請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/88123完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 李貫銘 | zh_TW |
| dc.contributor.advisor | Kuan-Ming Li | en |
| dc.contributor.author | 唐大為 | zh_TW |
| dc.contributor.author | Ta-Wei Tang | en |
| dc.date.accessioned | 2023-08-08T16:24:02Z | - |
| dc.date.available | 2023-11-09 | - |
| dc.date.copyright | 2023-08-08 | - |
| dc.date.issued | 2023 | - |
| dc.date.submitted | 2023-07-13 | - |
| dc.identifier.citation | [1] Artificial Intelligence (AI) Market (2023). https://www.precedenceresearch.com/artificial-intelligence-market
[2] Keiron O'Shea, Ryan Nash. (2015). An Introduction to Convolutional Neural Networks. arXiv, arXiv:1511.08458. [3] Jong Hyuk Lee, Byeong Hak Kim, Min Young Kim. (2021). Machine Learning-based Automatic Optical Inspection System with Multimodal Optical Image Fusion Network. International Journal of Control, Automation and Systems, 19, 3503-3510. [4] Jiaquan Shen,Ningzhong Liu,Han Sun. (2021). Defect detection of printed circuit board based on lightweight deep convolution network. IET Image Processing, 14(15), 3932-3940. [5] Ji Kun,Zhang Zhenhai,Yu Jiale,Dang Jianwu. (2022). A deep learning-based method for pixel-level crack detection on concrete bridges. IET Image Processing, 16(10), 2609-2622. [6] Jiawei Pan,Deyu Zeng,Qi Tan,Zongze Wu,Zhigang Ren. (2022). EU-Net: A novel semantic segmentation architecture for surface defect detection of mobile phone screens. IET Image Processing, 16(10), 2568-2576. [7] Saad Mohamed Darwish. (2013). Soft computing applied to the build of textile defects inspection system. IET Image Processing, 7(5), 373-381. [8] Xiaokang Zhou, Yiyong Hu, Wei Liang, Jianhua Ma, Qun Jin. (2021). Variational LSTM Enhanced Anomaly Detection for Industrial Big Data. IEEE Transactions on Industrial Informatics, 17(5), 3469-3477. [9] Xiaokang Zhou, Wei Liang, Shohei Shimizu, Jianhua Ma, Qun Jin. (2021). Siamese Neural Network Based Few-Shot Learning for Anomaly Detection in Industrial Cyber-Physical Systems. IEEE Transactions on Industrial Informatics, 17(8), 5790-5798. [10] Zhipeng Wang,Chunping Hou,Bangbang Ge,Yang Liu,Zhicheng Dong,Zhiqiang Wu. (2022). Unsupervised anomaly detection via dual transformation-aware embeddings. IET Image Processing, 16(6), 1657-1668. [11] Karsten Roth, Latha Pemula, Joaquin Zepeda, Bernhard Schölkopf, Thomas Brox, Peter Gehler. (2022). Towards Total Recall in Industrial Anomaly Detection. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 14318-14328. [12] Dor Bank, Noam Koenigstein, Raja Giryes. (2020). Autoencoders. arXiv, arXiv:2003.05991. [13] Dunphy, K., Fekri, M.N., Grolinger, K., Sadhu. (2022). Data Augmentation for Deep-Learning-Based Multiclass Structural Damage Detection Using Limited Information. Sensors, 22, 6193. [14] Wang, L., Tang, D., Liu, C., Nie, Q., Wang, Z., Zhang, L. (2022). An Augmented Reality-Assisted Prognostics and Health Management System Based on Deep Learning for IoT-Enabled Manufacturing. Sensors, 22, 6472. [15] Zhang, H., Cao, J., Zheng, D., Yao, X., Ling, B.W.K. (2022). Deep Learning-Based Synthesized View Quality Enhancement with DIBR. Distortion Mask Prediction Using Synthetic Images. Sensors, 22, 8127. [16] Thomas Schlegl, Philipp Seeböck, Sebastian M. Waldstein, Ursula Schmidt-Erfurth, Georg Langs. (2017). Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery. International Conference on Information Processing in Medical Imaging, 147-157. [17] Samet Akcay, Amir Atapour-Abarghouei, Toby P. Breckon. (2018). GANomaly: Semi-supervised Anomaly Detection via Adversarial Training. Asian Conference on Computer Vision, 622-637. [18] Samet Akcay, Amir Atapour-Abarghouei, Toby P. Breckon. (2019). Skip-GANomaly: Skip Connected and Adversarially Trained Encoder-Decoder Anomaly Detection. International Joint Conference on Neural Networks. [19] Jie Yang, Yong Shi, Zhiquan Qi. (2020). DFR: Deep Feature Reconstruction for Unsupervised Anomaly Segmentation. arXiv, arXiv:2012.07122. [20] David H. Hubel. (2004). Our First Paper, on Cat Cortex, 1959. Brain and Visual Perception: The Story of a 25-year Collaboration, 59-82. [21] Yann LeCun Leon Bottou Yoshua Bengio and Patrick Haffner. (1998). GradientBased Learning Applied to Document Recognition. PROC OF THE IEEE. [22] 陳思翰，陳金聖，唐大為。 (2020)。 Si-EYE深度學習與卷積神經網路-圖像檢測原理與應用。智泰科技股份有限公司。 [23] M.A. Hearst, S.T. Dumais, E. Osuna, J. Platt, B. Scholkopf. (1998). Support vector machines. IEEE Intelligent Systems and their Applications, 13(4), 18-28. [24] M.A. Ganaie, Minghui Hu, A.K. Malik, M. Tanveer, P.N. Suganthan. (2022). Ensemble deep learning: A review. arXiv, arXiv:2104.02395. [25] Leo Breiman. (2001). Random Forests. Machine Learning, 45, 5-32. [26] Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, Li Fei-Fei. (2009). ImageNet: A large-scale hierarchical image database. 2009 IEEE Conference on Computer Vision and Pattern Recognition, 20-25. [27] Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton. (2012). ImageNet Classification with Deep Convolutional Neural Networks. Advances in Neural Information Processing Systems 25 (NIPS 2012). [28] Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich. (2014). Going Deeper with Convolutions. arXiv, arXiv:1409.4842. [29] Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun. (2015). Deep Residual Learning for Image Recognition. arXiv, arXiv:1512.03385. [30] Saining Xie, Ross Girshick, Piotr Dollár, Zhuowen Tu, Kaiming He. (2017). Aggregated Residual Transformations for Deep Neural Networks. arXiv, arXiv:1611.05431. [31] Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, Hartwig Adam. (2017). MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv, arXiv:1704.04861. [32] Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen. (2018). MobileNetV2: Inverted Residuals and Linear Bottlenecks. arXiv, arXiv:1801.04381. [33] Andrew Howard, Mark Sandler, Grace Chu, Liang-Chieh Chen, Bo Chen, Mingxing Tan, Weijun Wang, Yukun Zhu, Ruoming Pang, Vijay Vasudevan, Quoc V. Le, Hartwig Adam. (2019). Searching for MobileNetV3. arXiv, arXiv:1905.02244. [34] The CIFAR-10 dataset. https://www.cs.toronto.edu/~kriz/cifar.html. [35] Tsung-Yi Lin, Michael Maire, Serge Belongie, Lubomir Bourdev, Ross Girshick, James Hays, Pietro Perona, Deva Ramanan, C. Lawrence Zitnick, Piotr Dollár. (2015). Microsoft COCO: Common Objects in Context. arXiv, arXiv:1405.0312. [36] Olaf Ronneberger, Philipp Fischer, Thomas Brox. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. International Conference on Medical Image Computing and Computer-Assisted Intervention, 234-241. [37] Jonathan Long, Evan Shelhamer, Trevor Darrell. (2015). Fully Convolutional Networks for Semantic Segmentation. arXiv, arXiv:1411.4038. [38] Karen Simonyan, Andrew Zisserman. