臺灣博碩士論文加值系統

為了滿足高速高精度自動化檢測與遠程監控之需求，勢必要有更快速更詳細的分類演算法並結合雲端儲存系統，故本研究目的在開發一套結合雲端儲存之瑕疵分類系統，瑕疵經過分類後將檢測結果儲存至雲端伺服器中，透過網頁呈現給遠端使用者。
具體作法係以Hu矩描述瑕疵輪廓特徵並結合特徵影像亮度參數，當特徵值經過正規化後，利用倒傳遞類神經網路(Back Propagation Neural Network，BPN)來做此特徵資料與瑕疵類別之訓練，分類結果則儲存至MySQL所建立的資料庫上，使用超文字預處理器(PHP: Hypertext Preprocessor，PHP)進行阿帕契(Apache)伺服器與資料庫的溝通，使用者就可透過網頁觀看檢測結果。
本研究以觸控面板作為測試樣本，以擷取350*350像素、每一個像素尺寸為3.5mm之影像進行訓練，經過1000次迭代後，倒傳遞類神經網路的均方差(Mean Square Error，MSE)為0.0019，取其權重w與偏權值，以刮痕、氣泡、粉塵瑕疵做分類測試，共20張影像，每張影像分類過程耗時低於0.0001秒，準確率約90% 。

In order to meet the industry needs for high-speed high-precision automated detection and remote monitoring, a defective part that has undergone line inspection is subjected to a fast classification scheme consisting of an algorithm which can feed the results directly to a cloud storage server. The purpose of this study is to develop a combination of cloud storage and defect classification system where the detection results are stored to the cloud server and then accessed via web presentation to a remote user.
The classification of defect profile is implemented by means of comparing a defect’s luminance characteristics to a target pixel value using the Hu set of invariant moments. The characteristic values normalization and the Back-Propagation Neural Network (BPN) model are implemented to train the algorithm to recognize defect information their characteristics. The classification results are saved to an established Mysql database and use PHP to communicate with the database side of the page. The user can view and access the test results via a website.
Defect maps from the optical inspection of touch panel glass samples were used to evaluate experimentally the classification algorithm. Each map records a 350 * 350 pixel region of the glass sample, with each pixel equal to 3.5 m. Different iterations of the BPN were implemented to seek optimized classification by comparing the mean square error (MSE) between target output and defect profile of the test sample. Defect classification of microscopic scratches, bubbles, and dusts on 20 different defect maps yielded accuracy rates above 90%. Classification of each image was completed in 0.1 ms.

目錄
摘要 I
Abstract II
目錄 III
圖目錄 V
表目錄 VII
第一章 緒論 1
1.1前言 1
1.2 文獻回顧 2
第二章 研究方法 4
2.1 平行運算 4
2.2 叢集電腦 5
2.2.1 高可用性叢集 6
2.2.2負載均衡叢集 7
2.2.3高效能計算叢集 8
2.2.4網格計算 9
2.3 類神經網路 10
2.3.1 倒傳遞類神經網路(Back Propagation Neural Network，BPN) 12
2.4 Hu ''s Moment Invariants 17
2.5 二值化 18
第三章 瑕疵分類實驗與討論 20
3.1 觸控面板瑕疵分類訓練 20
3.2 分類結果與討論 33
第四章 雲端系統 39
4.1伺服器架構 40
4.1 PHP 42
4.2 MySQL資料庫 44
4.4 MPI 44
4.5 雲端網頁 45
第五章 結論與未來展望 51
5.1 結論 51
5.2 未來展望 51
參考文獻 53

 
圖目錄
圖2.1叢集式電腦架構示意圖 6
圖2.2高可用性叢集示意圖 7
圖2.3 負載均衡叢集示意圖 8
圖2.4 高效能叢集示意圖 9
圖2.5 網格叢集示意圖 10
圖2.6 倒傳遞類神經網路架構圖 12
圖2.7 倒傳遞類神經網路流程圖 14
圖3.1 分類實驗流程圖 21
圖3.2均方差與訓練次數關係圖 32
圖4.1 雲端系統架構圖 41
圖4.2帳號密碼輸入 42
圖4.3帳密輸入錯誤 43
圖4.4帳號管理 43
圖4.5登入者IP確認 44
圖4.6良率圖 45
圖4.7 1、2與瑕疵種類關係圖 46
圖4.8 2、3與瑕疵種類關係圖 46
圖4.9 檢測結果網頁 47
圖4.10 瑕疵種類與特徵值數據 48
圖4.11 上傳圖檔 49
圖4.12 上傳成功顯示畫面 49
圖4.13 分析結果 50


 
表目錄
表3.1刮痕樣本與特徵值 22
表3.2氣泡樣本與特徵值 24
表3.3粉塵樣本與特徵值 25
表3.4刮痕、氣泡樣本與特徵值 27
表3.5刮痕、粉塵樣本與特徵值 28
表3.6氣泡、粉塵樣本與特徵值 29
表3.7刮痕、氣泡、粉塵樣本與特徵值 30
表3.8 瑕疵種類與樣本數目 31
表3.9 倒傳遞類神經網路參數設定 32
表3.10 待測影像與分類結果 34

