臺灣博碩士論文加值系統

由於科技的日新月異，人們對於技術與品質的要求也日益提高，與人們生活息息相關的顯示螢幕亦是如此，隨著對於顯示螢幕品質的要求提高，被當成面板檢驗標準的壞點數目更是一個值得重視的問題。傳統的人眼檢測未來勢必將逐漸被淘汰，由於人眼檢測不僅可能會造成職業傷害，檢出的良率也是一個值得商榷的問題。因此，以機器視覺取代人眼檢測的自動光學檢測推行將是勢在必行。本研究將以自動光學檢測為基準，建構一個以卷積神經網路為基礎的TFT-LCD壞點分類模型，並透過台灣某知名筆電品牌商之實際面板影像資料實證之。近年對於TFT-LCD壞點的相關分類研究，大多數是以機器學習方法透過人為的影像處理以及特徵值計算，最後利用單層的演算法分類之。本研究最大的突破在於省去人為對於影像的特徵值計算以及影像的前處理過程，而整體判別的準確度也能達到99.4%的高準確度，能夠成功有效的分類TFT-LCD的壞點。

Since the ever-changing technology nowadays, people are increasing their request for skill and qualities as well as the display screens. As the level of the quality of display screens rise, the numbers of dead dots that used to be the inspection standard become a problem that can’t be ignored. Traditional inspection methods that inspected by humans may cause occupational injuries and fatigue and also harm the yield rate. Therefore, the trend of using Automatic Optical Inspection (AOI) instead of the traditional way is inevitable. This research is based on AOI, constructing a TFT-LCD defect classification model based on Convolutional Neural Network, evidenced with practical data provided by one well-known laptop brand in Taiwan. The related researches for dead dots recently are most thorough machine learning which processes images and calculates feature values first and finally classifies it with the algorithm. The breakthrough of this research is that there is no need to process images and calculate feature values. Besides, the distinguish rate is up to 99.4% so that we can say it’s effective to classify dead dots for TFT-LCD.

第一章 緒論 1
1.1 研究背景與動機 1
1.2 研究目的 3
1.3 論文架構 3
第二章 文獻探討 5
2.1 TFT-LCD面板瑕疵檢測 5
2.2 深度學習 7
2.2.1 深度學習 7
2.2.2 資料擴增(Data Augmentation) 9
2.2.3 深度學習模型 11
第三章 研究方法 17
3.1 問題描述 17
3.2 模型建置 17
3.3 影像瑕疵判別流程 21
3.4 評估指標 22
第四章 實例驗證 24
4.1 開發環境 24
4.2 研究資料 24
4.3 模型實例展示 27
4.4 判別成果 29
4.4.1 紅色檢測型態之壞點檢測分類結果 29
4.4.2 綠色檢測型態之壞點檢測分類結果 31
4.4.3 藍色檢測型態之壞點檢測分類結果 32
4.4.4 整體判別準確度 35
第五章 結論與未來建議 36
5.1 結論與貢獻 36
5.2 未來研究方向 36
參考文獻 38