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv, arXiv:1409.1556. [39] Paul Bergmann, Michael Fauser, David Sattlegger, Carsten Steger. (2019). MVTec AD — A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 15-20. [40] Neelu Madan, Nicolae-Catalin Ristea, Radu Tudor Ionescu, Kamal Nasrollahi, Fahad Shahbaz Khan, Thomas B. Moeslund, Mubarak Shah. (2022). Self-Supervised Masked Convolutional Transformer Block for Anomaly Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 14(8). [41] Jonathan Pirnay, Keng Chai. (2021). Inpainting Transformer for Anomaly Detection. arXiv, arXiv:2104.13897. [42] Yunkang Cao, Qian Wan, Weiming Shen, Liang Gao. (2022). Informative knowledge distillation for image anomaly segmentation. Knowledge-Based Systems,248,108846. [43] Hanqiu Deng, Xingyu Li. (2022). Anomaly Detection via Reverse Distillation from One-Class Embedding, arXiv, arXiv:2201.10703. [44] Ta-Wei Tang, Wei-Han Kuo, Jauh-Hsiang Lan, Chien-Fang Ding, Hakiem Hsu, Hong-Tsu Young. (2020). Anomaly Detection Neural Network with Dual Auto-Encoders GAN and Its Industrial Inspection Applications. Sensors, 20(12), 3336. [45] Ta-Wei Tang, Hakiem Hsu, Kuan-Ming Li. (2023). Industrial anomaly detection with multiscale autoencoder and deep feature extractor-based neural network. IET Image Processing, 17, 16. [46] Ta-Wei Tang ,Hakiem Hsu, Wei-Ren Huang, Kuan-Ming Li. (2022). Industrial Anomaly Detection with Skip Autoencoder and Deep Feature Extractor. Sensors, 22(23), 9327. [47] Diederik P. Kingma, Jimmy Ba. (2014). Adam: A Method for Stochastic Optimization. arXiv, arXiv:1412.6980. [48] Intel Core i7 10th Gen. https://www.newegg.com/intel-core-i7-10700k-core-i7-10th-gen/p/N82E16819118123. [49] NVIDIA GEFORCE GTX 1080 Ti. https://www.amazon.com/Nvidia-GEFORCE-GTX-1080-Ti/dp/B07NHHKFLG. [50] 李浩平 (2022)。領域自適應應用於自動化光學檢測。碩士論文，國立臺灣大學機械工程學研究所，臺北市。 [51] BFLY-PGE-50S5C-C 2/3" Blackfly® PoE GigE Color Camera. https://www.edmundoptics.com/p/bfly-pge-50s5c-c-2-3-blackfly-reg-poe-gige-color-camera/3876/. [52] Classification: ROC Curve and AUC. https://developers.google.com/machine-learning/crash-course/classification/roc-and-auc?hl=en. [53] Karsten Roth, Latha Pemula, Joaquin Zepeda, Bernhard Schölkopf, Thomas Brox, Peter Gehler. (2022). Towards Total Recall in Industrial Anomaly Detection. arXiv, arXiv:2106.08265. [54] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, Illia Polosukhin. (2017). Attention Is All You Need. arXiv, arXiv:1706.03762. [55] Welcome to Python.org. https://www.python.org/. [56] PyQt5 – PyPI. https://pypi.org/project/PyQt5/. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/88123 | - |
| dc.description.abstract | 隨著深度學習的技術日益成熟，將此技術應用於影像檢測的案例已經成為近年來學界與業界重要的研究議題。然而，過去的卷積神經網路檢測方法需要蒐集大量的瑕疵樣本圖像並消耗大量時間進行人工標記，這導致了深度學習導入實際產線的困難。有鑑於此，本研究提出了三個新的異常偵測模型，並探討其應用於實際產線檢測的效果。研究結果顯示所提出的模型在公開資料集 MVTec AD中比起過去的異常偵測方法有著更好的異常偵測能力。此外，在本研究中蒐集的兩組實際產線資料集中，由於其中的圖像更為複雜，因此所提出的方法優勢也更為明顯。更甚，本研究也探討了不同特徵抽取器對檢測效果的影響，結果顯示即使只使用較為輕量化的預訓練特徵抽取器，所提出的方法仍然具有良好的檢測能力，這代表了即使在算力受限的實際產線硬體中，所提出的方法仍然可以維持相當的檢測能力。最後，本研究也設計了應用程式軟體，讓使用者可以很簡單地訓練本研究所提出的模型，並與相機或網域內的硬體串接。這將使本研究可以更好地被應用於實際產線，真正為業界創造價值! | zh_TW |
| dc.description.abstract | With the growing of deep learning techniques, applying this technology to image detection has become an important research topic in both academia and industry in recent years. However, previous CNN (Convolutional Neural Network) detection methods required collecting a large number of defective sample images and spending a lot of time on manual labeling, which made it difficult to implement deep learning in actual production lines. Therefore, this study proposes three new anomaly detection models and explores their effectiveness in real production line detection. The results show that the proposed models have better anomaly detection capabilities compared to previous methods on the publicly available dataset MVTec AD. Furthermore, in the two sets of actual production line datasets collected in this study, the advantages of the proposed