近年來，光學量測需求激增推動了半導體及傳統製造業對三維掃描技術的探索。傳統接觸式方法雖然精確，但成本高、效率低，易損壞物體。相比之下，非接觸式技術成本低、效率高，能準確測量複雜形狀，無需直接接觸物體。在半導體、汽車、醫療和航空等領域廣泛應用，提升了測量和檢測效率。儘管結構光掃描可解決雙目立體視覺的問題，但掃描金屬物時，高反光率會導致相機像素過飽和，使結構光條紋模糊或丟失，難以解碼三維資訊。近年來，人工智慧期刊論文數量激增，顯示了人工智慧的發展。為應對此挑戰，本研究將導入機器學習技術，解決高反光金屬表面的過曝問題。
本研究提出一套系統，透過偽曝光圖像生成系統中，計算參考圖像間的Gamma矩陣，生成多組偽曝光圖像以減少拍攝圖像的時間。接著利用Retinex深度學習網路將低曝光圖像進行強度增強，顯露出較暗區域的細節，增加結構光投影在較暗圖像中的完整度。最後針對圖像中各像素進行權重計算，保留最佳像素進行圖像熔接。藉由此流程期望能夠增加系統精準度並使其可應用於較為複雜的金屬表面。

Recent demand for optical measurement drives semiconductor and manufacturing towards 3D scanning. While contact methods offer precision, they're costly and risky. Non-contact techniques provide cost-effective solutions, revolutionizing industries. Despite structured light's benefits, scanning metal faces challenges with oversaturation. Our study integrates machine learning to address overexposure on reflective surfaces, aiming to enhance efficiency.
Our study proposes a comprehensive system that leverages a pseudo-exposure image generation system. This system calculates the Gamma matrix between reference images to produce multiple sets of pseudo-exposure images, thereby streamlining the image capture process. Subsequently, applying advanced Retinex deep learning networks, low-exposure images undergo meticulous intensity enhancement to unveil intricate details in darker regions, thereby augmenting the completeness of structured light projections within these areas. Finally, through pixel-wise weight calculations, optimal pixels are selected for image fusion, ensuring the preservation of critical details. Through this meticulously crafted process, we aim to not only enhance system accuracy but also extend its applicability to much more complex metallic surfaces than flat surface.

[1] Nestor Maslej, Loredana Fattorini, Erik Brynjolfsson, John Etchemendy, Katrina Ligett, Terah Lyons,James Manyika, Helen Ngo, Juan Carlos Niebles, Vanessa Parli, Yoav Shoham, Russell Wald, Jack Clark, and Raymond Perrault, “The AI Index 2023 Annual Report,” AI Index Steering Committee, Institute for Human-Centered AI, Stanford University, Stanford, CA, (2023).
[2] C.-S. Liu, J.-J. Lin, and B.-R. Chen, “A Novel 3d Scanning Technique for Reflective Metal Surface Based on Hdr-Like Image from Pseudo Exposure Image Fusion Method,” Optics and Lasers in Engineering, vol. 168, p. 107688, 2023.
[3] C. Wei, W. Wang, W. Yang et al., “Deep Retinex Decomposition for Low-Light Enhancement,” arXiv preprint arXiv:1808.04560, 2018.
[4] L. Robert, S. Peter, B. Alice et al., “Time-of-Flight Range Imaging with a Custom Solid State Image Sensor,” in Proc.SPIE, vol. 3823, pp. 180-191, 1999.
[5] I. Moring, T. Heikkinen, R. Myllyla et al., “Acquisition of Three-Dimensional Image Data by a Scanning Laser Range Finder,” Optical engineering, vol. 28, no. 8, pp. 897-902, 1989.
[6] S. Hussmann, T. Ringbeck, and B. Hagebeuker, “A Performance Review of 3d Tof Vision Systems in Comparison to Stereo Vision Systems,” Stereo vision, vol. 372, 2008.
[7] J.-H. Wu, R.-S. Chang, and J.-A. Jiang, “A Novel Pulse Measurement System by Using Laser Triangulation and a Cmos Image Sensor,” Sensors, vol. 7, no. 12, pp. 3366-3385, 2007.
