本應用模糊-類神經滑動控制器於被動式自動對焦系統之研究與驗證，係探討擷取物體影像後，運用清晰度值演算法，將影像清晰度數值化，再應用智慧型焦距點搜尋技術，找尋影像最大清晰度值之位置，使影像擷取器經由馬達移至最佳焦距點以擷取最清晰之影像。
清晰度值演算法分為空間域與頻域演算方式。本研究使用三種不同複雜度之紋理樣本，依序以空間域演算法之變異數法、最大梯度法及拉普拉斯能量法與頻域演算法之快速傅立葉轉換法分析彼此之差異性，其中最大梯度法具有最佳清晰度值運算之優點。
焦距點搜尋技術，係探討運用所提出之模糊-類神經滑動控制器，透過模糊控制器控制系統之非線性與不確定性，應用類神經網路之學習功能自動調整模糊歸屬函數，並結合滑動平面減少模糊控制規則庫之優點，此新搜尋技術與模糊滑動控制器比較，有較佳搜尋焦距點之效果。
本研究亦建置實務驗證機台，藉由攝影機擷取樣本影像，經由最大梯度法將其清晰度數值化，結合所提出之模糊-類神經滑動控制器驅動馬達，改變攝影機與樣本距離使擷取最清晰之樣本影像。經由實驗驗證，本智慧型自動對焦系統不但具有快速且精確之優點亦能擷取非平面物品表面之清晰影像，可增進自動化光學辨識與檢測之效益。

This study research and verify a passive auto-focusing system by using fuzzy-neural network sliding controller. The system acquires object image, uses sharpness algorithm to find the sharpness, employs the intelligent focus searching technique to search the location of the maximum sharpness, and moves the image capturing system by motor to the optimum focus in order to capture the sharpest image.
Sharpness algorithm includes spatial domain and frequency domain. This study tested three texture samples with different complexities, and employed variance method, gradient magnitude maximization and energy of Laplace method (spatial domain algorithm), and fast Fourier transform (frequency domain algorithm) to analyze the differences among the samples. Results showed that the gradient magnitude maximization provides the best result for the sharpness.
This study employed focus search technique to apply the proposed fuzzy-neural network sliding controller, use fuzzy controller to control the system nonlinearity and uncertainty, and employ the neural network learning function to automatically adjust the fuzzy membership function. The technique was combined with sliding surface to reduce the fuzzy control rule base. Compared with fuzzy sliding controller, this new search technique proved to have better focus searching effect.
This study also built a machine for verification, which captures the sample image using a camera, and computes the sharpness by gradient magnitude maximization. The fuzzy-neural network sliding controller drive motor was used to change the distance between the camera and the sample so as to capture the sharpest sample image. The experiment verified that this auto-focusing system can operate quickly and accurately, and capture sharp images of nonplanar object surface, which can improve the effectiveness of automatic optical recognition and inspection.

[1] S. K. Nayar, M. Watanabe, and M. Noguchi, “Real-time focus range sensor”, Fifth international conference on computer vision, pp. 995-1001, 1995.
[2] J. Widjaja and S. Jutamulia, “Wavelet transform-based autofocus camera systems”, Proceedings of the IEEE asia-pacific conference on circuits and systems, pp. 49-51, 1998.
[3] W. Kesseler and J. Fischer, “Analytical model of autofocus system eith CCD camera”, Sensors and camera systems for scientific, industrial, and digital photography applications, san jose, CA, USA, January 2000.
[4] J. Kautsky, J. Flusser, B. Zitová and S. Šimberová, “A new wavelet-based measure of image focus”, Pattern recognition letters, Vol. 23, pp. 785-1794, 2002.
[5] J. T. Huang, C. H. Shen, S. M. Phoong and H. Chen, “Robust measure of image focus in the wavelet domain”, International symposium on intelligent signal processing and communication systems, Hong Kong, pp. 157–160, 2005.
[6] S. Y. Lee, Y. Kumar, J. M. Cho, S. W. Lee and S.W. Kim, “Enhanced autofocus algorithm using robust focus measure and fuzzy reasoning”, IEEE trans. circuits syst. video technology, Vol. 18, No. 9, pp. 1237-1246, 2008.
[7] C. Y. Chen, R. C Hwang and Y. J. Chen, “A passive auto-focus camera control system”, Applied soft computing, Vol. 10, pp. 296- 303, 2010.
