本研究針對互補式金屬氧化物半導體影像感測器(CMOS image sensor, CIS)微型多層非球面透鏡組開發一套光學檢測系統。因CIS微型多層非球面透鏡組之構造為多層非球面透鏡之組合，當光線透過非球面透鏡組時，會在不同層上發生折射及反射，導致所擷取之影像產生環形光暈，進而影響後續進行瑕疵判別，且為考慮拍攝影像時之影像清晰度與檢測之瑕疵大小，採用之鏡頭景深較淺(0.4mm)無法涵蓋整個樣本影像之高度(1.6mm)，使得擷取到的影像無法一次性對待測物進行全檢。上述兩種情況都會使後續進行瑕疵檢測產生問題，因此本研究自行設計軟硬體設備，並搭配所開發的影像處理流程，進而克服上述問題並建立CIS微型多層非球面透鏡組之瑕疵檢測系統。
本研究提出一套CIS微型多層非球面透鏡組之瑕疵檢測演算法，主要分為三階段，第一階段為影像前處理，利用霍夫測圓進行影像定位並切割感興趣區間，接著使用single-scale Retinex(SSR)亮度校正法來消除或降低光暈現象所造成的亮度不均之問題；第二階段為瑕疵檢測流程，分為大範圍瑕疵及細微瑕疵之檢測流程。利用Kuwahara濾波器、管制界限法、影像遮罩、區域成長以及形態學等方法分割待測物上的瑕疵，並且為克服景深無法覆蓋待測物高度之問題，本研究自行開發實驗機台，利用Z軸移動平台進行多層影像的擷取，且為避免大面積瑕疵影響附近層所拍攝的成像品質，利用瑕疵完整度與其瑕疵銳利度來進行判別，藉此消除大面積瑕疵造成的影響，進而準確地對瑕疵進行分割並計算其特徵值；第三階段進行瑕疵辨識，利用支持向量機進行分類，實驗結果顯示，瑕疵分類準確率為97.97%，證實本研究所設計之軟硬體設備能有效的對CIS微型多層非球面透鏡組進行瑕疵檢測與分類。

This paper developed an optical inspection system of CMOS image sensor (CIS) micro multi-layer non-spherical lens module. However, the CIS lens module structure was multi-layer. When light passed through the non-spherical lens module, it will cause a halo because of reflection and refraction. It led defect is difficult to be found. When acquiring the image, the image resolution and size of defects needed to be considered. It caused the magnification lens’s depth of field does not cover the height of the inspected object. The mentioned two cases would be difficult to perform a follow-up defect detection so this paper developed solutions these problem, and developed a CIS micro multi-layer non-spherical lens module inspection system.
The CIS micro multi-layer non-spherical lens module inspection system consisted three main components: (1) Image preprocessing, (2) Defect inspection procedure, and (3) Defect recognition. The first component mainly used Hough transform to detect circle and to segment region of interest (ROI), and then amended illumination unevenness by using single-scale Retinex. The second component used the Kuwahara filter, control limit method, region growing, etc to segment the defect. In order to solve the problem of lens’s depth field not covering the inspected object’s height, the multi-image was acquired. This paper proposed a way to avoid major defect that influenced different layers image by judging defect unabridged rate and defect sharp rate, and calculated the defect feature. Finally, this study used a support vector machine to recognize different kinds of defect. The experimental result showed the accuracy of defect recognition is 97.97 %. This paper proposed an optical inspection system of CMOS image sensor micro multi-layer non-spherical lens module that effectively detected and recognized the defects.

[1] 陳榕庭，「半導體封裝與測試工程─CMOS影像感測器實務」，全華圖書股份有限公司，台灣台北，2007年。
[2] 呂建鋒 編著，「整合影像感測器/光學元件 晶圓級影像感測模組誕生」，新通訊元件雜誌，第八十七期，2008年。
[3] 吳志凌，「隱形眼鏡自動光學檢測系統之設計與開發」，國立交通大學，工業工程及管理研究所，碩士論文，2007年。
[4] Tsai, D. M., and Chuang, S. T., “1D-based defect detection in patterned TFT-LCD panels using characteristic fractal dimension and correlations,” Machine Vision and Applications, Vol. 20, No. 6, pp. 423-434, 2009.
[5] Mar, N. S. S., Yarlagadda, P. K. D. V., and Fookes, C., “Design and development of automatic visual inspection system for PCB manufacturing,” Robotics and Computer-Integrated Manufacturing, Vol. 27, No. 5, pp. 949-962, 2011.
[6] Ko, K. W., Kim, D. H., Kim, M. Y., and Kim, J. H., “An automatic optical inspection system for inspection of CMOS compact camera module assembly,” International Journal of Precision Engineering and Manufacturing, Vol. 10, No. 5, pp. 67-72, 2009.
[7] Chiu, Y. S., and Lin, H. D., “An innovative blemish detection system for curved LED lenses,” Expert Systems with Applications, Vol. 40, No. 2, pp. 471-479, 2013.
[8] Chen, Y. H., Hsieh, Y. F., Hsu, C. W., Hwang, C. H., and Liao, T. S., “An image based optical lens eccentric error inspection system,” International Instrumentation and Measurement Technology Conference, pp. 1094-1097, Graz, Austria, 2012.
[9] Yang, S. W., Lin, C. S., Fu, S. H., Tsou, C., and Lai, T. H., “Lens sag measurement of microlens array using optical interferometric microscope,” Optics Communications, Vol. 285, No. 6, pp. 1066-1074, 2012.
[10] Lee, J. S., “RII: Renovating the irregular illumination of digital image archives,” Journal of Visual Communication and Image Representation, Vol. 24, No. 7, pp. 739-751, 2013.
