影像處理應用於預充填針劑瓶之法蘭損傷研究

以作者查詢圖書館館藏

、以作者查詢臺灣博碩士

、以作者查詢全國書目

、勘誤回報

、線上人數：46

、訪客IP：3.22.249.135

姓名

邱以利(Yi-Li Chiu) 查詢紙本館藏

畢業系所

機械工程學系在職專班

論文名稱

影像處理應用於預充填針劑瓶之法蘭損傷研究
(Research on Image Analysis Applied to Flange Damage Detection)

相關論文

★ 應用於車身號碼打刻機之號碼辨識	★ 複合式掌紋識別系統
★ 圓形偵測在OLED Panel 檢測上的應用	★ MLCC薄膜厚度即時線上影像檢測技術之研發
★ 全自動微鑽針影像檢測系統之研究	★ 應用類神經網路預測COG製程對於中小尺寸TFT-LCD產生之應力狀態
★ 應用機器視覺系統檢測高滲透壓刀輪切割 TFT-LCD 玻璃後斷面之研究	★ 低成本輕量化機械手臂之研究
★ 應用在同軸電纜加工之雷射光斑導引機構設計與分析	★ 表面電漿波共振-非旋轉方式的新機構設計理論
★ 網路協同式機械設計系統研發	★ 軟膠囊自動辨識系統
★ 心電訊號之擷取與分析	★ 盲人圖樣感知輔助裝置之研發設計
★ 非旋轉式表面電漿共振儀之改良與實現	★ 可攜式無線心電訊號擷取器之設計

檔案

[Endnote RIS 格式]

[Bibtex 格式]

[相關文章]

[文章引用]

[完整記錄]

[館藏目錄]

至系統瀏覽論文 (2027-7-31以後開放)

摘要(中)

預充式注射器是近代醫學中廣泛使用的醫療器械之一，為了提升醫療品質並獲得更健康、舒適的醫療服務，注射器結合人因工程領域的創新，發展出許多類型的注射型態以符合不同患者的需求。如果注射器內部的針劑瓶法蘭面破損，導致患者在緊急情況時無法將藥劑順利地注入體內，將會危及患者的生命安全，造成無可挽回的嚴重後果。
　　本研究旨在探討如何運用非接觸式的影像處理技術，檢測預充式針劑瓶的法蘭輪廓損傷，以AlexNet預訓練卷積神經網路進行遷移學習，將訓練資料分成完整輪廓、破損輪廓、無藥瓶三種類別，快速對影像的數據分類並且分析模型的精確度、召回率、F1-Score以及準確度，同時建立一套自動化檢測系統分析法蘭的損傷特徵，避免不符合規範的藥瓶流入市場。
　　研究結果顯示遷移學習應用於法蘭檢測具可行性，其正面法蘭模型的辨識準確度可達94.07%，背面法蘭模型的辨識準確度可達90.55%。經過法蘭輪廓檢測系統對遷移學習修正後，可將正面法蘭誤判成NOK的樣本總數從原先的3.7%降至2.2%，背面法蘭誤判成NOK的樣本總數從原先的6.5%降至2.6%，且實際為破損法蘭卻誤判成完整輪廓的影像皆能被檢測系統修正成正確的分類項目，最終正面法蘭影像得到97.77%的準確度，背面法蘭影像得到97.4%的準確度。

摘要(英)

Nowadays, Prefilled syringes are widely used medical devices in modern medical community. In order to allow each patient to experience a comfortable medical quality, many different types of prefilled syringes have been developed in past decades. However, when a flange of the syringe is broken, the patient is not able to use the syringe in an emergency. This problem may affect the life with irreversible outcome and should be avoided.
This research explores the methods using machine vision to detect flange edge in prefilled syringe. The AlexNet convolutional neural network is used for transfer learning and divides the data into three categories: normal flange image, Broken Flange image and no medicine bottle image. Confusion Matrix is the evaluation method of this research. The performance of the model is evaluated by four metrics: Precision, Recall, F1-Score, and Accuracy.
The results of the research found that applying transfer learning to detect flanges is a feasible solution. The model accuracy of Front-Flange and Back-Flange can reach 94.07% and 90.55%. This research also developed a detection system, which can correct the damaged flanges misjudged as OK image. Finally, Front-Flange model got 97.77% accuracy and Back-Flange model got 97.4% accuracy.

