微影製程是半導體產業不斷前進的重要技術，透過將微縮線路用光學投影在晶圓上，將特徵尺寸不斷縮小，而數位微影製程捨棄了對光罩的使用，能透過如數位微反射鏡(Digital Micromirror Device, DMD)等光學元件，將線路直接投射至晶圓上，因此可有效的減少成本，且更能因應少量多樣的製程要求。在本篇論文中針對數位微影製程進行探討，針對於台科大實驗室自行搭建的數位微影(Digital Lithography)曝光機台，開發一套數位微影的模型，透過光學模擬實際曝光的條件，節省大量重複曝光的時間，並且開發了基於反向微影技術的機器學習模型，和一套基於蒙地卡羅的傳統演算法，為第一個可針對每個微反射鏡獨立規劃曝光時間的方法，以14-16μm大小的光點，曝光最小特徵尺寸為4μm的光阻圖案時的誤差改善率能高於95%以上。為了驗證以上數位微影模型的可靠性，和演算法的優化能力，開發了基於SIFT的自動化圖案對準方法，並透過濾波和邊緣檢測等方法，能定義量測圖案的真實光阻圖案位置與邊緣，並將其與目標圖案進行比較，驗證經由演算法和機器學習模型優化後的PCB圖案和扇出封裝分別具有55.8%和70.7%的誤差改善率，且在關鍵尺寸誤差的量測上，直線的誤差為4.8%、斜線的誤差為8.6%、圓孔為6.2%，將關鍵尺寸的誤差控制於10%之內，且與目標圖案的整體匹配度高於90%。

The lithography process is an important technology in the continuous advancement of the semiconductor industry. By optically projecting miniature circuits on the wafer, the feature size is continuously reduced, and the digital lithography process abandons the use of photomasks and can transmit through Digital Micromirror Device( DMD ) and other optical components project the circuit directly on the wafer, so it can effectively reduce the cost, and can better meet the requirements of a small amount of various processes. In this paper, the digital lithography process is discussed, and a set of digital lithography models are developed for the digital lithography exposure machine built by the National Taiwan University of Science and Technology Laboratory, and the actual exposure conditions are simulated through optics. Save a lot of time for repeated exposure, and developed a machine learning model based on reverse lithography technology, and a set of traditional Monte Carlo-based algorithms, which is the first one that can independently plan exposure time for each micromirror. With the method, the error improvement rate can be higher than 95%, when exposing a photoresist pattern with a minimum feature size of 4 μm with a beam size of 14-16 μm. In order to verify the reliability of the above digital lithography model and the optimization ability of the algorithm, an automatic pattern alignment method based on SIFT was developed, it can define the real photoresist pattern position and edge of the measurement and compare it to the target pattern that the PCB pattern and fan-out package optimized by the algorithm and machine learning model have an error improvement rate of 55.8% and 70.7%. And in the measurement of the critical dimension error, the error of the straight line is 4.8%, the error of the oblique line is 8.6%, and the error of the round hole is 6.2%, the error of the critical dimension is controlled within 10%, and the overall matching degree with the target pattern above 90%.

Z. Zhang, S. Li, X. Wang, and W. Cheng, "Fast heuristic-based source mask optimization for EUV lithography using dual edge evolution and partial sampling," Optics Express, vol. 29, no. 14, pp. 22778-22795, 2021/07/05 2021, doi: 10.1364/OE.432010.
[2] J. Liu, J. Liu, Q. Deng, J. Feng, S. Zhou, and S. Hu, "Intensity modulation based optical proximity optimization for the maskless lithography," Optics Express, vol. 28, no. 1, pp. 548-557, 2020/01/06 2020, doi: 10.1364/OE.381503.
[3] Carmelo Rosales-Guzmán, Xiao-Bo Hu, Adam Selyem, Pedro Moreno-Acosta., "Polarisation-insensitive generation of complex vector modes from a digital micromirror device," Scientific Reports, vol. 10, no. 1, p. 10434, 2020/06/26 2020, doi: 10.1038/s41598-020-66799-9.