[1]Mei Chih Hu and I Shou Tsai, "Fabric inspection based on best wavelet packet bases," Textile Research Journal, vol. 70, pp. 662-670, 2000.
[2]Gang Wang and T.Warren Liao, "Automatic identification of different types of welding defects in radiographic images," Ndt &; E International, vol. 35, pp. 519-528, 2002.
[3]S. W. Liu, J. H. Huang, J. C. Sung, and C. C. Lee, "Detection of cracks using neural networks and computational mechanics," Computer Methods in Applied Mechanics and Engineering, vol. 191, pp. 2831-2845, 2002.
[4]Issam Abu Mahfouz, "Drilling wear detection and classification using vibration signals and artificial neural network," International Journal of Machine Tools and Manufacture, vol. 43, pp. 707-720, 2003.
[5]Meng Xin Li, Cheng Dong Wu, and Yong Yue, "Automatic visual inspection and classification based on rough sets and neural network," in International Conference on Machine Learning and Cybernetics, 2003, pp. 3095-3099.
[6]Soo Beom Park, Jae Won Lee, and Sang Kyoon Kim, "Content-based image classification using a neural network," Pattern Recognition Letters, vol. 25, pp. 287-300, 2004.
[7]Xiao Feng Wang, De Shuang Huang, Ji Xiang Du, Huan Xu, and Laurent Heutte, "Classification of plant leaf images with complicated background," Applied Mathematics and Computation, vol. 205, pp. 916-926, 2008.
[8]A. L. Ankudinov, C. E. Bouldin, J. J. Rehr, J. Sims, and H. Hung, "Parallel calculation of electron multiple scattering using Lanczos algorithms," Physical Review B - Condensed Matter and Materials Physics, vol. 65, pp. 1041071-10410711, 2002.
[9]Matthew L Massie, Brent N Chun, and David E Culler, "The ganglia distributed monitoring system: Design, implementation, and experience," Parallel Computing, vol. 30, pp. 817-840, 2004.
[10]Andrew Pavlo, Erik Paulson, Alexander Rasin, Daniel J. Abadi, David J. DeWitt, Samuel Madden and Michael Stonebraker, "A comparison of approaches to large-scale data analysis," in SIGMOD-PODS''09 - Proceedings of the International Conference on Management of Data and 28th Symposium on Principles of Database Systems, pp. 165-178, 2009.
[11]Daniel Menascé and Casalic Chio Emiliano, "QoS in grid computing," Internet Computing, IEEE, vol. 8, pp. 85-87, 2004.
[12]Gamal ElMasry, Ning Wang, and Clément Vigneault, "Detecting chilling injury in Red Delicious apple using hyperspectral imaging and neural networks," Postharvest Biology and Technology, vol. 52, pp. 1-8, 2009.
[13]Sung Nien Yu and Kuan To Chou, "Integration of independent component analysis and neural networks for ECG beat classification," Expert Systems with Applications, vol. 34, pp. 2841-2846, 2008.
[14]M. Egmont-Petersen, D. De Ridder, and H. Handels, "Image processing with neural networks- A review," Pattern Recognition, vol. 35, pp. 2279-2301, 2002.
[15]J. F. Mas and J. J. Flores, "The application of artificial neural networks to the analysis of remotely sensed data," International Journal of Remote Sensing, vol. 29, pp. 617-663, 2008.
[16]Zhi Xiao, Shi Jie Ye, Bo Sun Zhong and Xin Cai, "BP neural network with rough set for short term load forecasting," Expert Systems with Applications, vol. 36, pp. 273-279, 2009.
[17]Taskin Kavzoglu and Paul M. Mather, "The use of backpropagating artificial neural networks in land cover classification," International Journal of Remote Sensing, vol. 24, pp. 4907-4938, 2003.
[18]Zhihu Huang and Jinsong Leng, "Analysis of Hu''s moment invariants on image scaling and rotation," in Computer Engineering and Technology (ICCET), 2010 2nd International Conference on, 2010, pp. V7-476-V7-480.
[19]Iosup Alexandru, Ostermann Simon, Yigitbasi Nezih Nezih, Prodan Radu, Fahringer Thomas, and Epema Dick H J, "Performance analysis of cloud computing services for many-tasks scientific computing," IEEE Transactions on Parallel and Distributed Systems, vol. 22, pp. 931-945, 2011.
[20]Henry Wang, Yunzhi Ma, Guillem Pratx, and Xing Lei, "Toward real-time Monte Carlo simulation using a commercial cloud computing infrastructure," Physics in Medicine and Biology, vol. 56, pp. N175-N181, 2011.
[21]Kumar Vipin, K. Ravikumar, S. Aravinth, and B. Rajkumar, "A message passing interface to support fast data access in distributed cloud environment along with master and slave communication," in Current Trends in Engineering and Technology (ICCTET), 2014 2nd International Conference on, 2014, pp. 309-312.
[22]Francesco Adamo, Filippo Attivissimo, Attilio Di Nisio, and Mario Savino, "A low-cost inspection system for online defects assessment in satin glass," Measurement, vol. 42, pp. 1304-1311, 2009.
[23]Ahmed Abouelela, Hazem M. Abbas, Hesham Eldeeb, Abdelmonem A. Wahdan, and Salwa M. Nassar, "Automated vision system for localizing structural defects in textile fabrics," Pattern Recognition Letters, vol. 26, pp. 1435-1443, 2005.