作步驟模組 41
3.1.3 功能插件模組 43
3.1.4 變數模組 53
3.1.5 條件控制模組 54
3.1.6 多人多機控制模組 54
3.1.7 其他 57
第四章 實驗結果 58
4.1 藥丸自動光學檢測系統 58
4.1.1 實驗設計 58
4.1.2 實驗結果 62
4.2 智慧影像自動代理操作系統 67
4.2.1 實驗設計 67
4.2.2 實驗結果 73
第五章 結論 85
參考文獻 89
附錄A：自動代操系統插件清單 96
附錄B：自動代操系統設定範例 (以Google搜尋為例) 97

圖目錄
圖1: 目標藥丸與瑕疵藥丸之例子 8
圖2: 配合廠商之數粒機填充設備 9
圖3: 兩種不同瑕疵的影像類型 11
圖4: 手動藥丸瑕疵檢測設備 14
圖5: 自動藥丸瑕疵檢測設備- Yenchen Machinery [27] 15
圖6: 自動藥丸瑕疵檢測設備- Key International [28] 15
圖7: 按鍵精靈操作畫面 (取自官方網站) 17
圖8: AutoHotKey腳本範例 (取自官方網站) 17
圖9: 簡易代操工具操作畫面 (取自官方網站) 18
圖10: RoboTask操作畫面 (取自官方網站) 19
圖11: 硬體設備俯視示意圖 22
圖12: 硬體設備剖面示意圖 23
圖13: 自動光學檢測技術-設定階段流程圖 25
圖14: 藥丸樣板範例 26
圖15: 檢測設定與檢測畫面 26
圖16: 自動光學檢測技術-檢測階段流程圖 27
圖17: 原始影像與使用者設定之檢測區域 28
圖18: 裁剪後之檢測區域 28
圖19: OK藥丸主樣板 29
圖20: OK藥丸主樣板比對結果 30
圖21: 子樣板比對方式 31
圖22: 過濾重疊位置之比對範例 31
圖23: 建立OK藥丸遮罩 32
圖24: 取得前景之步驟圖像 33
圖25: 取得NG藥丸並進行追蹤 34
圖26: 藥丸越過剔除線 35
圖27: 超自動化方法運作畫面 (a)至(d)為連續畫面 37
圖28: 代操系統與被代操設備(或軟體)之硬體架構 39
圖29: 人機操作介面(左)與智慧影像代理操作系統(右)介面 40
圖30: 自動代理操作系統架構圖 40
圖31: 自動代理操作系統流程圖 42
圖32: 定位點擊插件流程圖 45
圖33: 自動對焦插件流程圖 47
圖34: 確認畫面作動中插件流程圖 48
圖35: AI DL模型更換與偵測插件流程圖 50
圖36: AI DL應用範例-面板瑕疵偵測(非本研究之圖像，示意圖取自[43]) 51
圖37: 樣板多宮格搜尋插件流程圖 52
圖38: 樣板多宮格搜尋插件搜尋範例 53
圖39: 傳統一人一機架構 55
圖40: KVM架構 55
圖41: 多人多機搭配KVM架構 56
圖42: 多人多機OP Call運作時序圖 56
圖43: 硬體設備架設環境 59
圖44: 藥丸檢測系統介面 61
圖45: 藥丸檢測系統子介面 61
圖46: 實驗藥丸樣本 62
圖47: 橘色藥丸檢測結果 63
圖48: 白色圓形藥丸檢測結果 64
圖49: 雙色膠囊藥丸檢測結果 64
圖50: 剔除慢速攝影 65
圖51: 誤判之NG藥丸的特例 66
圖52: 代操系統主畫面 69
圖53: 請求人員介入處理(OP Call)畫面 70
圖54: 多人多機系統畫面-登入畫面 71
圖55: 多人多機系統畫面-設定畫面 72
圖56: 來源影像範例 (非本研究之實驗圖像，示意圖取自[39]) 78
圖57: 雷射修補設備畫面(左)與代操系統畫面(右) 79
圖58: 兩種不同影像但同瑕疵樣式之比較 79
圖59: 同一片面板各種不同位置所拍攝的影像色差範例 80
圖60: AI DL偵測與雷射修補設備上瑕疵位置 83
圖61: 中華民國專利資訊檢索系統之專利公報[45] 87
圖62: 榮獲【第30屆馬來西亞ITEX國際發明展】金牌獎 87

 
表目錄
表1: 國內外AOI相關研究 12
表2: 市面上常見代操工具比較表 19
表3: 設備俯視圖與剖面圖之編號說明參照表 23
表4: 功能插件需實現的內容或函式 43
表5: 對焦調整過程 46
表6: 實驗結果統計表 63
表7: 自動代操第一次實驗時間統計結果 74
表8: 自動代操第二次實驗時間統計結果 75
表9: 自動代操兩次實驗結果比較表 76
表10: 自動代操AI偵測與瑕疵匹配實驗結果 77
表11: AI DL模型訓練辨識結果統計 82

[1]N. Bhardwaj, S. Agarwal, and V. Bhardwaj (2015), “An imaging approach for the automatic thresholding of photo defects,” Pattern Recognition Letters, Vol. 61, pp. 32-40.