[8] M. A. Isa and I. Lazoglu, “Design and Analysis of a 3d Laser Scanner,” Measurement, vol. 111, pp. 122-133, 2017.
[9] M. Stafne, L. D. Mitchell, and R. L. West, “Positional Calibration of Galvanometric Scanners Used in Laser Doppler Vibrometers,” Measurement, vol. 28, no. 1, pp. 47-59, 2000.
[10] Q. Yao and M. Cao, “Design of Optical Emission System in 3d Shape Detection with Oblique Laser Triangulation Probe,” in Journal of Physics: Conference Series, vol. 1774, no. 1, p. 012063, 2021.
[11] P. Axelsson, “Processing of Laser Scanner Data—Algorithms and Applications,” ISPRS Journal of photogrammetry and remote sensing, vol. 54, no. 2-3, pp. 138-147, 1999.
[12] M. Elmqvist, E. Jungert, F. Lantz et al., “Terrain Modelling and Analysis Using Laser Scanner Data,” International Archives of Photogrammetry Remote Sensing and Spatial Information Sciences, vol. 34, no. 3/W4, pp. 219-226, 2001.
[13] A. Wehr and U. Lohr, “Airborne Laser Scanning—an Introduction and Overview,” ISPRS Journal of photogrammetry and remote sensing, vol. 54, no. 2-3, pp. 68-82, 1999.
[14] Taryudi and M.-S. Wang, “Eye to Hand Calibration Using Anfis for Stereo Vision-Based Object Manipulation System,” Microsystem Technologies, vol. 24, pp. 305-317, 2018.
[15] R. Blake and H. Wilson, “Binocular Vision,” Vision research, vol. 51, no. 7, pp. 754-770, 2011.
[16] S. Zhang, “High-Speed 3d Shape Measurement with Structured Light Methods: A Review,” Optics and Lasers in Engineering, vol. 106, pp. 119-131, 2018.
[17] X. Sun, Y. Jiang, Y. Ji et al., “Distance Measurement System Based on Binocular Stereo Vision,” in IOP Conference Series: Earth and Environmental Science, vol. 252, no. 5, p. 052051, 2019.
[18] Z. Zhang, “Determining the Epipolar Geometry and Its Uncertainty: A Review,” International journal of computer vision, vol. 27, pp. 161-195, 1998.
[19] T. Bell, B. Li, and S. Zhang, “Structured Light Techniques and Applications,” Wiley Encyclopedia of Electrical and Electronics Engineering, pp. 1-24, 1999.
[20] J. Salvi, J. Pages, and J. Batlle, “Pattern Codification Strategies in Structured Light Systems,” Pattern recognition, vol. 37, no. 4, pp. 827-849, 2004.
[21] J. Pages and J. Salvi, “Coded Light Projection Techniques for 3d Reconstruction,” J3eA, vol. 4, p. 001, 2005.
[22] M. Gupta and N. Nakhate, “A Geometric Perspective on Structured Light Coding,” in Proceedings of the European Conference on Computer Vision (ECCV), pp. 87-102, 2018.
[23] J. Tajima and M. Iwakawa, “3-D Data Acquisition by Rainbow Range Finder,” in [1990] Proceedings. 10th International Conference on Pattern Recognition, vol. 1, pp. 309-313, 1990.
[24] J. Pages, J. Salvi, and J. Forest, “A New Optimised De Bruijn Coding Strategy for Structured Light Patterns,” in Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004., vol. 4, pp. 284-287, 2004.
[25] E. R. Hauge and T. Helleseth, “De Bruijn Sequences, Irreducible Codes and Cyclotomy,” Discrete Mathematics, vol. 159, no. 1-3, pp. 143-154, 1996.
[26] P. Payeur and D. Desjardins, “Structured Light Stereoscopic Imaging with Dynamic Pseudo-Random Patterns,” in Image Analysis and Recognition: 6th International Conference, ICIAR 2009, Halifax, Canada, July 6-8, 2009. Proceedings 6, pp. 687-696, 2009.
