本論文提出一改良式密度為基礎分群演算法，「整合密度趨勢與虛擬核心點之改良式密度分群演算法」：DTVC-DBSCAN(Integration of Density-Trend and Virtual Corepoint on Density-Based Clustering of Applications with Noise)。本演算法首創虛擬核心點方式，以未分類資料點分布趨勢從八方位方向決定虛擬核心點的位置，並進行以密度為基礎的資料分群。由本論文提出的演算法配合一系列影像處理流程並應用於太陽能電池背面檢測，其檢測瑕疵項目包含刮痕、破裂、破孔、裂痕、微裂等。從線型掃描平台中取得原影像後進行灰階處理，接著利用Sobel輪廓偵測方式突顯影像中的瑕疵特徵，再利用Hough轉換法測線並去線化，去除原始影像中屬於bus-bar及邊線的部分，最後再使用本論文提出之DTVC-DBSCAN對影像資料進行分群動作。經實驗結果，可將太陽能電池背面的九分割瑕疵影像進行有效的標記分群位置與範圍，並用顏色差異方式來使分群結果更直覺化。一張300dpi的5吋太陽能電池板背面進行九分割（影像為525*525pixels大小）檢測，其分割影像總運算時間為12~17ms，整張5吋太陽能電池板影像總運算時間為138ms，就分群演算法相比依資料數目不同其性能比GDBSCAN節省2.3%∼12.9%的時間不等。

This thesis proposed an improved Density-Based Clustering of Applications with Noise (DBSCAN): Integration of Density-Trend and Virtual Corepoint on Density-Based Clustering of Applications with Noise (DTVC-DBSCAN). DTVC-DBSCAN originated Virtual Corepoint method by using the distributed trend of undefined data to locate one virtual corepoint from 8 neighbor direction and cluster the data by density. The collocation of DBSCAN and a series of image processing process can be used on a solar cell backside’s defects such as scratch, fracture, hole, crack and micro crack. Firstly, a linear scanner is used to get original image of a solar cell backside and grays-scale the image. And then the Sobel edge detection method is used to find the object edge in the image. Third, Hough transform line detection method is used to detect the lines which then are removed from the original image. Finally, the proposed DTVC-DBSCAN is used to cluster the defects. According to the experimental results, this process can effectively locate the solar cell defects position and area, and it also maked the cluster result more noticeable by using different colors. In the experiment, it took 12~17ms for processing each 9-grid-divided image and took 138ms for processing whole 5" solar cell backside. For the different amount of data, the DTVC-DBSCAN can save 2.3% ~12.9% processing time than the GDBSCAN.

[1] 聯合國氣候變化綱要公約(UNFCCC),
http://unfccc.int/kyoto_protocol/status_of_ratification/items/2613.php, June,2010
[2] 國際能源總署太陽光發電系統實施協定(IEA PVPS), http://www.iea-pvps.org
[3] 台灣區電機電子工業同會，http://www.teema.org.tw
[4] 陳婉如，「台灣太陽能電池產業未來展」，光連雙月刊，2005。
[5] 楊昌中，「能源領域中的奈米科技研究」，工研院能源與環境研究所，2005。
[6] S. Roberts, “Solar electricity: A practical guide to designing and installing small photovoltaic systems,” Prentice Hall, 1991.
[7] 拓墣產業研究所，「2010年太陽能產業四大趨勢」，2009。
[8] 能源局，「新兆元能源產業旗艦計畫」，經濟部，2008。
[9] 能源局，「綠色能源產業旭升方案」，經濟部，2009。
[10] 投資業務處，「太陽光電產業分析及投資機會」，經濟部，2008。
[11] 鄭文瑋、薛名凱、羅文期、簡宏達，「太陽能電池之分色與瑕疵檢測應用」，Taiwan AOI Forum, Show and Contest，台灣科技大學，台北，十一月，2009。
[12] 太陽能光電中心，「綠能革命新紀元太陽光電精采可期」，工業技術研究院，2008。
[13] 劉智生、洪儒生，「太陽能電池的高效率化」，科學發展439期，2009。
[14] 太陽光電資訊網，http://solarpv.itri.org.tw/aboutus/sense/battery.asp
[15] 連水養，「量產型單晶太陽能電池製作」，國立雲林科技大學電機工程系碩士論文，2002。
[16] 中華太陽能聯誼會，http://www.solar-i.com/know.html
[17] 吳財福、張健軒、陳裕愷，「太陽能供電與照明系統綜論」，全華圖書，1999。
[18] 尤如瑾，「世界太陽光電產業現況與展望」，機械工業技術與市場資訊專輯，2005。
[19] A. Kolodziej, “Staebler-Wronski effect in amorphous silicon and its alloys,” OPTO-Electronics Review 12, pp. 21-32, 2004.
[20] 鄭淑娟，「薄膜太陽能技術、製程與產品特性分析」，MIC產業情報研究所，2009。
[21] 郭冠志，「機器視覺應用於太陽電池之表面瑕疵檢測」，國立台北科技大學機電整合研究所碩士論文，2007。
[22] 陳心怡，「太陽能電池板表面瑕疵檢測」，國立中央大學資訊工程研究所碩士論文，2007。
[23] 蔡欣儒，「太陽能電池板的尺寸量測與線路瑕疵檢測」，國立中央大學資訊工程研究所碩士論文，2007。
[24] Z. Fu, Y. Zhao, Y. Liu, Q. Cao, M. Chen, J. Zhang, and J. Lee, “Solar Cell Crack Inspection by Image Processing,” International Conference on the Business of Electronic Product Reliability and Liability, Shanghai, China, April, 2004.
