本論文使用「光機電系統控制實驗室」歷年來研究之微夾持器，利用影像處理、物件影像分割和模糊識別的方式以取得物件於三維空間中的資訊，並且利用了加入了穩態特性的區域邊緣統計法(Regional Edge Statistics, RES)，發展具DSP之PC-based的三維空間中物件自動化微操縱之影像伺服控制，系統主要分為影像系統、微夾持器系統和搬運系統三大部份。
在三個子系統中，微夾持器系統為352×285×100μm大小的撓性微夾爪，材料為PU薄膜，為一個SMA致動器驅動的撓性微夾持器，夾持的物件大小約10~40μm，可搬運系統中所要求的物件。而在影像系統的部分，主要以TI DSP C6416為主軸，並且搭配VDB影像擷取卡以擷取影像，發展影像的演算法、物件影像分割與模糊識別演算法，利用即時資料交換(RTDX, Real-Time Data eXchange)讓DSP與IPC端做溝通，讓物件於三維空間中的資訊得以傳到電腦，並且利用RES達到影像閉迴路控制。最後是運動平台系統，該系統主要有三個平台，分別為微夾持器載具平台、載物平台與置物平台，構成一個4.0mm×3.8mm×3.64mm的運動空間，平台的解析度最大為1.3μm，最小可達0.5μm，並且能精準地定位與搬運。
本研究利用二組CCD取得物件於三維空間中的資訊，利用影像演算法成功的取得了物件於三維空間中的座標，並且成功地移動了 20μm~ 30μm的微細金線，利用加了穩態概念的區域邊緣統計法(Regional Edge Statistics, RES)達到影像閉迴路控制自動化微操縱系統，採用最模糊分類方法，成功的辨識物件。

The micro-compliant gripper is developed by“Opto-Mechatronic System Control Laboratory” in this thesis. The system use image processing, template image separate, and pattern recognition via fuzzy sets to get the information of object in 3D space. with the use of steady state in regional edge statistics (RES) algorithm, a visual servo for automatic micromanipulation of object in 3D space is developed by a PC-based system with DSP. There are three parts in the system：visual system, gripper system, and transportation system.
The gripper system is a compliant gripper with size of 352×285×100μm. It is made by PU film and uses SMA actuator to actuate the gripper, and it can grip the object with 10~40μm. The TI DSP C6416 and VDB card is utilized to develop image algorithm, template image separate, and pattern recognition via fuzzy sets for the visual system. The Real-Time Data eXchange (RTDX) is used to transfer the data between the DSP and IPC. The information of object can be transferred to computer and the system use RES to do the visual servoing control. The final part is transportation system. This system have three stages： motion stage, carry stage, and object stage. It is constructed to provide a motion space with 4.0mm×3.8mm×3.64mm. The resolution of the motion stage, with maximum positioning accuracy of 1.3μm and the minimum of 0.5μm is expected for precise positioning and taking object.
This thesis use two CCD to get the information of 3D space and use the image algorithm to get the 3D coordinates of the object. The system uses pattern recognition via fuzzy sets to find the object and can automatically transport a gold wire with diameter 20μm~30μm and length 2mm for micromanipulation.

[1] Y. Shirai, and H. Inoue, “Guidinf a robot by a visual feedback in assembling task,” Pattern Recognit., Vol. 5, pp. 99-108, 1973.
[2] J. Hill, and W. T. Park, “Real time control of a robot with a mobile camera,” in Proc. 9th ISIR, Washington, D.C., pp. 233-246, Mar. 1979.
[3] A. C. Sanderson, and L. E. Weiss, “Image-Based visual servo control using relational graph error signals,” in Proceedings of the IEEE International Confference on Cybernetics and Society, pp. 404-417, Oct. 1980.
[4] S. Hutchinson, G. D. Hager, and P. I. Corke, “A tutorial on Visual Servo Control,” IEEE Transaction on Robotics & Automation, Vol. 12, No. 5, pp. 651-670, Oct. 1996.
[5] Kragic D., and Christensen H. I., “Survey on Visual Servoing for Manipulation,” IEEE Transaction on Robotics & Automation, Vol. 15, No. 2, pp. 238-250, April. 1999.
[6] Anil K. Jain, P. W. Duin, and Jianchang Mao, “Statistical Pattern Recognition: A Review,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.22, No. 1, January 2000.
[7] Moghaddamzadeh A. and Bourbakis N., “A fuzzy region growing approach for segmentation of color images,” Pattern Recognition, Vol.30, No. 6, 867-881,1991.
[8] Zhu S. C. and Yuille A., “Region competition:unifying snakes, region growing, and Bayes/MDL for multiband image segmentation,” IEEE Trans. Pattern Analysis Mach, Vol.18, No. 9,884-990,1996.
[9] Farag A. A. and Delp E. J., “Edge linking by sequential search,” Pattern Recognition, Vol.28, No. 5, 611-633,1995.