[11] Lin, H. D., “Tiny surface defect inspection of electronic passive components using discrete cosine transform decomposition and cumulative sum techniques,” Image and Vision Computing, Vol. 26, No. 5, pp. 603-621, 2008.
[12] Xie, X., Zheng, W. S., Lai, J., Yuen, P. C., and Suen, C. Y., “Normalization of face illumination based on large-and small-scale features,” IEEE Transactions on Image Processing, Vol. 20, No. 7, art. no. 5658185, pp. 1807-1821, 2011.
[13] Land, E. H., “The Retinex theory of colour vision,” Scientific American , Vol. 237, No. 6, pp. 108-128, 1977.
[14] Fu, B., Xiong, X., and Sun, G., “An efficient mean filter algo-rithm,” International Conference on Complex Medical Engineering, 5876785, pp. 466-470, Harbin, Heilongjiang, China , 2011.
[15] Ko, S. J., and Lee, Y. H., “Center weighted median filters and their applications to image enhancement,” IEEE Transactions on Circuits and Systems, Vol. 38, No. 9, pp. 984-993, 1991.
[16] Chang, C. C., Hsiao, J. Y., and Hsieh, C. P., “An adaptive median filter for image denoising,” Proceedings - 2008 2nd International Symposium on Intelligent Information Technology Application, 4739784, pp. 346-350, Shanghai, China, 2008.
[17] Kuwahara, M., Hachimura, K., Eiho, S., and Kinoshita, M., “Processing of RI-angiocardiographic images,” Digital Processing of Biomedical Images, pp.187-202, 1976.
[18] Kyprianidis, J. E., Kang, H., and Dollner, J., “Image and video abstraction by anisotropic Kuwahara filtering,” Computer Graphics Forum, Vol. 28, No. 7, pp. 1955-1963, 2009.
[19] Ying, Wen, “An improved discriminative common vectors and support vector machine based face recognition approach,” Expert Systems with Applications, Vol. 39, No. 4, pp. 4628-4632, 2012.
[20] Al-Anazi, A., and Gates, I. D., “A support vector machine algorithm to classify lithofacies and model permeability in heterogeneous reservoirs,” Engineering Geology, Vol. 114, No. 3-4, pp. 267-277, 2010.
[21] Halfawy, M. R., and Hengmeechai, J., “Automated defect detection in sewer closed circuit television images using histograms of oriented gradients and support vector machine,” Automation in Construction, Vol. 38, pp. 1-13, 2014.
[22] Hu, Y. J., Ku, T. H., Jan, R. H., Wang, K. C., Tseng, Y. C., and Yang, S. F., “Decision tree-based learning to predict patient controlled analgesia consumption and readjustment,” BMC medical informatics and decision making, Vol. 12, pp. 131, 2012.
[23] 吳欣儒，「資料探勘技術於病人疼痛自控裝置之應用與分析」，國立交通大學資訊科學與工程研究所碩士學位論文，2011年。
[24] 蔡鴻達，「照像模組鏡頭之雜光分析與對策」，國立虎尾科技大學光電與材料科技研究所碩士學位論文，2010年。
[25] Rahman, Z. U., Jobson, D. J., and Woodell, G. A., “Retinex processing for automatic image enhancement,” Journal of Electronic Imaging, Vol. 13, No. 1, pp. 100-110, 2004.
[26] 郭慶祥，「傳統光學製作與檢測」，國家實驗研究院儀器科技研究中心，第七十期，2005年。
[27] Khireddine, A., Benmahammed, K., and Puech, W., “Digital image restoration by Wiener filter in 2D case,” Advances in Engineering Software, Vol. 38, No. 7, pp. 513–516, 2007.
[28] 鐘國亮，「影像處理與電腦視覺(第四版)」，東華書局，台灣台北，2008。
[29] Gonzalez, R. G., and Woods, R. E., “Digital image processing 3rd edition,” Prentice Hall, Taiwan, Taipei, 2008.
[30] Hough, P. V. C, “Method and means for recognizing complex patterns,” U. S.Patent, 3069654, Dec. 18, 1962.
[31] Duda, R. O., and Hart, P. E., “Use of the Hough transformation to detect lines and curves in picture,” Commun. ACM, Vol. 15, No 1, pp.11-15, 1972.
[32] Shewhart, W. A., “Economic control of quality manufactured product,” Van Nostrand, New York, 1931.
[33] Cortes, C., and Vapnik, V., “Support-vector networks,” Machine Learning, Vol. 20, No. 3, pp. 273-297, 1995.
[34] Vapnik, V. N., “Statistical learning theory,” John Wiley & Sons, Inc., New York, 1998.
[35] Cover, T. M., “Geometrical and statistical properties of systems of linear inequalities with applications in pattern recognition,” IEEE Transactions Electronic Computer, Vol. 14, No. 3,pp. 326-334, 1965.
[36] Hsu, C. W., and Lin, C. J., “A comparison of methods for mul-ticlass support vector machines,” IEEE Transactions on Neural Networks, Vol. 13, No. 2, pp. 415-423, 2002.
[37] Fan, R. E., Chen, P. H., and Lin, C. J., “Working set selection using second order information for training support vector ma-chines,” Journal of Machine Learning Research, Vol. 6, pp. 1889-1918, 2005.
[38] 張智星，「MATLAB程式設計入門篇(第三版)」，碁峰資訊股份有限公司，台灣台北，2011年。
[39] 連國珍，「數位影像處理MATLAB」，儒林圖書公司，台灣台北，2007。
[40] http://www.csie.ntu.edu.tw/~cjlin/libsvm/