[8] J. He, R. Zhou and Z. Hong, “Modified fast climbing search auto- focus algorithm with adaptive step size searching technique for digital camera”, Consumer electronics, IEEE transactions on, Vol. 49, Issue. 2, pp. 257-262, 2003.
[9] H. C. Chang, T. M. Shih, N. Z. Chen and N. W. Pu, “A microscope system based on bevel- axial method auto-focus”, optics and lasers in engineering, Vol. 47, pp. 547-551, 2009.
[10] L. Tao, Y. Sihan, Z. Yong and W. Qinzhang, “Auto-focusing tech- nology for photoelectric measurement system”, 4th international symposium on advanced optical manufacturing and testing：optical test and measurement technology and equipment, Chengdu, China, 2009.
[11] J. Liu, X. Song, R. Han and H. Wang, “Autofocus method in digital holographic microscopy”, 4th international symposium on advanced optical manufacturing and testing：optical test and measurement technology and equipment, Chengdu, China, 2009.
[12] K. C. Lin, “Microscopic autofocusing using regional monotonous variations of multiple focal value measures”, Journal of electronic imaging, Vol. 19, No. 2, 023012, 2010.
[13] G. S. Beveridge and R. S. Schechter, “Optimization: theory and practice,” McGraw-Hill, New York, 1970.
[14] J. Baina, and J. Dublet, “Automatic focus and iris control for video cameras”, Fifth international conference on image processing and its applications, pp. 232-235, 1995.
[15] N. K. Chern, P. A. Neow, H. Marcelo, and J. Ang, “Practical issues in pixel-based autofocusing for machine vision”, Proceedings of the IEEE international conference on robotics and automation, Vol. 3, pp. 2791-2796, 2001.
[16] L. A. Zadeh, “Fuzzy sets”, Information and control, Vol. 8, pp. 338- 353, 1965.
[17] E. H. Mamdani and S. Assilian, “A fuzzy logic controller for a dynamic plant”, Int. J. man, maching study, Vol. 7, pp. 1-13, 1975.
[18] C. H. Hsu, Y. Lin and K. A. Ye, “Comparison of using proportional and servo valves on position control in a hydraulic servo system”, Tran sactions of the aeronautical and astronautical socieity of the republic of China, pp. 359-366, 1996.
[19] K. C. Cheok, K. Kobayashi, S. Scaccia and G. Scaccia, “A fuzzy logic-based smart automatic windshield wiper”, IEEE control system magazine, Vol. 16, pp. 28-34, 1996.
[20] C. F. Kuo and C. H. Chiu, “Auto-focus control of a CMOS image sensing module”, Journal of intelligent and fuzzy systems, Vol. 18, pp. 405-415, 2007.
[21] J. F. Shiu and C. M. Lin, “ Decoupled fuzzy controller designed with fuzzy sliding surface”, Automatic control conference, pp. 463-468, 2000.
[22] L. C. Hung and H. Y. Chung, “Decoupled sliding-mode with fuzzy- neural network controller for nonlinear system”, International journal of approximate reasoning, Vol. 46, pp. 74-97, 2007.
[23] N. K. Chern, P. A. Neow and M.H. Ang, “Practical issues in pixel- based autofocusing for machine vision,” Proceedings of the IEEE international conference on robotics and automation, Vol. 3, pp. 2791-2796, 2001.
[24] J. Baina, and J. Dublet, “Automatic focus and iris control for video cameras,” Fifth international conference on image processing and its applications, pp. 232-235, 1995.
[25] S. C. Hsu, C. H. Liu and N. J. Wang, “Fuzzy PI controller tuning for a linear permanent magnet synchronous motor drive”, The 27th annual conference of the IEEE industrial electronics society, pp. 1661-1666, 2001.
[26] M. N. Uddin, T. S. Radwan, M. A. Rahman and G. H. George, “Fuzzy logic based position control of permanent magnet synchronous motor”, 2000 canadian conference on Electrical and computer engineering, Vol. 1, pp. 93-97, 2000.
[27] V. I. Utkin, “Variable structure system with sliding mode,” IEEE trans. automatic control, Vol. 2, No. 2, pp. 212-222, 1977.
[28] V. I. Utkin, “Sliding modes and their application in variable structure system,” MIR moscow, 1978.
[29] I. C. Yeh, “Modeling chaotic two-dimensional mapping with fuzzy neuron networks,” Fuzzy sets and systems, pp. 421-427, 1999.
[30] J. S. R. Jang, ”ANFIS:adaptive network based fuzzy inference system”, IEEE trans. system, man, and cybernetics, Vol. 23(3), pp. 665-685, 1993.