[4] Jiamiao Yang, Qiaozhi He, Linxian Liu, Yuan Qu., "Anti-scattering light focusing by fast wavefront shaping based on multi-pixel encoded digital-micromirror device," Light: Science & Applications, vol. 10, no. 1, p. 149, 2021/07/20 2021, doi: 10.1038/s41377-021-00591-w.
[5] H.-L. Chien, Y.-H. Chiu, and Y.-C. Lee, "Maskless lithography based on oblique scanning of point array with digital distortion correction," Optics and Lasers in Engineering, vol. 136, p. 106313, 2021/01/01/ 2021
[6] G. Chen, S. Li, and X. Wang, "Efficient optical proximity correction based on virtual edge and mask pixelation with two-phase sampling," Optics Express, vol. 29, no. 11, pp. 17440-17463, 2021/05/24 2021, doi: 10.1364/OE.415913.
[7] Shengen Zhang, Xu Ma, Junbi Zhang., "Fast optical proximity correction based on graph convolution network," in Proc.SPIE, 2021, vol. 11613, p. 116130V, doi: 10.1117/12.2583773. [Online].
[8] Z. M. Elgamal, N. B. M. Yasin, M. Tubishat, M. Alswaitti, and S. Mirjalili, "An Improved Harris Hawks Optimization Algorithm With Simulated Annealing for Feature Selection in the Medical Field," IEEE Access, vol. 8, pp. 186638-186652, 2020, doi: 10.1109/ACCESS.2020.3029728.
[9] R. Biswas and S. K. Bandyapadhay, "Random selection based GA optimization in 2D-DCT domain color image steganography," Multimedia Tools and Applications, vol. 79, no. 11, pp. 7101-7120, 2020/03/01 2020, doi: 10.1007/s11042-019-08497-x.
[10] G. Cocchi and M. Lapucci, "An augmented Lagrangian algorithm for multi-objective optimization," Computational Optimization and Applications, vol. 77, no. 1, pp. 29-56, 2020/09/01 2020, doi: 10.1007/s10589-020-00204-z.
[11] R. Wu, L. Dong, X. Ma, and Y. Wei, "Compensation of EUV lithography mask blank defect based on an advanced genetic algorithm," Optics Express, vol. 29, no. 18, pp. 28872-28885, 2021/08/30 2021, doi: 10.1364/OE.434787.
[12] S. Zavrak and M. İskefiyeli, "Anomaly-Based Intrusion Detection From Network Flow Features Using Variational Autoencoder," IEEE Access, vol. 8, pp. 108346-108358, 2020, doi: 10.1109/ACCESS.2020.3001350.
[13] A. Dhillon and G. K. Verma, "Convolutional neural network: a review of models, methodologies and applications to object detection," Progress in Artificial Intelligence, vol. 9, no. 2, pp. 85-112, 2020/06/01 2020, doi: 10.1007/s13748-019-00203-0.
[14] J. Gui, Z. Sun, Y. Wen, D. Tao, and J. Ye, "A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications," IEEE Transactions on Knowledge and Data Engineering, pp. 1-1, 2021, doi: 10.1109/TKDE.2021.3130191.
[15] V. K. Prajapati, M. Jain, and L. Chouhan, "Tabu Search Algorithm (TSA): A Comprehensive Survey," in 2020 3rd International Conference on Emerging Technologies in Computer Engineering: Machine Learning and Internet of Things (ICETCE), 7-8 Feb. 2020 2020, pp. 1-8, doi: 10.1109/ICETCE48199.2020.9091743.
[16] H. Yang, S. Li, Z. Deng, Y. Ma, B. Yu, and E. F. Young, "GAN-OPC: Mask optimization with lithography-guided generative adversarial nets," IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 39, no. 10, pp. 2822-2834, 2019.
[17] M. B. Alawieh, Y. Lin, Z. Zhang, M. Li, Q. Huang, and D. Z. Pan, "GAN-SRAF: Sub-resolution assist feature generation using conditional generative adversarial networks," in Proceedings of the 56th Annual Design Automation Conference 2019, 2019, pp. 1-6.
