請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/92989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 | 何志宏 | zh_TW |
| dc.contributor.author | Zhi-Hong He | en |
| dc.date.accessioned | 2024-07-12T16:09:27Z | - |
| dc.date.available | 2024-07-13 | - |
| dc.date.copyright | 2024-07-12 | - |
| dc.date.issued | 2024 | - |
| dc.date.submitted | 2024-07-05 | - |
| dc.identifier.citation | [1] S. Akcay, A. Atapour-Abarghouei, and T. P. Breckon “GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training,” https://arxiv.org/abs/1805.06725, 2018.
[2] P. Bergmann, M. Fauser, D. Sattlegger, and C. Steger, “Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, pp. 4183–4192, doi: 10.1109/CVPR42600.2020.00424, 2020. [3] C. Ding, G. Pang, and C. Shen, “Catching Both Gray and Black Swans: Open-Set Supervised Anomaly Detection,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, pp. 7388-7398, doi:10.1109/CVPR52688.2022.00724, 2022. [4] J. Ho, A. Jain, and P. Abbeel, “Denoising Diffusion Probabilistic Models,” Advances in Neural Information Processing Systems 33, pp. 6840-6851, https://arxiv.org/abs/2006.11239, 2020. [5] E. Hu, Y. Shen, P. Wallis, Z. Allen Zhu, Y. Li, S. Wang, L. Wang, and W. Chen, “LoRA: Low-Rank Adaptation of Large Language Models,” https://doi.org/10.48550/arXiv.2106.09685, 2021. [6] D. P. Kingma, and M. Welling, “Auto-Encoding Variational Bayes,” https://doi.org/10.48550/arXiv.1312.6114, 2013. [7] Z. Liu, Y. Zhou, Y. Xu, and Z. Wang, “SimpleNet: A Simple Network for Image Anomaly Detection and Localization,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, pp. 20402-20411, doi: 10.1109/CVPR52729.2023.01954, 2023. [8] A. Mousakhan, T. Brox, and J. Tayyub “Anomaly Detection with Conditioned Denoising Diffusion Models,” https://arxiv.org/abs/2305.15956, 2023. [9] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi “You Only Look Once: Unified, Real-Time Object Detection,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, pp. 779-788, doi: 10.1109/CVPR.2016.91, 2016. [10] K. Roth, L. Pemula, J. Zepeda, B. Schölkopf, T. Brox, and P. Gehler, “Towards Total Recall in Industrial Anomaly Detection,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, pp. 14318-14328, doi: 10.1109/CVPR52688.2022.01392, 2022. [11] M. Teodorczyk, M. Cardosi, and S. Setford, “Hematocrit Compensation in Electrochemical Blood Glucose Monitoring Systems,” Journal of Diabetes Science and Technology, vol. 6, no. 3, pp. 648-655, doi: 10.1177/193229681200600320, 2012. [12] WHO, “Thermostability of Human Insulin,” WHO Technical Document, https://www.who.int/publications/i/item/9789240089044, 2024. [13] J. Wyatt, A. Leach, S. M. Schmon, and C. G. Willcocks, “AnoDDPM: Anomaly Detection with Denoising Diffusion Probabilistic Models using Simplex Noise,” https://openaccess.thecvf.com/content/CVPR2022W/NTIRE/papers/Wyatt_AnoDDPM_Anomaly_Detection_With_Denoising_Diffusion_Probabilistic_Models _Using_Simplex_CVPRW_2022_paper.pdf, 2024. [14] V. Zavrtanik, M. Kristan, and D. Skočaj, “Reconstruction by Inpainting for Visual Anomaly Detection,” Pattern Recognition, vol. 112, no. 107706, pp. 107706???, doi: 10.1016/j.patcog.2020.107706, 2021. [15] V. Zavrtanik, M. Kristan, and D. Skočaj, “DSR – A Dual Subspace Re-Projection Network for Surface Anomaly Detection,” Proceedings of European Conference on Computer Vision, Tel Aviv, Israel, pp. 539-554, 2022. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/92989 | - |
| dc.description.abstract | 血糖酵素試片是糖尿病管理的重要部分，然而在網版印刷方式的印製過程中可能會出現錯誤，例如血糖酵素試片的導電碳墨溢出或破損，可能導致檢測結果的不準確性，進而影響患者的健康管理。當前製程中會於流水線的過程中安排人工檢測血糖酵素試片，其成本不容小覷，本研究旨在開發能應用於工業場景的血糖酵素試片碳墨瑕疵檢測方法。
由於工業製程中的異常樣品難以獲得，故傳統監督式檢測方法並不適用。本論文提出的HeInspect是基於Mousakhan, Arian and Brox, Thomas and Tayyub, Jawad於2023所發表的DDAD (Anomaly Detection with Conditioned Denoising Diffusion Models)採用無監督的異常檢測架構[11]。考量其龐大的計算成本，本論文利用自編碼器等技術對影像進行特徵提取和重建，通過比較重建影像與真實影像誤差實現對異常樣品的檢測，優化其影像重建的檢測框架，以利實際場景之應用。 | zh_TW |
| dc.description.abstract | Blood glucose enzyme test strips are an integral component of diabetes management. However, errors may occur during the printing process of screen printing, such as the overflow or damage of the conductive carbon ink on blood glucose enzyme test strips. These errors could lead to inaccuracies in measurement results, thus affecting patient health management. Currently, the process involves manual inspection of blood glucose enzyme test strips on the production line, incurring significant costs. This study aims to develop a method for detecting carbon ink defects on blood glucose enzyme test strips that can be applied in industrial settings.
