近年來，影像除霧的問題被廣泛的探討，當在戶外環境拍照時，空氣中的介質引起光的衰減並導致影像品質的降低，尤其對於朦朧的環境更為明顯。影像品質的降低結果將造成資訊的遺失，從而阻礙了影像辨識系統去識別物件的分析。因此，對於後續處理的需求，去除有霧影像是可以提供解決問題之參考。影像預處理－除霧技術將扮演著極為重要角色並盡可能的恢復其影像品質。
本文主要分為兩大部分。第一部份，首先我們提出了模糊推論系統及權重估算的方法來解決其影像除霧的問題，但由於模糊推論系統是根據專家經驗或是大量數據分析並藉由手設計模擬出法則，對於模糊推論法則的數量是固定的，準確上亦也產生不精確的推論估測。因此，在第二部分中，我們提出一個遞迴式模糊小腦模型控制器模組及其線上學習演算法。此演算法包含架構學習及參數學習，架構學習是藉由熵的量測決定是否要增長一個新的法則，參數學習是使用倒傳遞演算法來調整網路上的所有參數。
最後，將提出的兩個機器學習方法及其相關演算法應用於解決各種影像除霧問題上。我們將與其他方法比較，以證實所提出的兩個方法之有效性。

In recent years, the image dehazing issue has been widely discussed. During photography in an outdoor environment, the medium in the air causes light attenuation and reduce image quality; these impacts are especially obvious in a hazy environment. Reduction of image quality results in the loss of information, which hinders image recognition systems to identify objects in the image. Removal of haze can provide a reference for subsequent image processing for specific requirements. Notably, image dehazing technology is used to maintain image quality during preprocessing.
This dissertation presents machine learning methods for image haze removal and consists of two major parts. In the first part, a fuzzy inference system (FIS) model is presented. Users of this model can customize designs to generate applicable fuzzy rules from expert knowledge or data. The number of fuzzy rules is fixed. In addition, the FIS model requires substantial amounts of data and expertise; even if the model is used to develop a fuzzy system, the image output of that system may suffer from a loss of accuracy. Therefore, in the second part of this dissertation, a recurrent fuzzy cerebellar model articulation controller (RFCMAC) model with a self-evolving structure and online learning is presented to improve the FIS model. The recurrent structure in an RFCMAC is formed with internal loops and internal feedback by feeding the rule firing strength of each rule to other rules and to itself. A Takagi-Sugeno-Kang (TSK) type is used in the consequent part of the RFCMAC. The online learning algorithm consists of structure and parameter learning. The structure learning depends on an entropy measure to determine the number of fuzzy rules. The parameter learning, based on back-propagation, can adjust the shape of the membership function and the corresponding weights of the consequent part. This dissertation describes, the proposed machine learning methods and its related algorithm, applies them to various image dehazing problems, and analyzes the results to demonstrate the effectiveness of the proposed methods.

[1] D. Brulin, Y. Benezeth, and E. Courtial, “Posture recognition based on fuzzy logic for home monitoring of the elderly,” IEEE Transactions on Information Technology in Biomedicine, vol. 16, no. 5, pp. 974–982, Sep. 2012.
[2] H. H. Kim, D. J. Kim, and K. H. Park, “Robust elevator button recognition in the presence of partial occlusion and clutter by specular reflections,” IEEE Transactions on Industrial Electronics, vol. 59, no. 3, pp. 1597–1611, Mar. 2012.
[3] S. Walk, N. Majer, K. Schindler, and B. Schiele, “New features and insights for pedestrian detection,” in Proceeding of the 2010 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1030–1037, Jun. 2010.
[4] J. C. McCall and M. M. Trivedi, “Video-based lane estimation and tracking for driver assistance: survey, system, and evaluation,” IEEE Transactions on Intelligent Transportation Systems, vol. 7, no. 1, pp. 20–37, Mar. 2006.
