請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/87735完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 傅楸善 | zh_TW |
| dc.contributor.advisor | Chiou-Shann Fuh | en |
| dc.contributor.author | 游凱任 | zh_TW |
| dc.contributor.author | Kai-Jen Yu | en |
| dc.date.accessioned | 2023-07-19T16:11:36Z | - |
| dc.date.available | 2023-11-09 | - |
| dc.date.copyright | 2023-07-19 | - |
| dc.date.issued | 2023 | - |
| dc.date.submitted | 2023-06-16 | - |
| dc.identifier.citation | [1] S. Akcay, D. Ameln, A. Vaidya, B. Lakshmanan, N. Ahuja, and U. Genc, “Anomalib: A Deep Learning Library for Anomaly Detection,” Proceedings of IEEE International Conference on Image Processing, Bordeaux, France, pp. 1706 - 1710, 2022.
[2] Z. Chen, X. Huang, "End-to-End Learning for Lane Keeping of Self-Driving Cars," Proceedings of IEEE Intelligent Vehicles Symposium, vol. 4, pp. 1856-1860, 2017. [3] T. Defard, A. Setkov, A. Loesch, and R. Audigier, "PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization," Proceedings of International Conference on Pattern Recognition, International Workshops and Challenges, Virtual, vol. 12664, pp. 475-489, 2021. [4] A. Dogra and A. Dogra, "Performance Comparison of Gaussian and Elliptic High Pass Filter," Proceedings of International Journal of Advanced Biological and Biomedical Research, vol. 3, no. 1, pp. 93-96, 2014. [5] D. Eberly, "Minimum-Area Rectangle Containing a Set of Points," https://www.geometrictools.com/Documentation/MinimumAreaRectangle.pdf, 2023. [6] K. Erickson, "Programmable Logic Controllers," Proceedings of IEEE Potentials, vol. 15, no. 1, pp. 14 - 17, 1996. [7] R. Girshick, J. Donahue, T. Darrell, and J. Malik, "Region-Based Convolutional Networks for Accurate Object Detection and Segmentation," Proceedings of IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 38, no. 1, pp. 142-158, 2016. [8] D. Gudovskiy, S. Ishizaka, and K. Kozuka, "CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows," Proceedings of IEEE/CVF Winter Conference on Applications of Computer Vision, Waikoloa, HI, pp. 1819 - 1828, 2022. [9] K. He, X. Zhang, S. Ren, and Jian Sun, "Deep Residual Learning for Image Recognition," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, pp. 770-778, 2016. [10] G. Jocher, "YOLOv5," https://github.com/ultralytics/yolov5, 2023. [11] Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-Based Learning Applied to Document Recognition," Proceedings of the IEEE, vol. 86, no. 11, pp. 2278 - 2324, 1998. [12] B. Leibe, A. Leonardis, and B. Schiele , "Robust Object Detection with Interleaved Categorization and Segmentation," Proceedings of International Journal of Computer Vision, vol. 77, no. 1, pp. 259-289, 2008. [13] Y. Q. Liu, X. Du, H. L. Shen, and S. J. Chen, "Estimating Generalized Gaussian Blur Kernels for Out-of-Focus Image Deblurring," Proceedings of IEEE Transactions on Circuits and Systems for Video Technology, vol. 31, no. 3, pp. 829-843, 2021. [14] L. G. Nyul, J. K. Udupa, and X. Zhang, "New Variants of a Method of MRI Scale Standardization," Proceedings