[25] 張志傑，「應用非線性擴散模式於異質性紋路之多晶太陽能晶片表面微裂瑕疵檢測」，元智大學工業工程與管理研究所碩士論文，2008。
[26] 馮趙祥，「新式Haar-like矩形特徵於太陽能板表面及邊緣瑕疵檢測研究」，國立台灣科技大學自動化及控制研究所碩士論文，2008。
[27] 顏旭男、王浩鑑、林顏諭，「無需精準定位之太陽能表面瑕疵檢測系統開發」，Taiwan AOI Forum, Show and Contest，台灣科技大學，台北，十一月，2009。
[28] 高祥恩，「多晶矽太陽能電池之表面瑕疵檢測」，中華大學機械工程學系碩士班論文，2007。
[29] 林育臣，「群聚技術之研究」，朝陽科技大學資訊管理研究所碩士論文，2002
[30] J. MacQueen, “Some Methods for Classification and Analysis of Multivariate Observations, ” In Proc. 5th Berkeley Symp. Math. Stat. and Prob., Vol. 1, pp. 281-297, 1967.
[31] S. Guha, R. Rastogi and K. Shim, “CURE: An efficient clustering algorithm for large databases, ” In Proc. 1998 ACM-SIGMOD Int. Conf. Management of Data (SIGMOD’98), Seattle, WA, pp. 73-84, June, 1998.
[32] M. Ester, H.P. Kriegel, J. Sander and X. Xu, “A density-based algorithm for discovering clusters in large spatial databases with noise, ” Proceedings of the Second International Conference on Knowledge Discovery and Data Mining, Portland, Oregon, USA, pp. 226-231, 1996.
[33] W. Wang, R. Yang and R. Muntz, “STING: A Statistical Information grid Approach to Spatial Data Mining,” In Proc. 1997 Int. Conf. Very Large Data Bases(VLDB’97), Athens, Greece, pp. 186-195, August, 1997.
[34] N. Beckmann, H.P. Kriegel, R. Schneider, and B. Seeger, “The R*-Tree: An Efficient and Robust Access Method for Points and Rectangles,” Proc. ACM SIGMOD Conf. Management of Data, Atlantic City, NJ, 1990.
[35] S. Berchtold, D. Keim, and H.P. Kriegel, “The X-Tree: An Index Structure for High-Dimensional Data,” Proc. 22nd Conf. Very Large Data Bases, Taj Mahal Hotel, Mumbai (Bombay), India, pp. 28-39. 1996.
[36] X. Xu, M. Ester, H.P. Kriegel and J. Sander, “A distribution– based Clustering Algorithm for Mining in Large Spatial Databases,” In Proc. 14th Int. Conf. Data Engineering (ICDE'98),Orlando, Florida, USA, 1998.
[37] M. Ester, H.P. Kriegel, J. Sander, M. Wimmer and X. Xu, “Incremental Clustering for Mining in a Data Warehousing Environment,” In Proc. 24th Int. Conf. Very Large Databases (VLDB'98), New York City, USA, pages 24 - 27, August, 1998.
[38] M. Ankerst, M. Breunig, H.P. Kriegel, and J. Sander, “OPTICS: Order-ing points to identify the clustering structure,” In Proc. 1999 ACM-SIGMOD Int. Conf. Management of Data (SIGMOD’99), pages 49-60, Philadelphia, PA, June 1999.
[39] B. Borah and D.K. Bhattacharyya, “An Improved Sampling-Based DBSCAN for Large Spatial Databases,” Intelligent Sensing and Information Processing, pp. 92-96, 2004.
[40] D. Ma and A. Zhang, “An Adaptive Density-Based Clustering Algorithm for Spatial Database with Noise,” Data Mining, ICDM '04. Fourth IEEE International Conference, Brighton, United Kingdom, pp.467–470, Nov. 01-04, 2004.
[41] P. Viswanath and R. Pinkesh, “l-DBSCAN : A Fast Hybrid Density Based Clustering Method,” Pattern Recognition, 2006. ICPR 2006. 18th International Conference on Volume 1, Hong Kong, pp. 912-915, August 20-24, 2006.
[42] Y.P. Wu, J.J. Guo and X.J. Zhang, “A Linear DBSCAN Algorithm Based on LSH,” Proceedings of the Sixth International Conference on Machine Learning and Cybernetics, Hong Kong, pp. 2608-2614, August, 2007.
[43] A. Gionis, P. Indyk, and R. Motwani, “Similarity Search in High Dimensions via Hashing,” Proc. Very Large Data Base Conf. (VLDB '99), pp. 518-529, Sept, 1999.
[44] Y. Chen, L. Tu, “Density-Based Clustering for Real-Time Stream Data.” KDD’07, San Jose, California, USA, pp. 133-142, August 12–15, 2007.
[45] L. Duan, L. Xu, F. Guo, J. Lee, B. Yan, “A local-density based spatial clustering algorithm with noise,” Information Systems Vol.32, pp. 978-986, 2007.
[46] B. Liu, “A Fast Density-Based Clustering Algorithm for Large Databases,” Proceedings of the Fifth International Conference on Machine Learning and Cybernetics, Dalian, pp. 996-1000, August, 2006.
[47] 吳宗諭、蔡明忠、田芬寧，「以密度為基礎之改良型快速分群演算法及其於偏光板瑕疵檢測之應用」，技術學刊Vol.24，No.4，pp. 267-274，2009，12月。
[48] 蔡明忠、田芬寧、林家戊，「以密度重心導引之分群演算法及其於抗反射玻璃瑕疵檢測之應用」，Taiwan AOI Forum, Show and Contest，台灣科技大學，台北，十一月，2009。
[49] 鐘國亮，「影像處理與電腦視覺」，東華書局，2006。