[10] Iyengar S.S. and Deng W., “An efficient edge detection algorithm using relaxing labeling technique,” Pattern Recognition, Vol.28, No. 4, 519-536,1995.
[11] Chun D. N. and Yang H. S., “Robust image segmentation using genetic algorithm with a fuzzy measure,” Pattern Recognition, Vol.29, No. 7, 1195-1211,1996.
[12] C-J. Kim, etc., “Polysilicon microgripper,” 4th Technical Digest, IEEE Solid-State Sensor and Actuator Workshop, Pages: 48-51, June 1990.
[13] 張景堯，「形狀記憶合金驅動高分子微夾持系統之發展」，國立成功大學機械工程學系碩士論文，頁次：1-7，中華民國九十二年六月。
[14] 机啟成，「形狀記憶合金驅動生醫用高分子微夾持系統之發展」，國立成功大學機械工程學系碩士論文，頁次：2-8，中華民國九十三年七月。
[15] 施博偉，「形狀記憶合金驅動微夾持系統之應用」，國立成功大學機械工程學系碩士論文，頁次：1-8，中華民國九十四年七月。
[16] Dong-S Kwon, etc., “Microsurgical Telerobot System,” Proceeding of the IEEE International Conference in Intelligent Robots and Systems, Vol.2, pp. 945-950, Oct. 1998.
[17] K. Ikuta, ”Micro/Minature Shape Memory Alloy Actuator,” IEEE, 1999.
[18] S. B. Choi, Y. M. Han, J. H. Kim, C. C. Cheong, “Force Tracking Control of a Flexible Gripper future Shape Memory Alloy Actuator,” Mechatronics, November 2001.
[19] S. Aramaki, “Tube Type Micro Manipulator Using Shape Memory Alloy,”Sixth internal symposium on micro machine and human science, 1995.
[20] I. Roch, “Fabrication and Characterization of an SU-8 Gripper Actuated by a Shape Memory Alloy Thin Film,” Journal of Micromechanics and Microengineering, 2003.
[21] Whitney V., “Quasi-static assembly of compliantly supported rigid parts,” ASME J. Dyn. Systems Meas. Control 104, pp. 65-77, 1992.
[22] F. Fallside, etc., “A Prototype, Integrated, Cad-Based Robotic Assembly System,” IEEE , Vol.2, pp. 228-234, 1989.
[23] H. Woern, etc., “Flexible Microrobots for Micro Assembly Tasks,” Proceeding of the 2000 International Symposium on Micromechatronics and Human Science, pp. 135-143, Oct. 2000.
[24] Xudong Li, etc., “Development of Global Vision System for Biological Automatic Micro-Manipulation System,” Proceeding of the 2001 IEEE International Conference on Robotic & Automation, Seoul Korea, pp. 127-132, May 2001.
[25] Baidyk T. and Ernst Kussul, etc., “Application of neural classifier for flat image recognition in process of microdevice assembly,” Proceedings of the International Joint Conference on Neural Networks, pp. 12-17, 2002.
[26] Baidyk T., etc., “Flat image recognition in process of microdevice assembly,” Pattern Recognition Letters, Vol.25, pp. 107-118, 2004.
[27] Kenji Inoue, and Tatsuo Arai, etc., “Dexterous Micromanipulation Supporting Cell and Tissue Engineering,” Proceedings of the IEEE International Symposium on Micro-NanoMechatronics and Human Science, pp. 197-202, Nov 2005.
[28] Kemal Berk Yesin, and Bradley J. Nelson, “A CAD model based tracking system for visually guided microassembly,” J. of Robotica, Vol.23, pp. 409-418, 2005.
[29] Mehdi Ammi, and Vincent Fremont, etc., “ Flexible Microscope Calibration using Virtual Pattern for 3-D Telemicromanipulation,” IEEE International Conference on Robotics and Automation, pp. 3888-3893, April 2005.
[30] 張威弘，「視覺伺服微物件搬運自動化之發展」，國立成功大學機械工程學系碩士論文，頁次：21-22，中華民國九十三年七月。
[31] 林光彥，「以DSP實現圖形識別於微物件操縱系統之發展」，國立成功大學機械工程學系碩士論文，頁次：25-34，中華民國九十四年七月。
[32] 陳慶昌，「影像自動化微組裝工廠之發展」，國立成功大學機械工程學系碩士論文，中華民國九十五年六月。
[33] G. Woods原著，謬紹綱編譯，「數位影像處理」，2nd edition， 普林斯頓國際有限公司，2004年10月。
[34] J. C. Bezdek, IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. PAMI-2, No.1, pp. 1-8, January 1980.
[35] R. C. Miall, D. J. Weir, D. M. Wolpert and J. F. Stein, “Is the cerebellum a Smith predictor,” Journal of Motor Behavior, Vol. 25, No. 3, pp. 203-216, 1993.