[2]M. H. Hung and C. H. Hsieh (2015), “A novel algorithm for defect inspection of touch panels,” Image and Vision Computing, Vol. 41, pp. 11-25.2
[3]C. F. Kuo, K. C. Peng, H. C. Wu, and C. C. Wang (2015), “Automated inspection of micro-defect recognition system for color filter,” Optics and Lasers in Engineering, Vol. 70, pp. 6-17.
[4]S. W. Yang, C. S. Lin, S. K. Lin, and H. T. Chiang (2014), “ Automatic defect recognition of TFT array process using gray level co-occurrence matrix,” Optik, Vol. 125, pp. 2671-2676.
[5]X. W. Zhang, Y. Q. Ding, Y. Y. Lv, A. Y. Shi, and R. Y. Liang (2011), “A vision inspection system for the surface defects of strongly reflected metal based on multi-class SVM,” Expert Systems with Applications, Vol. 38, pp. 5930-5939.
[6]X. F. Wang, S. B. Qiu, and Q. Wang (2011), “A new method of paper defect recognition based on wavelet packet decomposition and BP neural network,” Energy Procedia, Vol. 11, pp. 1491-1497.
[7]S. K. S. Fan and Y. C. Chuang (2010), “Automatic detection of Mura defect in TFT-LCD based on regression diagnostics,” Pattern Recognition Letters, Vol. 31, pp. 2397-2404.
[8]Y. H. Tseng and D. M. Tsai (2010), “Defect detection of uneven brightness in low-contrast images using basis image representation,” Vol. 43, pp. 1129-1141.
[9]Y. C. Chiou, C. S. Lin, and B. C. Chiou (2008), “The feature extraction and analysis of flaw detection and classification in BGA gold-plating areas,” Expert Systems with Applications, Vol. 35, pp. 1771-1779.
[10]T. Yuan and W. Kuo (2008), “Spatial defect pattern recognition on semiconductor wafers using model-based clustering and Bayesian inference,” European Journal of Operational Research, Vol. 190, pp. 228-240.
[11]C. H. Wang (2008), “Recognition of semiconductor defect patterns using spatial filtering and spectral clustering,” Expert Systems with Applications, Vol. 34, pp. 1914-1923.
[12]S. Lee, L. M. Chang, and M. Skibniewski (2006), “Automated recognition of surface defects using digital color image processing,” Automation in Construction, Vol. 15, pp.540-549.
[13]M. Aminzadeh and T. Kurfess (2015), “Automatic thresholding for defect detection by background histogram mode extents,” Journal of Manufacturing Systems, Vol. 37, pp. 83-92.
[14]Y. H. Xie and J. C. Wang (2015), “Study on the identification of the wood surface defects based on texture features,” Optik, Vol. 125, pp. 2231-2235.
[15]M. H. Karimi and D. Asemani (2014), “Surface defect detection in tiling industries using digital image processing methods: analysis and evaluation,” ISA Transactions, Vol. 53, pp. 834-844.
[16]K. Song and Y. Yan (2013), “A noise robust method based on completed local binary patterns for hot-rolled steel strip surface defects,” Applied Surface Science, Vol. 285 (Part B), pp. 858 864.
[17]E. S. Wacker and J. Denzler (2013), “Enhanced anomaly detection in wire ropes by combining structure and appearance,” Pattern Recognition Letters, Vol. 34, pp. 942-953.
[18]W. C. Li and D. M. Tsai (2012), “Wavelet-based defect detection in solar wafer images with inhomogeneous texture,” Pattern Recognition, Vol. 45, pp. 742-756.
[19]D. R. Rohrmus (2005), “Invariant and adaptive geometrical texture features for defect detection and classification,” Pattern Recognition, Vol. 38, pp. 1540-1559.
[20]Y. Shen and P. F. Taday (2008), “Development and application of terahertz pulsed imaging for nondestructive inspection of pharmaceutical tablet,” Journal of Selected Topics in Quantum Electronics, Vol. 14, No. 2, pp. 407-415.
[21]Ž. Špiclin, M. Bukovec, F. Pernuš, and B. Likar (2011), “Image registration for visual inspection of imprinted pharmaceutical tablets,” Machine Vision and Applications, Vol. 22, pp. 197-206.