[18] W. Ye, M. B. Alawieh, Y. Lin, and D. Z. Pan, "LithoGAN: End-to-end lithography modeling with generative adversarial networks," in 2019 56th ACM/IEEE Design Automation Conference (DAC), 2019: IEEE, pp. 1-6.
[19] X.-Y. Yu, L. Yu, L. Shen, X. Song, H. Chen, and X. W. Lou, "General Formation of MS (M = Ni, Cu, Mn) Box-in-Box Hollow Structures with Enhanced Pseudocapacitive Properties," Advanced Functional Materials, vol. 24, no. 47, pp. 7440-7446, 2014/12/01 2014
[20] M.-J. Wang and C.-L. Huang, "Evaluating the eye fatigue problem in wafer inspection," IEEE Transactions on Semiconductor Manufacturing, vol. 17, no. 3, pp. 444-447, 2004.
[21] A. K. Wong, R. A. Ferguson, L. W. Liebmann, S. M. Mansfield, A. F. Molless, and M. O. Neisser, "Lithographic effects of mask critical dimension error," in Optical Microlithography XI, 1998, vol. 3334: SPIE, pp. 106-116.
[22] D. S. Abrams and L. Pang, "Fast inverse lithography technology," in Optical Microlithography XIX, 2006, vol. 6154: SPIE, pp. 534-542.
[23] Y. Granik, "Fast pixel-based mask optimization for inverse lithography," Journal of Micro/Nanolithography, MEMS, and MOEMS, vol. 5, no. 4, p. 043002, 2006.
[24] X. Li, H. Chen, X. Qi, Q. Dou, C.-W. Fu, and P.-A. Heng, "H-DenseUNet: hybrid densely connected UNet for liver and tumor segmentation from CT volumes," IEEE transactions on medical imaging, vol. 37, no. 12, pp. 2663-2674, 2018.
[25] Huimin Huang; Lanfen Lin; Ruofeng Tong;, "Unet 3+: A full-scale connected unet for medical image segmentation," in ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020: IEEE, pp. 1055-1059.
[26] S. Albawi, T. A. Mohammed, and S. Al-Zawi, "Understanding of a convolutional neural network," in 2017 international conference on engineering and technology (ICET), 2017: Ieee, pp. 1-6.
[27] N. Bjorck, C. P. Gomes, B. Selman, and K. Q. Weinberger, "Understanding batch normalization," Advances in neural information processing systems, vol. 31, 2018.
[28] B. Xu, N. Wang, T. Chen, and M. Li, "Empirical evaluation of rectified activations in convolutional network," arXiv preprint arXiv:1505.00853, 2015.
[29] Chengxi Ye, Matthew Evanusa, Hua He, Anton Mitrokhin, Tom Goldstein, James A. Yorke, Cornelia Fermüller, Yiannis Aloimonos., "Network deconvolution," arXiv preprint arXiv:1905.11926, 2019.
[30] Y. Li, X. Zhang, and D. Chen, "Csrnet: Dilated convolutional neural networks for understanding the highly congested scenes," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 1091-1100.
[31] A. F. Agarap, "Deep learning using rectified linear units (relu)," arXiv preprint arXiv:1803.08375, 2018.
[32] D. A. Van Dyk and X.-L. Meng, "The art of data augmentation," Journal of Computational and Graphical Statistics, vol. 10, no. 1, pp. 1-50, 2001.
[33] M. Hénon, "The Monte Carlo method," in International Astronomical Union Colloquium, 1971, vol. 10: Cambridge University Press, pp. 151-167.
[34] R. Y. Rubinstein and D. P. Kroese, Simulation and the Monte Carlo method. John Wiley & Sons, 2016.
[35] Y. A. Shreider, The Monte Carlo method: the method of statistical trials. Elsevier, 2014.
[36] M. Rosenblatt, "A CENTRAL LIMIT THEOREM AND A STRONG MIXING CONDITION," Proceedings of the National Academy of Sciences, vol. 42, no. 1, pp. 43-47, 1956/01/01 1956, doi: 10.1073/pnas.42.1.43.
