具深度學習之數位全像顯微系統於玻璃基板瑕疵檢測

Simple item page
dc.contributor鄭超仁zh_TW
dc.contributor杜翰艷zh_TW
dc.contributorCheng, Chau-Jernen_US
dc.contributorTu, Han-Yenen_US
dc.contributor.author蔡昕澔zh_TW
dc.contributor.authorCai, Sin-Haoen_US
dc.date.accessioned2020-10-19T07:12:16Z
dc.date.available不公開
dc.date.available2020-10-19T07:12:16Z
dc.date.issued2018
dc.description.abstract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。zh_TW
dc.description.abstractWe 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.en_US
dc.description.sponsorship光電工程研究所zh_TW
dc.identifierG060448005S
dc.identifier.urihttp://etds.lib.ntnu.edu.tw/cgi-bin/gs32/gsweb.cgi?o=dstdcdr&s=id=%22G060448005S%22.&%22.id.&
dc.identifier.urihttp://rportal.lib.ntnu.edu.tw:80/handle/20.500.12235/112014
dc.language中文
dc.subject深度學習zh_TW
dc.subject全像術zh_TW
dc.subject瑕疵檢測zh_TW
dc.subject玻璃基板zh_TW
dc.subject摺積神經網路zh_TW
dc.subjectDeep Learningen_US
dc.subjectHolographyen_US
dc.subjectDefect Inspectionen_US
dc.subjectGlass Substrateen_US
dc.subjectConvolutional Neural Networken_US
dc.title具深度學習之數位全像顯微系統於玻璃基板瑕疵檢測zh_TW
dc.titleDefect inspection of glass substrate in digital holographic microscope with deep learningen_US

Files

Collections

學位論文