窗戶是房屋的重要組成部分，窗戶不僅有促進房屋美觀的作用，而且對人體健康也有影響。窗戶可以提供太陽光，這比電燈更為自然，對人眼來說更好。當今都市建物使用大量電氣設備，往往導致能源短缺以及環境污染等問題。為避免此問題持續惡化，房屋採光和通風設計已經是個重要的項目。為確保家庭擁有自然採光的同時，設計滿足房屋安全的窗戶類型是至關重要的任務。
金屬擴張網的菱狀結構，在通透性上提供最佳的優勢，可作為光線漫反射設施並形成有效的透光、透風、透視環境，以確保入射的光線是足夠的。因此，本研究提出一個專用於計算金屬網透光率的照明傳輸系統。在這項研究中，我們設計了一個專業設備用來分析金屬網的透光率。所提出的系統包括兩個步驟，步驟一為圖像採集系統，在暗箱中藉由轉動裝置進行多角度連續取像;步驟二使用自適應高階奇異值分解演算技術，對於金屬網格圖像的小波子帶張量進行圖像增強，以應用於通過金屬網格的亮度分析。
實驗結果證明，以很短的時間即可以得出很精準的金屬網格透光率分析。所提出的系統確實可以有效地用於分析金屬網的透光率量測，以確保產品品質和檢測效率，這在大規模生產中尤其重要。
關鍵詞：圖像增強、金屬網格檢測，透光率，光透射分析，圖像增強。

Windows are an essential component of a house. Windows not only play the role of promoting the appearance of the house but also impact human health. A window can provide sunlight, which is natural and better for human eyes than electrical lighting. Moreover, using a lot of electrical equipment causes several problems such as the energy industries facing a severe lack of energy and the world facing up to the pollution of the environment. In architecture fields, a window beside the design for lighting and ventilation is also a challenge for designing a new kind of window that breaks the old view. Therefore, creating window types to satisfy the house's security while ensuring the natural lighting transmission for the home is a crucial task.
The design of the metal mesh window faces the challenge of designing the curves and holes of the mesh to make sure the lighting transmissible into the house is suitable. So, proposing a lighting transmission analysis system for the metal mesh window plays a vital role in metal mesh production. This research proposes a system that calculates the lighting transmission through the metal mesh window. In this research, I design the system to analyze the lighting transmission through the metal mesh. The proposed system involves two main components. The first component is an image acquisition system which is constructed by applying lighting source design, building a mechanical system for holding and moving samples, and setting up the testing environment. The second part involves image enhancement using Adaptive High-order Singular Value Decomposition on Tensor of Wavelet Subbands for the metal mesh image and an analysis system to determine the lighting transmission through the metal mesh.
The experimental results reveal that the lighting transmission analysis task for the metal mesh window can be obtained with high accuracy and less time consumption. Therefore, the proposed system can be effectively used for analyzing lighting transmission in the metal mesh production to ensure the product quality and saving time consumption which is very important in mass production.
Keywords: Metal mesh inspection, auto optical inspection, lighting transmission analysis, tensor, image enhancement.

TABLE OF CONTENTS
LIST OF FIGURES ...............................................................xii
LIST OF TABLES ...............................................................xiv
CHAPTER 1 INTRODUCTION .......................................................1
CHAPTER 2 THE IMAGE ACQUISITION SYSTEM .......................................5
2.1 Previous Image Acquisition System .......................................5
2.1.1 Image Acquisition System 1 .......................................5
2.1.2 Image Acquisition System 2 .......................................7
2.3 Result of Image Capturing ...............................................13
2.4 Conclusion for Image Acquisition System ...............................21
CHAPTER 3 IMAGE PREPROCESSING FOR LIGHTING TRANSMISSION ANALYSIS .............22
3.1.1 Median Filter .......................................................23
3.1.2 Gaussian Filter .......................................................24
3.1.3 Bilateral Filter .......................................................24
3.2. Adaptive Higher-Order Singular Value Decomposition Applied on Tensor of Wavelet Subbands for Denoising. ...............................................25
3.3 Binary Image .......................................................33
3.4 Conclusion for Enhancing Metal Mesh Image ...............................34
CHAPTER 4 LIGHTING TRANSMISSION ANALYSIS ...............................35
4.1 Contour Detection for Lighting Transmission Analysis ...............35
4.2 Metal Mesh Window Lighting Transmission Analysis .......................37
4.3 Conclusion for Lighting Transmission Analysis .......................38
CHAPTER 5 EXPERIMENTAL RESULT AND DISCUSSION ...............................39
5.1 Experiment ...............................................................39
5.2 Discussion ...............................................................52
CONCLUSION ...................................................................53
REFERENCES ...................................................................55
BIOGRAPHY ...................................................................57