[27] L. Zhang, B. Curless, and S. M. Seitz, “Rapid Shape Acquisition Using Color Structured Light and Multi-Pass Dynamic Programming,” in Proceedings. First International Symposium on 3D Data Processing Visualization and Transmission, pp. 24-36, 2002.
[28] F.-H. Cheng, C.-T. Lu, and Y.-S. Huang, “3d Object Scanning System by Coded Structured Light,” in 2010 Third International Symposium on Electronic Commerce and Security, pp. 213-217, 2010.
[29] J. L. Posdamer and M. D. Altschuler, “Surface Measurement by Space-Encoded Projected Beam Systems,” Computer graphics and image processing, vol. 18, no. 1, pp. 1-17, 1982.
[30] Y. Zhang and A. Yilmaz, “Structured Light Based 3d Scanning for Specular Surface by the Combination of Gray Code and Phase Shifting,” The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. 41, pp. 137-142, 2016.
[31] J. Lu, R. Mo, H. Sun et al., “Invalid Phase Values Removal Method for Absolute Phase Recovery,” Applied Optics, vol. 55, no. 2, pp. 387-394, 2016.
[32] L. Huang and A. K. Asundi, “Phase Invalidity Identification Framework with the Temporal Phase Unwrapping Method,” Measurement Science and Technology, vol. 22, no. 3, p. 035304, 2011.
[33] H. Wang, Q. Kemao, and S. H. Soon, “Valid Point Detection in Fringe Projection Profilometry,” Optics Express, vol. 23, no. 6, pp. 7535-7549, 2015.
[34] J. Gühring, “Dense 3d Surface Acquisition by Structured Light Using Off-the-Shelf Components,” in Videometrics and Optical Methods for 3D Shape Measurement, vol. 4309, pp. 220-231, 2000.
[35] Z. Song, H. Jiang, H. Lin et al., “A High Dynamic Range Structured Light Means for the 3d Measurement of Specular Surface,” Optics and Lasers in Engineering, vol. 95, pp. 8-16, 2017.
[36] D. Palousek, M. Omasta, D. Koutny et al., “Effect of Matte Coating on 3d Optical Measurement Accuracy,” Optical Materials, vol. 40, pp. 1-9, 2015.
[37] S. Nayar, K. Ikeuchi, and T. Kanade, “Surface Reflection: Physical and Geometrical Perspectives,” in Proceedings: Image Understanding Workshop, pp. 185-212, 1990.
[38] S. Feng, Y. Zhang, Q. Chen et al., “General Solution for High Dynamic Range Three-Dimensional Shape Measurement Using the Fringe Projection Technique,” Optics and Lasers in Engineering, vol. 59, pp. 56-71, 2014.
[39] T. Chen, H. P. Lensch, C. Fuchs et al., “Polarization and Phase-Shifting for 3d Scanning of Translucent Objects,” in 2007 IEEE conference on computer vision and pattern recognition, pp. 1-8, 2007.
[40] N. T. Shaked, B. Katz, and J. Rosen, “Review of Three-Dimensional Holographic Imaging by Multiple-Viewpoint-Projection Based Methods,” Applied Optics, vol. 48, no. 34, pp. H120-H136, 2009.
[41] S. Feng, Q. Chen, C. Zuo et al., “Fast Three-Dimensional Measurements for Dynamic Scenes with Shiny Surfaces,” Optics Communications, vol. 382, pp. 18-27, 2017.
[42] G.-h. Liu, X.-Y. Liu, and Q.-Y. Feng, “3d Shape Measurement of Objects with High Dynamic Range of Surface Reflectivity,” Applied Optics, vol. 50, no. 23, pp. 4557-4565, 2011.
[43] Z. Cai, X. Liu, X. Peng et al., “Structured Light Field 3d Imaging,” Optics Express, vol. 24, no. 18, pp. 20324-20334, 2016.
[44] S. Nayar, K. Ikeuchi, and T. Kanade, “Surface Reflection: Physical and Geometrical Perspectives,” in Proceedings: Image Understanding Workshop, pp. 185-212, 1990.
[45] S. Zhang and S.-T. Yau, “High Dynamic Range Scanning Technique,” Optical engineering, vol. 48, no. 3, pp. 033604-033604-7, 2009.