關鍵字(中)

★ 預充式注射器
★ 法蘭破損
★ 機器視覺
★ 遷移學習

關鍵字(英)

★ Prefilled syringe
★ Flange damage
★ Machine vision
★ Transfer learning

論文目次

摘要 I
ABSTRACT II
謝誌 III
目錄 IV
圖目錄 VII
表目錄 X
第一章緒論 1
1.1 研究背景 1
1.1.1 醫療注射器械型態分類 1
1.1.2 預充式藥瓶之優勢 3
1.2 研究動機及目的 4
1.2.1 預充式注射器的潛在風險 4
1.2.2 研究目的 6
1.3 論文架構 7
第二章文獻探討 8
2.1 影像處理於損傷檢測之應用 8
2.2 影像處理技術 9
2.2.1 背景提取操作 9
2.2.2 影像分割及去背 11
2.2.3 霍夫轉換 12
2.2.4 侵蝕與膨脹 13
2.2.5 卷積神經網路 14
2.2.5.1 卷積層（Convolution Layer） 15
2.2.5.2 池化層（Pooling Layer） 15
2.2.5.3 平坦層（Flatten Layer） 16
2.2.5.4 全連接層（Fully-connected Layer） 16
2.2.6 神經網路 AlexNet 17
2.2.7 遷移學習（Transfer Learning） 18
第三章實驗設計與規劃 19
3.1 實驗設備-藥瓶組裝檢測旋轉平台 19
3.2 實驗樣本蒐集 21
3.3 法蘭輪廓檢測系統-程式介面 22
3.4 影像檢測系統流程圖 24
第四章模型建構 26
4.1 影像配准 26
4.2 ROI背景移除 29
4.3 三相異點自動尋邊 34
4.4 異質陣列灰階檢測 37
4.4.1法蘭中間圓弧檢測 37
4.4.2法蘭邊緣圓弧檢測 44
4.5法蘭輪廓臨界閥值調整 47
第五章實驗結果與討論 53
5.1 影像配准-運算子精度探討 53
5.2 臨界閥值之測試結果 57
5.3 模型效能評估 60
第六章結論與未來展望 70
6.1 結論 70
6.2 未來展望 71
參考文獻 72
附錄A 法蘭輪廓檢測系統-程式介面介紹 75
附錄B 影像配准檢測系統-程式介面介紹 78