of IEEE Transactions on Medical Imaging, vol. 19, no. 2, pp. 143-150, 2000. [15] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You Only Look Once: Unified, Real-Time Object Detection," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, pp. 779-788, 2016. [16] K. Roth, L. Pemula, J. Zepeda, B. Schölkopf, T. Brox, and P. Gehler, "Towards Total Recall in Industrial Anomaly Detection," Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, pp. 14298 - 14308, 2022. [17] O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and F. F. Li, "ImageNet Large Scale Visual Recognition Challenge," Proceedings of International Journal of Computer Vision, vol. 115, p. 211–252, 2015. [18] P. K. Sahoo, S. Soltani, and A. K. C. Wong, "A Survey of Thresholding Techniques," Proceedings of Computer Vision, Graphics, and Image Processing, vol. 41, no. 2, pp. 233-260, 1988. [19] K. A. M. Said and A. B. Jambek, "Analysis of Image Processing Using Morphological Erosion and Dilation," Proceedings of Journal of Physics: Conference Series, vol. 2071, no. 1, pp. 1-6, 2021. [20] M. Sharif, "A New Approach to Compute Convex Hull," Proceedings of Innovative Systems Design and Engineering, ISSN (Online) 2222-2871, vol. 2, no. 3, pp. 1-8, 2011. [21] D. Silver, A. Huang, C. J. Maddison, A. Guez, L. Sifre, G. V. D. Driessche. J. Schrittwieser, I. Antonoglou, V. Panneershelvam, M. Lanctot, S. Dieleman, D. Grewe, J. Nham, N. Kalchbrenner, I. Sutskever, T. Lillicrap, M. Leach, K. Kavukcuoglu, T. Graepel, and D. Hassabis, "Mastering the Game of Go with Deep Neural Networks and Tree Search," Proceedings of Nature, vol. 529, pp. 484-503, 2016. [22] A. R. Smith, "Color Gamut Transform Pairs," Proceedings of ACM SIGGRAPH Computer Graphics, vol. 12, no. 3, pp. 12-19, 1978. [23] A. M. Turing, "Computing Machinery and Intelligence," Proceedings of Mind, vol. 59, no. 236, pp. 433-460, 1950. [24] X. Yu, T. W. Kuan, Y. Zhang, and T. Yan, "YOLO v5 for SDSB Distant Tiny Object Detection," Proceedings of International Conference on Orange Technology, Shanghai, China, vol. 10, pp. 1-4, 2022. [25] K. P. Zhang, Z. P. Zhang, Z. F. Li, and Y. Qiao, "Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks," Proceedings of IEEE Signal Processing Letters, vol. 23, no. 10, pp. 1499-1503, 2016. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/87735 | - |
| dc.description.abstract | 本論文提出游檢測: 一個結合人工智慧和傳統影像處理的水閥檢測機台，透過機台的檢測可以知道水閥產線產出的水閥是否為瑕疵品，取代用人力辨別每個水閥並找出瑕疵品的人力成本。
總共有十一種型態的水閥且正反兩面皆須檢測，對於不同水閥的每一面客製化一個專屬於它的演算法，需被檢測的瑕疵類別有黑斑、紅斑、裂痕、缺角、無反光、缺角裂痕。 水閥會先經過震動盤初步篩選正反面，然後依次放入旋轉玻璃盤，藉由上下兩站相機得到水閥正反面照片。照片首先經由傳統演算法進行降噪和去背處理，然後送入訓練好的人工智慧模型判斷是否有瑕疵，最後決定這個水閥送往瑕疵產品或好的產品或非上述兩者的出料口。 | zh_TW |
| dc.description.abstract | In this thesis, we propose YuInspect: a water valve inspection machine, which combines artificial intelligence (AI) and traditional image processing. Through machine inspection, we can determine whether the water valves produced by the production line are defective or not, thereby replacing the manual labor required to identify each valve and find defective products.