[46] K. Zhong, Z. Li, X. Zhou et al., “Enhanced Phase Measurement Profilometry for Industrial 3d Inspection Automation,” The International Journal of Advanced Manufacturing Technology, vol. 76, pp. 1563-1574, 2015.
[47] D. Li and J. Kofman, “Adaptive Fringe-Pattern Projection for Image Saturation Avoidance in 3d Surface-Shape Measurement,” Optics Express, vol. 22, no. 8, pp. 9887-9901, 2014.
[48] H. Lin, J. Gao, Q. Mei et al., “Adaptive Digital Fringe Projection Technique for High Dynamic Range Three-Dimensional Shape Measurement,” Optics Express, vol. 24, no. 7, pp. 7703-7718, 2016.
[49] H. Lin, J. Gao, Q. Mei et al., “Three-Dimensional Shape Measurement Technique for Shiny Surfaces by Adaptive Pixel-Wise Projection Intensity Adjustment,” Optics and Lasers in Engineering, vol. 91, pp. 206-215, 2017.
[50] Y. Liu, Y. Fu, X. Cai et al., “A Novel High Dynamic Range 3d Measurement Method Based on Adaptive Fringe Projection Technique,” Optics and Lasers in Engineering, vol. 128, p. 106004, 2020.
[51] J. Sun and Q. Zhang, “A 3d Shape Measurement Method for High-Reflective Surface Based on Accurate Adaptive Fringe Projection,” Optics and Lasers in Engineering, vol. 153, p. 106994, 2022.
[52 ] L. Zhang, Q. Chen, C. Zuo et al., “High Dynamic Range 3d Shape Measurement Based on the Intensity Response Function of a Camera,” Applied Optics, vol. 57, no. 6, pp. 1378-1386, 2018.
[53] S. Feng, Q. Chen, G. Gu et al., “Fringe Pattern Analysis Using Deep Learning,” Advanced photonics, vol. 1, no. 2, pp. 025001-025001, 2019.
[54] D. Eigen, C. Puhrsch, and R. Fergus, “Depth Map Prediction from a Single Image Using a Multi-Scale Deep Network,” Advances in neural information processing systems, vol. 27, 2014.
[55] F. Liu, C. Shen, and G. Lin, “Deep Convolutional Neural Fields for Depth Estimation from a Single Image,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 5162-5170, 2015.
[56] C. B. Choy, D. Xu, J. Gwak et al., “3d-R2n2: A Unified Approach for Single and Multi-View 3d Object Reconstruction,” in Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part VIII 14, pp. 628-644, 2016.
[57] P. Dou, S. K. Shah, and I. A. Kakadiaris, “End-to-End 3d Face Reconstruction with Deep Neural Networks,” in proceedings of the IEEE conference on computer vision and pattern recognition, pp. 5908-5917, 2017.
[58] W. Yin, Q. Chen, S. Feng et al., “Temporal Phase Unwrapping Using Deep Learning,” Scientific reports, vol. 9, no. 1, p. 20175, 2019.
[59] S. Van der Jeught and J. J. Dirckx, “Deep Neural Networks for Single Shot Structured Light Profilometry,” Optics Express, vol. 27, no. 12, pp. 17091-17101, 2019.
[60] C. Guo, C. Li, J. Guo et al., “Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 1780-1789, 2020.
[61] Z. Ren, H. K.-H. So, and E. Y. Lam, “Fringe Pattern Improvement and Super-Resolution Using Deep Learning in Digital Holography,” IEEE Transactions on industrial informatics, vol. 15, no. 11, pp. 6179-6186, 2019.
[62] B. Lin, S. Fu, C. Zhang et al., “Optical Fringe Patterns Filtering Based on Multi-Stage Convolution Neural Network,” Optics and Lasers in Engineering, vol. 126, p. 105853, 2020.
[63] F. Hao, C. Tang, M. Xu et al., “Batch Denoising of Espi Fringe Patterns Based on Convolutional Neural Network,” Applied Optics, vol. 58, no. 13, pp. 3338-3346, 2019.