參考文獻

[1] J. Jin, et al, "The Optimal Choice of Medication Administration Route Regarding Intravenous, Intramuscular, and Subcutaneous Injection," DovePress, vol. 9, pp. 923-942, 2015.
[2] 楊中辰．藥用玻璃容器分類和應用指南．中國醫藥包裝協會．2021
[3] J. Mead, R. Dammerman and S. Rasmussen, " Patient Reported Ease-of-Use with a Disposable Autoinjector in Individuals with Migraine," DovePress, vol. 14, pp. 1137-1144, 2020.
[4] 王澤瑋．可攜式肌肉注射裝置之可行性分析與設計．國立交通大學機械工程學系．碩士論文．2009
[5] Food and Drug Administration, et al, "FDA Drug Safety Communication: Connection problems involving certain needleless pre-filled glass syringes containing adenosine and amiodarone," Silver Spring, Md 20993, 2013.
[6] Food and Drug Administration, et al, "Glass Syringes for Delivering Drug and Biological Products: Technical Information to Supplement International Organization for Standardization (ISO) Standard 11040-4," Silver Spring, Md 20993, 2013.
[7] L. Li, "Advances in Container Closure Integrity Testing," in Sterile Product Development, Springer, New York, pp. 315-329, 2013.
[8] 李益誠．影像處理於渦扇發動機轉子葉片損傷之檢測．國立中央大學機械工程學系．碩士論文．2019
[9] 吳亭慧．筆記型電腦滑鼠觸控板表面瑕疵檢測系統．國立台北科技大學機械工程學系．碩士論文．2019
[10] 田玉銓．基於行車紀錄器影像之道路標線破損評估系統．國立台灣海洋大學電機工程系．碩士論文．2020
[11] 徐睿鴻．咖啡瑕疵豆篩選機研究與實作-基於深度學習與輸送帶架構．國立雲林科技大學電機工程系．碩士論文．2022
[12] Z. Z. Chong, S. B. Tor, A. M. Gañán Calvo, Z. J. Chong, N. H. Loh, N.-T. Nguyen and S. H. Tan, "Automated droplet measurement (ADM): an Enhanced Video Processing Software for Rapid Droplet Measurements," Springer, vol. 20, no. 4, pp. 1-14, 2016.
[13] T. Porter and T. Duff, "Compositing Digital Images," ACM SIGGRAPH Computer Graphics, vol. 18, no. 3, pp. 253-259, 1984.
[14] P. V. C. Hough, "Method and Means for Recognizing Complex Patterns," U.S. Patent, no. 3069654, 1962.
[15] P. V. C. Hough, "Machine Analysis of Bubble Chamber Pictures," Proc. Int. Conf. High Energy Accelerators and Instrumentation, pp.554-558, 1959.
[16] R. O. Duda and P. E. Hart, "Use of the Hough Transformation to Detect Lines and Curves in Pictures," Communications of the ACM, vol. 15, no. 1, pp. 11-15, 1972.
[17] J. Y. Gil, R. Kimmel, "Efficient Dilation, Erosion, Opening and Closing Algorithms," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 12, pp. 1606-1617, 2002.
[18] D. H. Hubel and T. N. Wiesel, "Receptive Fields, Binocular Interaction and Functional Architecture in the Cat′s Visual Cortex," The Journal of Physiology, vol. 160, no. 1, pp. 106-154. 1962.
[19] Y. LeCun, L. Bottou and P. Haffner, "Gradient-based Learning Applied to Document Recognition," Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, 1998.
[20] 陳昭明．深度學習最佳入門邁向AI專題實戰．深智數位．台北市．2021
[21] A. Krizhevsky, I. Sutskever and G. E. Hiton, "ImageNet Classfication with Deep Convolutional Neural Networks," Advances in Neural Information Processing Systems, vol. 25, pp. 1090-1098, 2012.
[22] S. J. Pan and Q. Yang, "A Survey on Transfer Learning," IEEE Transactions on Knowledge and Data Engineering, vol. 22, no. 10, pp. 1345-1359, 2010.
[23] B. Zitova and J. Flusser, "Image Registration Methods: a Survey," Image and vision computing, vol. 21, no. 11, pp. 977-1000, 2003.
[24] 葉怡成．實驗計畫法-製程與產品最佳化．五南圖書出版．台北市．2001
[25] 陳維正．應用相對基本法之立體影像扭正．國立交通大學機械工程學系．碩士論文．2004
[26] N. Otsu, "A Threshold Selection Method from Gray-Level Histograms," IEEE Transactions on Systems, Man, and Cybernetics, vol. 9, no. 1, pp. 62-66, 1979.
[27] J. H. Xue and Y. J. Zhang, "Ridler and Calvard’s, Kittler and Illingworth’s and Otsu’s Methods for Image Thresholding," Pattern Recognition Letters, vol. 33, no. 6, pp. 793-797, 2012.
[28] X. Dong, G. Wang, Y. Pang, W. Li, J. Wen, W. Meng, and Y. Lu, "Fast Efficient Algorithm for Enhancement of Low Lighting Video," IEEE International Conference on Multimedia and Expo (ICME), pp. 1-6, 2010.
[29] A. Georgantzoglou, J. d. Silva and R. Jena, " Image Processing with MATLAB and GPU," in MATLAB Applications for the Practical Engineer, IntechOpen, ISBN: 978-953-51-1719-3, 2014.
[30] K. He, J. Sun, and X. Tang, "Single Image Haze Removal Using Dark Channel Prior," IEEE transactions on pattern analysis and machine intelligence, vol. 33, no. 12, pp. 2341-2353, 2010.
[31] B. P. Salmon, W. Kleynhans, C. P. Schwegmann and J. C. Olivier, "Proper Comparison Among Methods Using a Confusion Matrix," 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), pp. 3057-3060, 2015.

指導教授

黃衍任(Yean-Ren Hwang)

審核日期

2022-8-3

推文