本論文主要探討運用深度學習在玻璃基板瑕疵檢測的技術及利用數位全像顯微系統得到玻璃基板的複數影像進行瑕疵檢測，透過全像術取得玻璃基板的光學繞射資訊，其中複數影像包含振幅資訊及相位資訊，用深度學習進行學習背景、灰塵、刮痕、污漬、棉絮及水痕的振幅資訊及相位資訊之特性，更進一步探討各種瑕疵之間的差異、特性及辨識結果。在全像術和深度學習的運用，本研究會探討調整參數及改進流程達到檢測系統的辨識正確率最大化，以及影像校正方面使得可以得到品質穩定的複數影像，以利未來可以推廣到透過數位全像顯微系統擷取其他材料的光場資訊進行檢測，增加未來應用層面的潛力。

We present an inspection method based on deep learning for defect classification of glass substrate by using complex wavefronts measurement in digital holographic microscopy. The complex image contains the amplitude and phase. The proposed inspection performed on convolutional neural network can achieve high accuracy of classifying defects, such as dust, crack , fiber, stain and watermark, on the glass substrate. We will adjustment parameters and the image correction to obtain a stable image with stable quality, which has more potential in application in the future.

[ 1 ] Y. Jin, Z. Wang, L. Zhu and J. Yang, "Research on in-line glass defect inspection technology based on Dual CCFL," Proc. Engineering, 1797-1801 (2011).
[ 2 ] Y. LeCun, L. Bottou, Y. Bengio and P. Haffner. “Gradient-based learning applied to document recognition,” Proc. IEEE, 2278-2324 (1998).
[ 3 ] M.A. Hearst ; S.T. Dumais ; E. Osuna ; J. Platt ; B. Scholkopf, “Support vector machine,” IEEE Intelligent Systems 3, 18-28 (1998).
[ 4 ] A. Krizhevsky, I. Sutskever and G. E. Hinton, "ImageNet Classification with Deep Convolutional Neural Networks," Proc. NIPS, 1097-1105 (2012).
[ 5 ] R. Girshick, J. Donahue, T. Darrell, J. Malik, "Rich feature hierarchies for accurate object detection and semantic segmentation," CVPR, 580-587 (2014).
[ 6 ] R. Girshick, "Fast R-CNN," ICCV, 1440-1448 (2015).
[ 7 ] S. Ren, K. He, R. Girshick and J. Sun, "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks," NIPS, 1137-1149 (2015).
[ 8 ] T. Zhang and I. Yamaguchi, “Three-dimensional microscopy with phase-shifting digital holography,” Opt. Lett. 23, 1221–1223, (1998).
[ 9 ] I. Yamaguchi, “Image formation in phase-shifting digital holography and applications to microscopy,” Appl. Opt. 40, 6177-6186 (2001).
[ 10 ] P. Guo and A. J. Devaney, “Digital microscopy using phase-shifting digital holography with two reference waves,” Opt. Lett. 29, 857-859 (2004).
[ 11 ] V. Kebbel, Hans-Jürgen Hartmann, Werner P. O. Jüptner, “Application of digital holographic microscopy for inspection of microoptical components,” Proc. SPIE 4389, 189-198 (2001).
[ 12 ] V. Kebbel, J. Müller, W. P. O. Jüptner, “Characterization of aspherical micro-optics using digital holography: improvement of accuracy,” Proc. SPIE 4778, 188-197 (2002).
[ 13 ] V. Kebbel, H.-J. Hartmann, W. P. 0. JUptner, “Characterization of micro-optics using digital holography,” Proc. SPIE 4101, 477-487 (2000).
[ 14 ] F. Charrière, J. Kühn, T. Colomb “Characterization of microlenses by digital holographic microscopy,” Appl Opt. 45, 829-835 (2006).
[ 15 ] T. Colomb, E. Cuche, and C. Depeursinge, “Automatic procedure for aberration compensation in digital holographic microscopy and applications to specimen shape compensation,” Appl. Opt. 45, 851-863 (2006).
[ 16 ] J. Sheng, E. Malkiel, and J. Katz, “Digital holographic microscope for measuring three-dimensional particle distributions and motions,” Appl. Opt. 45, 3893-3901 (2006).
[ 17 ] E. Cuche, P. Marquet, and C. Depeursinge, “Simultaneous amplitude-contrast and quantitative phase-contrast microscopy by numerical reconstruction of Fresnel off-axis holograms,” Appl. Opt. 38, 6994–7001 (1999).
[ 18 ] G. Pedrini and H. J. Tiziani “Short-coherence digital microscopy by use of a lensless holographic imaging system,” Appl. Opt. 41, 4489-4496 (2002).
[ 19 ] L. Martínez-León, G. Pedrini, and W. Osten, “Applications of short-coherence digital holography in microscopy,” Appl. Opt. 44, 3977-3984 (2005).
[ 20 ] S. Tamano, Y. Hayasaki, and N. Nishida, “Phase-shifting digital holography with a low-coherence light source for reconstruction of a digital relief objecthidden behind a light-scattering medium,” Appl. Opt. 45, 963-969 (2006).
[ 21 ] G. Indebetouw and P. Klysubun, “Imaging through scattering media with depth resolution by use of low-coherencegating in spatiotemporal digital holography,” Opt. Lett. 25, 212-214 (2000).
[ 22 ] P. Massatsch, F. Charrière, E. Cuche, P. Marquet, and C. D. Depeursinge, “Time-domain optical coherence tomography with digital holographic microscopy,” Appl. Opt. 44, 1806–1812 (2005).
[ 23 ] L. Yu and Myung K. Kim, “Wavelength scanning digital interference holography for tomographic three dimensional imaging by use of the angular spectrum method,” Opt. Lett. 30, 2092-2094 (2005).
[ 24 ] F. Charrière, A. Marian, “Cell refractive index tomography by digital holographic microscopy,” Opt. Lett. 31, 178-180 (2006).
[ 25 ] U. Schnars, Werner P O J¨uptner, “Digital recording and numerical reconstruction of holograms,” Meas. Sci. Technol., 13, R85–R101 (2002).
[ 26 ] D. Gabor, Nature 161, 777–778 (1948).
[ 27 ] K. He, X. Zhang, S. Ren and J. Sun, “Spatial pyramid pooling in deep convolutional networks for visual recognition,” ECCV, (2014). [ 28 ] K. Simonyan and A. Zisserman, “Very Deep Convolutional Networks for Large-Scale Image Recognition.” ICLR, (2015).
[ 29 ] K. He, X. Zhang, S. Ren and J. Sun, “Deep Residual Learning for Image Recognition,” CVPR, (2016).
[ 30 ] P. Viola and M. J. Jones, “Robust Real-Time Face Detection,” International Journal of Computer Vision, 57(2), 137-154 (2003).