[64] A. Reyes-Figueroa, V. H. Flores, and M. Rivera, “Deep Neural Network for Fringe Pattern Filtering and Normalization,” Applied Optics, vol. 60, no. 7, pp. 2022-2036, 2021.
[65] P. Stavroulakis, S. Chen, C. Delorme et al., “Rapid Tracking of Extrinsic Projector Parameters in Fringe Projection Using Machine Learning,” Optics and Lasers in Engineering, vol. 114, pp. 7-14, 2019.
[66] K. Yan, Y. Yu, C. Huang et al., “Fringe Pattern Denoising Based on Deep Learning,” Optics Communications, vol. 437, pp. 148-152, 2019.
[67] J. Shi, X. Zhu, H. Wang et al., “Label Enhanced and Patch Based Deep Learning for Phase Retrieval from Single Frame Fringe Pattern in Fringe Projection 3d Measurement,” Optics Express, vol. 27, no. 20, pp. 28929-28943, 2019.
[68] H. Yu, X. Chen, Z. Zhang et al., “Dynamic 3-D Measurement Based on Fringe-to-Fringe Transformation Using Deep Learning,” Optics Express, vol. 28, no. 7, pp. 9405-9418, 2020.
[69] C. B. Duane, “Close-Range Camera Calibration,” Photogramm. Eng, vol. 37, no. 8, pp. 855-866, 1971.
[70] J. Weng, P. Cohen, and M. Herniou, “Camera Calibration with Distortion Models and Accuracy Evaluation,” IEEE Transactions on pattern analysis and machine intelligence, vol. 14, no. 10, pp. 965-980, 1992.
[71] S. Zhang and S.-T. Yau, “High Dynamic Range Scanning Technique,” Optical engineering, vol. 48, no. 3, pp. 033604-033604-7, 2009.
[72] Z. Zhang, “A Flexible New Technique for Camera Calibration,” IEEE Transactions on pattern analysis and machine intelligence, vol. 22, no. 11, pp. 1330-1334, 2000.
[73] Z. Huang, J. Xi, Y. Yu et al., “Accurate Projector Calibration Based on a New Point-to-Point Mapping Relationship between the Camera and Projector Images,” Applied Optics, vol. 54, no. 3, pp. 347-356, 2015.
[74] D. Lanman and G. Taubin, "Build Your Own 3d Scanner: Optical Triangulation for Beginners," in Acm Siggraph Asia 2009 Courses, pp. 1-94, 2009.
[75] E. H. Land, “The Retinex Theory of Color Vision,” Scientific american, vol. 237, no. 6, pp. 108-129, 1977.
[76] M. F. Zakaria, H. Ibrahim, and S. A. Suandi, “A Review: Image Compensation Techniques,” in 2010 2nd international conference on computer engineering and technology, vol. 7, pp. V7-404-V7-408, 2010.
[77] M. Dileep and A. S. Murthy, “A Comparison between Different Colour Image Contrast Enhancement Algorithms,” in 2011 International Conference on Emerging Trends in Electrical and Computer Technology, pp. 708-712, 2011.
[78] A. K. Vishwakarma and A. Mishra, “Color Image Enhancement Techniques: A Critical Review,” Indian J. Comput. Sci. Eng, vol. 3, no. 1, pp. 39-45, 2012.
[79] D. J. Jobson, Z.-u. Rahman, and G. A. Woodell, “Properties and Performance of a Center/Surround Retinex,” IEEE transactions on image processing, vol. 6, no. 3, pp. 451-462, 1997.
[80] G. Hines, Z.-u. Rahman, D. Jobson et al., “Single-Scale Retinex Using Digital Signal Processors,” in Global signal processing conference, no. Paper 1324, 2005.
[81] C. Wang, M. Peng, L. Xu et al., “A Single Scale Retinex Based Method for Palm Vein Extraction,” in 2016 IEEE Information Technology, Networking, Electronic and Automation Control Conference, pp. 75-78, 2016.
[82] Z. Al‐Ameen and G. Sulong, “A New Algorithm for Improving the Low Contrast of Computed Tomography Images Using Tuned Brightness Controlled Single‐Scale Retinex,” Scanning, vol. 37, no. 2, pp. 116-125, 2015.