曾豊庭. (2016). 應用基因演算法與支持向量機之特徵值篩選於建立液晶面板自動化光學檢測分類模型. 交通大學工業工程與管理系論文
劉芝妤. (2016). 利用提升決策樹建構液晶面板自動光學檢測分類模型. 交通大學工業工程與管理系論文
蔡易達. (2017). 建構以約略集合理論為基礎之 TFT-LCD 自動光學檢測瑕疵分類模型. 交通大學工業工程與管理系論文
簡浩容. (2015). 應用實驗設計於 LCD 面板自動化光學瑕疵檢測之影像處理方法選擇. 交通大學工業工程與管理系論文
Barra, A., Genovese, G., Sollich, P., & Tantari, D. (2017). Phase transitions in Restricted Boltzmann Machines with generic priors. Physical Review E, 96(4), 042156.
Bengio, Y., Courville, A., & Vincent, P. (2013). Representation learning: A review and new perspectives. IEEE transactions on pattern analysis and machine intelligence, 35(8), 1798-1828.
Chen, L.-C., & Kuo, C.-C. (2007). Automatic TFT-LCD mura defect inspection using discrete cosine transform-based background filtering and ‘just noticeable difference’quantification strategies. Measurement Science and Technology, 19(1), 015507.
Cui, X., Liu, Y., Zhang, Y., & Wang, C. (2018). Tire defects classification with multi-contrast convolutional neural networks. International Journal of Pattern Recognition and Artificial Intelligence, 32(04), 1850011.
Fan, S.-K. S., & Chuang, Y.-C. (2010). Automatic detection of Mura defect in TFT-LCD based on regression diagnostics. Pattern recognition letters, 31(15), 2397-2404.
Glorot, X., Bordes, A., & Bengio, Y. (2011). Deep sparse rectifier neural networks. Paper presented at the Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics.
Hinton, G. E., & Salakhutdinov, R. R. (2006). Reducing the dimensionality of data with neural networks. science, 313(5786), 504-507.
Hinton, G. E., & Sejnowski, T. J. (1999). Unsupervised learning: foundations of neural computation: MIT Press.
Huang, L., & Wang, L. (2017). Accelerated Monte Carlo simulations with restricted Boltzmann machines. Physical Review B, 95(3), 035105.
Huang, S.-H., & Pan, Y.-C. (2015). Automated visual inspection in the semiconductor industry. Computers in industry, 66, 1-10.
Ko, T., Peddinti, V., Povey, D., Seltzer, M. L., & Khudanpur, S. (2017). A study on data augmentation of reverberant speech for robust speech recognition. Paper presented at the Acoustics, Speech and Signal Processing (ICASSP), 2017 IEEE International Conference.
Kruthiventi, S. S., Ayush, K., & Babu, R. V. (2017). Deepfix: A fully convolutional neural network for predicting human eye fixations. IEEE Transactions on Image Processing, 26(9), 4446-4456.
LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. nature, 521(7553), 436.
Lee, J. Y., & Yoo, S. I. (2004). Automatic detection of region-mura defect in TFT-LCD. IEICE TRANSACTIONS on Information and Systems, 87(10), 2371-2378.
Lou, Z., Gevers, T., Hu, N., & Lucassen, M. P. (2015). Color constancy by deep learning. Paper presented at the BMVC.
Lu, N., Li, T., Ren, X., & Miao, H. (2017). A deep learning scheme for motor imagery classification based on restricted boltzmann machines. IEEE transactions on neural systems and rehabilitation engineering, 25(6), 566-576.
Lu, R.-s. (2016). Surface defect inspection of TFT-LCD panels based on 1D Fourier method. Paper presented at the Seventh International Symposium on Precision Mechanical Measurements.
Murugan, P., & Durairaj, S. (2017). Regularization and optimization strategies in deep convolutional neural network. arXiv preprint arXiv:1712.04711.
Nakashima, K. (1994). Hybrid inspection system for LCD color filter panels. Paper presented at the Instrumentation and Measurement Technology Conference, 1994. IMTC/94.1994 IEEE.
Nie, D., Cao, X., Gao, Y., Wang, L., & Shen, D. (2016). Estimating CT image from MRI data using 3D fully convolutional networks. In Deep Learning and Data Labeling for Medical Applications (pp. 170-178): Springer.
Parsaei, H., Faraz, M., & Mortazavi, S. (2017). A multilayer perceptron neural network–based model for predicting subjective health symptoms in people living in the vicinity of mobile phone base stations. Ecopsychology, 9(2), 99-105.
Pham, B. T., Bui, D. T., Pourghasemi, H. R., Indra, P., & Dholakia, M. (2017). Landslide susceptibility assesssment in the Uttarakhand area (India) using GIS: a comparison study of prediction capability of naïve bayes, multilayer perceptron neural networks, and functional trees methods. Theoretical and Applied Climatology, 128(1-2), 255-273.
Ranjan, R., Sankaranarayanan, S., Castillo, C. D., & Chellappa, R. (2017). An all-in-one convolutional neural network for face analysis. Paper presented at the Automatic Face & Gesture Recognition (FG 2017), 2017 12th IEEE International Conference.
Relaxation, S. (1984). Gibbs Distributions, and the Bayesian Restoration of Images. S. Geman and D. Geman. IEEE transactions on pattern analysis and machine intelligence, 6, 721-741.
Rosenblatt, F. (1958). The perceptron: a probabilistic model for information storage and organization in the brain. Psychological review, 65(6), 386.
Rosenblatt, F. (1961). Principles of neurodynamics. perceptrons and the theory of brain mechanisms. Retrieved from
Salehinejad, H., Barfett, J., Valaee, S., & Dowdell, T. (2017). Training neural networks with very little data--A Draft. arXiv preprint arXiv:1708.04347.
Shao, H., Jiang, H., Zhang, H., & Liang, T. (2018). Electric locomotive bearing fault diagnosis using a novel convolutional deep belief network. IEEE Transactions on Industrial Electronics, 65(3), 2727-2736.
Shen, D., Wu, G., & Suk, H.-I. (2017). Deep learning in medical image analysis. Annual review of biomedical engineering, 19, 221-248.
Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
Talukdar, J., & Mehta, B. (2017). Human Action Recognition System using Good Features and Multilayer Perceptron Network. arXiv preprint arXiv:1708.06794.
Tanner, M. A., & Wong, W. H. (1987). The calculation of posterior distributions by data augmentation. Journal of the American statistical Association, 82(398), 528-540.
Wehrmann, J., Becker, W., Cagnini, H. E., & Barros, R. C. (2017). A character-based convolutional neural network for language-agnostic Twitter sentiment analysis. Paper presented at the Neural Networks (IJCNN), 2017 International Joint Conference.
Yang, Z., Salakhutdinov, R., & Cohen, W. W. (2017). Transfer learning for sequence tagging with hierarchical recurrent networks. arXiv preprint arXiv:1703.06345.
Zhang, Y., & Zhang, J. (2005). A fuzzy neural network approach for quantitative evaluation of mura in TFT-LCD. Paper presented at the Neural Networks and Brain, 2005. ICNN&B'05.
Zhao, Z., Jiao, L., Zhao, J., Gu, J., & Zhao, J. (2017). Discriminant deep belief network for high-resolution SAR image classification. Pattern Recognition, 61, 686-701.
Zhou, Z., Shin, J., Zhang, L., Gurudu, S., Gotway, M., & Liang, J. (2017). Fine-tuning convolutional neural networks for biomedical image analysis: actively and incrementally. Paper presented at the IEEE Conference on Computer Vision and Pattern Recognition, Hawaii.