[22]Z. Csoban, B. Kallai-Szabo, N. Kallai-Szabo, T. Takacs, T. Hurtony, P. Gordon, R. Zelko, and I. Antal (2016), “Assessment of distribution of pellets in tablets by non-destructive microfocus X-ray imaging and image analysis technique,” Powder Technology, Vol. 301, pp. 228-233.
[23]H. Zhang, X. Li, H. Zhong, Y. Yang, Q. M. J. Wu, J. Ge, and Y. Wang (2018), “Automated machine vision system for liquid particle inspection of pharmaceutical injection,” IEEE Transactions on Instrumentation and Measurement, Vol. 67, No. 6, pp. 1278-1297.
[24]Accura Pharmaquip Tablet Inspection Machine, https://www.youtube.com/watch?v=2Z161N6DLD8.
[25]Target Innovations Tablet Inspection Machine, http://news.targetinnovations.com/tablet-inspection-system/.
[26]SaintyCo Tablet Inspection Machine, https://www.saintyco.com/i-500-capsule-inspecting-rejecting-machine/.
[27]Yenchen Machinery Automatic Tablet Inspection, http://www.yenchen.com.tw/en/product/Automatic-Tablet-Inspection/automatic_tablet_inspection.html.
[28]Key International Enclony Planet 4.8, http://www.keyinternational.com/processing-equipment/tablet-capsule-inspection/enclony-planet-4-8-high-speed.
[29]D. M. Sangster, D. L. Ellis, N. Jayawardana, J. K. Ngari, and S. J. Fuelling (2009), “Recording, playback, and visual representation of macros,” United States Patent US20090144621A1.
[30]Y. Y. Lin and H. K. Huang (2016), “Input device and input system with macro record funcions and macro recording method thereof,” Taiwan Patent I530825.
[31]T. Yeh, T. H. Chang, and R. C. Miller (2009), “Sikuli: Using GUI screenshots for search and automation,” Proceedings of Annual ACM Symposium on User Interface Software and Technology, Victoria, BC, Canada, pp. 183-192.
[32]T. H. Chang, T. Yeh, and R. C. Miller (2010), “GUI testing using computer vision,” Proceedings of Conference on Human Factors in Computing Systems, CHI 2010, Atlanta, Georgia, USA, pp. 1535-1544.
[33]X. Lan, Y. Zhang, C. Yang, and M. Zhang(2010), “An investigation of online game bots in China,” Proceedings of International Conference on E-Product E-Service and E-Entertainment, Henan, pp. 1-5.
[34]P. Nagarani and R. V. R. Chary (2012), “A tool based approach for automation of GUI applications,” Proceedings of Third International Conference on Computing, Communication and Networking Technologies (ICCCNT'12), Coimbatore, pp. 1-6.
[35]R. C. Gonzalez and R. E. Woods (2007), Digital Image Processing Third Edition, Prentice Hall, pp. 649-700.
[36]H. Y. Kim and S. A. Araújo (2007), “Grayscale template-matching invariant to rotation, scale, translation, brightness and contrast,” IEEE Pacific-Rim Symposium on Image and Video Technology, Lecture Notes in Computer Science, Vol. 4872, pp. 100-113.
[37]R. Brunelli (2009), Template Matching Techniques in Computer Vision: Theory and Practice, Wiley Publishing.
[38]H. Y. Kim (2010), “Rotation-discriminating template matching based on fourier coefficients of radial projections with robustness to scaling and partial occlusion,” Pattern Recognition, Vol. 43, No. 3, pp. 859-872.
[39]J. Redmon and A. Farhadi (2018), “Yolov3: An incremental improvement,” arXiv:1804.02767.
[40]J. Redmon, S. Divvala, R. Girshick, and A. Farhadi (2016), “You only look once: Unified, real-time object detection,” Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 779-788.
[41]J. Redmon and A. Farhadi (2017), “YOLO9000: Better, Faster, Stronger,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263-7271.
[42]Z. Huang and J. Wang (2019), “DC-SPP-YOLO: Dense connection and spatial pyramid pooling based yolo for object detection,” arXiv:1903.08589.
[43]S.-W. Yang, C.S. Lin, S.-K. Lin, and H.-T. Chiang (2014), “Automatic defect recognition of TFT array process using gray level co-occurrence matrix,” Optik, Vol. 125, No. 11, pp. 2671-2676.
[44]A. Asad and H. Ali (2017), C# Programmer’s Study Guide (MCSD), Apress, Berkeley, CA, pp. 379-381.
[45]廖珗洲, 林子怡 (2016), “藥丸自動光學檢測裝置及檢測方法,” 中華民國發明專利 I646325. https://twpat3.tipo.gov.tw/tipotwoc/tipotwkm?!!FR_I646325