[83] D. J. Jobson, Z.-u. Rahman, and G. A. Woodell, “A Multiscale Retinex for Bridging the Gap between Color Images and the Human Observation of Scenes,” IEEE transactions on image processing, vol. 6, no. 7, pp. 965-976, 1997.
[84] K. Barnard and B. Funt, “Analysis and Improvement of Multi-Scale Retinex,” in Color and Imaging Conference, vol. 5, pp. 221-226, 1997.
[85] T. Mertens, J. Kautz, and F. Van Reeth, “Exposure Fusion: A Simple and Practical Alternative to High Dynamic Range Photography,” in Computer graphics forum, vol. 28, no. 1, pp. 161-171, 2009.
[86] S. Zhang, “Rapid and Automatic Optimal Exposure Control for Digital Fringe Projection Technique,” Optics and Lasers in Engineering, vol. 128, p. 106029, 2020.
[87] P. J. Burt and E. H. Adelson, “A Multiresolution Spline with Application to Image Mosaics,” ACM Transactions on Graphics (TOG), vol. 2, no. 4, pp. 217-236, 1983.
[88] Y. Lei, K. R. Bengtson, L. Li et al., “Design and Decoding of an M-Array Pattern for Low-Cost Structured Light 3d Reconstruction Systems,” in 2013 IEEE international conference on image processing, pp. 2168-2172, 2013.
[89] A. S. Parihar and K. Singh, “A Study on Retinex Based Method for Image Enhancement,” in 2018 2nd International Conference on Inventive Systems and Control (ICISC), pp. 619-624, 2018.
[90] S. Liu, W. Long, L. He et al., “Retinex-Based Fast Algorithm for Low-Light Image Enhancement,” Entropy, vol. 23, no. 6, p. 746, 2021.
[91] S. Tang, M. Dong, J. Ma et al., “Color Image Enhancement Based on Retinex Theory with Guided Filter,” in 2017 29th Chinese Control And Decision Conference (CCDC), pp. 5676-5680, 2017.
[92] J. Yang, Y. Xu, H. Yue et al., “Low‐Light Image Enhancement Based on Retinex Decomposition and Adaptive Gamma Correction,” IET image processing, vol. 15, no. 5, pp. 1189-1202, 2021.
[93] W. Yang, W. Wang, H. Huang et al., “Sparse Gradient Regularized Deep Retinex Network for Robust Low-Light Image Enhancement,” IEEE transactions on image processing, vol. 30, pp. 2072-2086, 2021.
[94] W. Wang, Z. Chen, X. Yuan et al., “Adaptive Image Enhancement Method for Correcting Low-Illumination Images,” Information Sciences, vol. 496, pp. 25-41, 2019.
[95] L. Li, R. Wang, W. Wang et al., “A Low-Light Image Enhancement Method for Both Denoising and Contrast Enlarging,” in 2015 IEEE international conference on image processing (ICIP), pp. 3730-3734, 2015.
[96] Z. Zhao, B. Xiong, L. Wang et al., “Retinexdip: A Unified Deep Framework for Low-Light Image Enhancement,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 32, no. 3, pp. 1076-1088, 2021.
[97] Y. Niu, J. Wu, W. Liu et al., “Hdr-Gan: Hdr Image Reconstruction from Multi-Exposed Ldr Images with Large Motions,” IEEE transactions on image processing, vol. 30, pp. 3885-3896, 2021.
[98] J. Shi, X. Zhu, H. Wang et al., “Label Enhanced and Patch Based Deep Learning for Phase Retrieval from Single Frame Fringe Pattern in Fringe Projection 3d Measurement,” Optics Express, vol. 27, no. 20, pp. 28929-28943, 2019.
[99] B. D. Lee and M. H. Sunwoo, “Hdr Image Reconstruction Using Segmented Image Learning,” IEEE Access, vol. 9, pp. 142729-142742, 2021.
[100] M. S. Santos, T. I. Ren, and N. K. Kalantari, “Single Image Hdr Reconstruction Using a Cnn with Masked Features and Perceptual Loss,” arXiv preprint arXiv:2005.07335, 2020.