[1] N. T. Le, J. -W. Wang, M. -H. Shih and C. -C. Wang, “Novel Framework for Optical Film Defect Detection and Classification,” in IEEE Access, vol. 8, pp. 60964-60978, 2020.
[2] N. T. Le, J. -W. Wang, C. -C. Wang and T.N. Nguyen. “Novel Framework Based on HOSVD for Ski Goggles Defect Detection and Classification”. Sensors 2019, 19, 5538.
[3] N. T. Le, J. -W. Wang, C. -C. Wang and T.N. Nguyen. “Automatic Defect Inspection for Coated Eyeglass Based on Symmetrized Energy Analysis of Color Channels”. Symmetry 2019, vol. 11, no.12.
[4] X. Zhou, Y. Wang, Q. Zhu, J. Mao and C. Xiao, “A Surface Defect Detection Framework for Glass Bottle Bottom Using Visual Attention Model and Wavelet Transform,” in IEEE Transactions on Industrial Informatics, vol. 16, no. 4, pp. 2189-2201, Apr. 2020.
[5] Q. Luo et al., “Automated Visual Defect Classification for Flat Steel Surface: A Survey,” in IEEE Transactions on Instrumentation and Measurement, vol. 69, no. 12, pp. 9329-9349, Dec. 2020.
[6] S. Mei, Q. Cai, Z. Gao, H. Hu, and G. Wen, “Deep Learning Based Automated Inspection of Weak Micro scratches in Optical Fiber Connector End-Face,” in IEEE Transactions on Instrumentation and Measurement, vol. 70, pp. 1-10, 2021.
[7] W. Fan, K. Wang, F. Cayre and Z. Xiong, “Median Filtered Image Quality Enhancement and Anti-Forensics via Variational Deconvolution,” in IEEE Transactions on Information Forensics and Security, vol. 10, no. 5, pp. 1076-1091, May 2015.
[8] S. A. Villar, S. Torcida and G. G. Acosta. “Median Filtering: A New Insight”. Journal of Mathematical Imaging and Vision, 2017.
[9] Johannes P.F. D' Haeyer, “Gaussian filtering of images: A regularization approach”, Signal Processing, vol.18, Issue 2,1989.
[10] K. N. Chaudhury and S. D. Dabhade, “Fast and Provably Accurate Bilateral Filtering,” in IEEE Transactions on Image Processing, vol. 25, no. 6, pp. 2519-2528, June 2016.
[11] N. T. Le, J. -W. Wang, D. H. Le, C. -C. Wang and T. N. Nguyen, “Fingerprint Enhancement Based on Tensor of Wavelet Subbands for Classification,” in IEEE Access, vol. 8, pp. 6602-6615, 2020.
[12] N. Otsu, “A threshold selection method from gray-level histograms”, IEEE Trans. Syst. Man Cybern., vol. 9, no. 1, pp. 62-66, Jan. 1979.
[13] Y. S. Ming, H. D. Li, X. M. He. “Contour completion without region segmentation”. IEEE Transactions on Image Processing, vol.25, no.9, pp.3597–3611, 2016.
[14] Daipeng Yang, Bo Peng, Zaid Al-Huda, Asad Malik, Donghai Zhai. “An overview of edge and object contour detection”. Neurocomputing, vol. 488, 2022.
[15] Satoshi Suzuki, Keiichi Abe, “Topological structural analysis of digitized binary images by border following”, Computer Vision, Graphics, and Image Processing, vol. 30, Issue 1,1985.