Due to the difficulty in obtaining abnormal samples in industrial processes, traditional supervised detection methods are not applicable. Our proposed method, HeInspect, is based on the unsupervised anomaly detection framework introduced in DDAD (Anomaly Detection with Conditioned Denoising Diffusion Models) by Mousakhan, Arian and Brox, Thomas and Tayyub, Jawad [8]. Considering its high computational cost, this paper utilizes techniques such as autoencoders for feature extraction and reconstruction of images. Detection of abnormal samples is achieved by comparing the error between reconstructed and original images, thereby optimizing the detection framework for image reconstruction and facilitating its application in practical scenarios. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2024-07-12T16:09:27Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2024-07-12T16:09:27Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 口試委員審定書 i
誌謝 ii 中文摘要 iii ABSTRACT iv CONTENTS vi LIST OF FIGURES ix LIST OF TABLES xii Chapter 1 Introduction 1 1.1 Overview 1 1.2 Blood Glucose Enzyme Test Strip 2 1.3 Inspection Environment 6 1.4 Industrial Anomaly Detection 7 1.5 Thesis Organization 8 Chapter 2 Related Works 10 2.1 Supervised Anomaly Detection 10 2.2 Unsupervised Anomaly Detection 12 2.2.1 Feature Embedding-Based Method 13 2.2.2 Reconstruction-Based Method 15 Chapter 3 Background 20 3.1 Denoising Diffusion Model 20 3.2 Feature Extraction 22 3.3 Domain Adaptation 23 3.4 DDAD [8] 24 Chapter 4 Methodology 26 4.1 Overview 26 4.2 AutoencoderKL (Kullback–Leibler) 27 4.3 Conditioned Denoising U-Net 30 4.4 Feature Extraction 32 4.4.1 Backbone 33 4.4.2 Domain Adaptation 34 4.4.3 LoRA 36 Chapter 5 Experimental Results 38 5.1 Datasets 38 5.1.1 6PG-CID01 Dataset 39 5.1.2 M2A4 Dataset 41 5.2 Evaluation Metric 42 5.2.1 ROC Curve 43 5.2.2 Image AUC and Pixel AUC 44 5.2.3 PRO 45 5.3 Experimental Results 46 5.3.1 Comparison 46 5.3.2 Test Image Result 48 Chapter 6 Conclusion and Future Works 56 References 57 | - |
| dc.language.iso | en | - |
| dc.title | 何檢測：血糖酵素試片瑕疵檢測 | zh_TW |
| dc.title | HeInspect: Blood Glucose Enzyme Test Strip Defect Inspection | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 112-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 方瓊瑤;劉木議 | zh_TW |
| dc.contributor.oralexamcommittee | Chiung-Yao Fang;Mu-Yi Liu | en |
| dc.subject.keyword | 何檢測,血糖酵素試片,異常檢測,影像重建,自編碼器,去噪擴散模型, | zh_TW |
| dc.subject.keyword | HeInspect,Blood Glucose Enzyme Test Strip,Image Reconstruction,Autoencoder,Denoising Diffusion Model, | en |
| dc.relation.page | 59 | - |
| dc.identifier.doi | 10.6342/NTU202401475 | - |
| dc.rights.note | 未授權 | - |
| dc.date.accepted | 2024-07-06 | - |
| 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-112-2.pdf 目前未授權公開取用 | 2.66 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。