There are eleven types of water valves to be inspected on both sides. For each side of different water valves, an algorithm is customized for it. The defects to be inspected include black spots, red spots, cracks, chipping, no-lapping, and chipping-cracks. The water valves are initially screened for their orientation using a vibrating plate, and then sequentially placed on a rotating glass plate. The top and bottom cameras capture photographs of both sides of the water valve. We use traditional algorithms for noise reduction and background removal before feeding photographs into a trained AI model to detect any defects. Finally, the decision is made whether to send the water valve to the defective product, good product, or undetermined output port. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2023-07-19T16:11:35Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2023-07-19T16:11:36Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 誌謝 i
中文摘要 ii ABSTRACT iii CONTENTS v LIST OF FIGURES ix LIST OF TABLES xviii Chapter 1 Introduction 1 1.1 Background 1 1.2 Product 2 1.3 Environmental 7 1.4 Thesis Organization 11 Chapter 2 PLC [6] 12 2.1 Introduction 12 2.2 Methods 12 Chapter 3 Traditional Way 17 3.1 Gaussian Blur [13] 17 3.2 Threshold [18] 17 3.3 Ellipse Filter [4] 18 3.4 Erode [19] 19 3.5 Dilate [19] 20 3.6 Max Contour and Rotation 21 3.7 Rotate the Original Image 22 3.8 Crop Image 23 3.9 Background Removal 24 3.10 Uniform Image Height Greater than Width 25 3.11 Decide if No-Lapping 26 3.12 Image Enhancement 27 3.13 Check if Reverse 29 3.14 Calculate Size 36 3.15 Traditional Flow Chart 37 Chapter 4 AI Way 38 4.1 AI background 38 4.2 Deep Learning and Convolutional Neural Network (CNN) 38 4.3 Object Detection 40 4.3.1 Background 40 4.3.2 R-CNN 41 4.4 You Only Look Once (YOLO) [15] 42 4.5 YOLOv5 [10] 44 4.6 YOLOv5 [10] Find Spot and Crack 46 4.7 Anomalib [1] 54 4.7.1 Background 54 4.7.2 Anomalib-Padim [3] 55 4.7.3 Residual Neural Network (ResNet) [9] 56 4.7.4 Hue, Saturation, Value (HSV) [22] 59 4.7.5 Result 60 4.8 Combine 62 Chapter 5 GUI 65 5.1 Function Introduction 65 5.2 User-Customized Settings 69 Chapter 6 Problems and Solutions 71 6.1 140N Problem 71 6.2 140C Problem 72 6.3 Light Source Adjustment 74 6.4 D69M Problem 76 6.5 D68F Problem 78 Chapter 7 Results 80 7.1 Result 80 7.2 Inspection Speed 87 Chapter 8 Conclusion and Future Works 88 References 89 | - |
| dc.language.iso | en | - |
| dc.subject | 游檢測 | zh_TW |
| dc.subject | 光學瑕疵檢測 | zh_TW |
| dc.subject | 工業產品影像處理 | zh_TW |
| dc.subject | 水閥瑕疵檢測 | zh_TW |
| dc.subject | 人工智慧瑕疵檢測 | zh_TW |
| dc.subject | iIndustrial product image processing | en |
| dc.subject | optical defect inspection | en |
| dc.subject | water valve defect inspection | en |
| dc.subject | YuInspect | en |
| dc.subject | Artificial Intelligence defect inspection | en |
| dc.title | 游檢測 : 水閥瑕疵檢測 | zh_TW |
| dc.title | YuInspect: Water Valve Defect Inspection | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 111-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 巫宗昇;方瓊瑤 | zh_TW |
| dc.contributor.oralexamcommittee | Zong-Sheng Wu;Qiong-Yao Fang | en |
| dc.subject.keyword | 游檢測,工業產品影像處理,光學瑕疵檢測,水閥瑕疵檢測,人工智慧瑕疵檢測, | zh_TW |
| dc.subject.keyword | YuInspect,iIndustrial product image processing,optical defect inspection,water valve defect inspection,Artificial Intelligence defect inspection, | en |
| dc.relation.page | 93 | - |
| dc.identifier.doi | 10.6342/NTU202301016 | - |
| dc.rights.note | 未授權 | - |
| dc.date.accepted | 2023-06-16 | - |
| dc.contributor.author-college | 電機資訊學院 | - |
| dc.contributor.author-dept | 資訊工程學系 | - |
| 顯示於系所單位： | 資訊工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-111-2.pdf 未授權公開取用 | 4.94 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。