[37] C. J. Geyer, "Practical markov chain monte carlo," Statistical science, pp. 473-483, 1992.
[38] S. Belan, "Restart Could Optimize the Probability of Success in a Bernoulli Trial," Physical Review Letters, vol. 120, no. 8, p. 080601, 02/21/ 2018, doi: 10.1103/PhysRevLett.120.080601.
[39] N. Jiang and L. Wang, "Quantum image scaling using nearest neighbor interpolation," Quantum Information Processing, vol. 14, no. 5, pp. 1559-1571, 2015.
[40] E. Aho, J. Vanne, K. Kuusilinna, and T. Hamalainen, "Comments on" Winscale: an image-scaling algorithm using an area pixel Model"," IEEE Transactions on circuits and systems for video technology, vol. 15, no. 3, pp. 454-455, 2005.
[41] W.-C. Wu, T.-H. Wang, and C.-T. Chiu, "Edge Curve Scaling and Smoothing with Cubic Spline Interpolation for Image Up-Scaling," Journal of Signal Processing Systems, vol. 78, no. 1, pp. 95-113, 2015/01/01 2015, doi: 10.1007/s11265-014-0936-6.
[42] N. Shimizu, T. Mizusaki, Y. Utsuno, and Y. Tsunoda, "Thick-restart block Lanczos method for large-scale shell-model calculations," Computer Physics Communications, vol. 244, pp. 372-384, 2019/11/01/ 2019
[43] S. Wong, S. Vassiliadis, and S. Cotofana, "A sum of absolute differences implementation in FPGA hardware," in Proceedings. 28th Euromicro Conference, 6-6 Sept. 2002 2002, pp. 183-188, doi: 10.1109/EURMIC.2002.1046155.
[44] M. Awaludin and V. Yasin, "APPLICATION OF ORIENTED FAST AND ROTATED BRIEF (ORB) AND BRUTEFORCE HAMMING IN LIBRARY OPENCV FOR CLASSIFICATION OF PLANTS," JISAMAR (Journal of Information System, Applied, Management, Accounting and Research); Vol 4 No 3 (2020): JISAMAR : Volume 4, Nomor 3, August 2020, 08/14 2020. [Online]
[45] H. Li, S. Wang, Y. Zhao, J. Wei, and M. Piao, "Large-scale elemental image array generation in integral imaging based on scale invariant feature transform and discrete viewpoint acquisition," Displays, vol. 69, p. 102025, 2021/09/01/ 2021
[46] E. H. Yuk, S. H. Park, C.-S. Park, and J.-G. Baek, "Feature-Learning-Based Printed Circuit Board Inspection via Speeded-Up Robust Features and Random Forest," Applied Sciences, vol. 8, no. 6, 2018, doi: 10.3390/app8060932.
[47] Z. Ye, Y. Pei, and J. Shi, "An Improved Algorithm for Harris Corner Detection," in 2009 2nd International Congress on Image and Signal Processing, 17-19 Oct. 2009 2009, pp. 1-4, doi: 10.1109/CISP.2009.5304635.
[48] F. K. Noble, "Comparison of OpenCV's feature detectors and feature matchers," in 2016 23rd International Conference on Mechatronics and Machine Vision in Practice (M2VIP), 28-30 Nov. 2016 2016, pp. 1-6, doi: 10.1109/M2VIP.2016.7827292.
[49] V. Vijayan and P. Kp, "FLANN Based Matching with SIFT Descriptors for Drowsy Features Extraction," in 2019 Fifth International Conference on Image Information Processing (ICIIP), 15-17 Nov. 2019 2019, pp. 600-605, doi: 10.1109/ICIIP47207.2019.8985924.
[50] W. Rong, Z. Li, W. Zhang, and L. Sun, "An improved Canny edge detection algorithm," in 2014 IEEE International Conference on Mechatronics and Automation, 3-6 Aug. 2014 2014, pp. 577-582, doi: 10.1109/ICMA.2014.6885761.