methods are even more apparent due to the more complex images in these datasets. Moreover, this study investigates the impact of different feature extractors on detection performance. The results show that even with lightweight (require fewer computational resources) pre-trained feature extractors, the proposed methods still maintain good detection capabilities. This means that even in actual production line hardware with limited computing power, the proposed methods can still maintain considerable detection capabilities. Finally, an application software that allows users to easily train the proposed models and interface with cameras or hardware within the same internet domain was designed in this study. This will enable the application of the proposed methods in actual production lines, creating real value for the industry. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2023-08-08T16:24:02Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2023-08-08T16:24:02Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 口試委員審定書 i
中文摘要 ii ABSTRACT iii ACKNOWLEDGEMENT v CONTENTS vi LIST OF TABLES ix LIST OF FIGURES xi CHAPTER 1 INTRODUCTION 1 1.1 Background of the Research 1 1.2 Motivation 3 1.3 Objectives 4 1.4 Research Methodology 5 1.5 Dissertation Framework 6 CHAPTER 2 LITERATURE REVIEW 7 2.1 Deep Learning-based Image Models 7 2.2 Deep Learning-based Anomaly Detection 21 2.3 Concluding Remark 30 CHAPTER 3 METHODOLOGY 31 3.1 Datasets 31 3.2 Proposed Method 1: Dual AE GAN Model 37 3.3 Proposed Method 2: Skip Autoencoder Model 42 3.4 Proposed Method 3: Multiscale Loss AE Model 47 3.5 Training Detail 52 3.6 Equipment 53 3.7 Evaluation Method 56 3.8 Concluding Remark 59 CHAPTER 4 EXPERIMENTAL RESULTS 60 4.1 Results of Dual GAN AE Model 60 4.2 Results of Skip AE Model 64 4.3 Results of Multiscale Loss AE Model 72 4.4 Comparison of Three Proposed Methods 81 4.5 Cases Study 83 4.6 Concluding Remark 90 CHAPTER 5 APPLICATION SOFTWARE DESIGN 91 5.1 Training Tool 92 5.2 Verification Tool 93 5.3 Detection Tool 94 5.4 Case Study 95 5.5 Concluding Remark 99 CHAPTER 6 CONCLUSIONS AND FUTURE WORK 100 6.1 Conclusions 100 6.2 Future Work 103 REFERENCE 104 | - |
| dc.language.iso | en | - |
| dc.subject | 異常偵測 | zh_TW |
| dc.subject | 工業檢測 | zh_TW |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | 瑕疵檢測 | zh_TW |
| dc.subject | 特徵抽取 | zh_TW |
| dc.subject | deep learning | en |
| dc.subject | industrial inspection | en |
| dc.subject | defect detection | en |
| dc.subject | anomaly detection | en |
| dc.subject | feature extraction | en |
| dc.title | 基於深度學習工業異常檢測方法之研究 | zh_TW |
| dc.title | Research of Deep Learning-based Industrial Anomaly Detection | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 111-2 | - |
| dc.description.degree | 博士 | - |
| dc.contributor.oralexamcommittee | 楊宏智;張恆華;許志青;黃暐仁 | zh_TW |
| dc.contributor.oralexamcommittee | Hong-Tsu Young;Herng-Hua Chang;Hakiem Hsu;Wei-Ren Huang | en |
| dc.subject.keyword | 異常偵測,深度學習,工業檢測,瑕疵檢測,特徵抽取, | zh_TW |
| dc.subject.keyword | anomaly detection,deep learning,industrial inspection,defect detection,feature extraction, | en |
| dc.relation.page | 108 | - |
| dc.identifier.doi | 10.6342/NTU202301528 | - |
| dc.rights.note | 同意授權(限校園內公開) | - |
| dc.date.accepted | 2023-07-14 | - |
| dc.contributor.author-college | 工學院 | - |
| dc.contributor.author-dept | 機械工程學系 | - |
| dc.date.embargo-lift | 2028-07-12 | - |
| 顯示於系所單位： | 機械工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-111-2.pdf 未授權公開取用 | 5.91 MB | Adobe PDF | 檢視/開啟 |
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。