[5] S. Kamijo, Y. Matsushita, K. Ikeuchi, and M. Sakauchi, “Traffic monitoring and accident detection at intersections,” IEEE Transactions on Intelligent Transportation Systems, vol. 1, no. 2, pp. 108–118, Jun. 2000.
[6] J. A. Stark, “Adaptive image contrast enhancement using generalizations of histogram equalization,” IEEE Transactions on Image Processing, vol. 9, no. 5, pp. 889–896, May. 2000.
[7] Z. Rahman, D. J. Jobson, and G. A. Woodell, “Retinex processing for automatic image enhancement,” Journal of Electronic Imaging, vol. 13, no. 1, pp. 100–110, Jan. 2004.
[8] P. Scheunders, “A multivalued image wavelet representation based on multiscale fundamental forms,” IEEE Transactions on Image Processing, vol. 10, no. 5, pp. 568–575, May. 2002.
[9] C. O. Ancuti, C. Ancuti, C. Hermans and P. Bekaert, “A Fast Semi-inverse Approach to Detect and Remove the Haze from a Single Image,” in Proceeding of the 2010 Asian Conference on Computer Vision, pp. 501–514, Nov. 2010.
[10] J. P. Oakley, B. L. Satherley, “Improving image quality in poor visibility conditions using a physical model for contrast degradation,” IEEE Transactions on Image Processing, vol. 7, no. 2, pp. 167–179, Feb. 1998.
[11] K. K. Tan, J. P. Oakley, “Physics-based approach to color image enhancement in poor visibility conditions,” Journal of the Optical Society of America A, vol. 18, no. 10, pp. 2460–2467, Oct. 2001.
[12] S. G. Narasimhan, and S. K. Nayar, “Contrast restoration of weather degraded images,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, no. 6, pp. 713–724, Jun. 2003.
[13] Y. Y. Schechner, S. G. Narasimhan, and S. K. Nayar, “Polarization based vision through haze,” Applied Optics, vol. 42, no. 3, pp. 511–525, Jan. 2003.
[14] P. S. Pandian, M. Kumaravel, and M. Singh, “Multilayer imaging and compositional analysis of human male breast by laser reflectometry and Monte Carlo simulation,” Medical & Biological Engineering & Computing, vol. 47, no. 11, pp. 1197–1206, Oct. 2009.
[15] S. Shwartz, E. Namer, and Y. Schechner, “Blind haze separation,” in Proceeding of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1984–1991, 2006.
[16] Y. Schechner, S. Narasimhan, and S. Nayar, “Instant dehazing of images using polarization,” in Proceeding of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 325–332, 2001.
[17] N. Hautiere, J. P. Tarel, and D. Aubert, “Towards fog-free in-vehicle vision systems through contrast restoration,” in Proceeding of the 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1–8, 2007.
[18] J. Kopf, B. Neubert, B. Chen, M. Cohen, D. Cohen-Or, O. Deussen, M. Uyttendaele, and D. Lischinski, “Deep photo: model-based photograph enhancement and viewing,” ACM Transactions on Graphics, vol. 27, no. 5, pp. 1–10, Dec. 2008.
[19] Y. Schechner, and Y. Averbuch, “Regularized image recovery in scattering media,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 29, no. 9, pp. 1655–1660, Sep. 2007.
[20] E. Namer, S. Shwartz, and Y. Schechner, “Skyless polarimetric calibration and visibility enhancement,” Optics Express, vol. 17, no. 2, pp. 472–493, Jan. 2009.
[21] R. Fattal, “Single image dehazing,” ACM Transactions on Graphics, vol. 27, no. 3, Aug. 2008.
[22] R. T. Tan, “Visibility in bad weather from a single image,” in Proceeding of the 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1–8, 2008.
[23] K. He, J. Sun, and X. Tang, “Single image haze removal using dark channel prior,” in Proceeding of the 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1956–1963, 2009.
[24] J. P. Tarel and N. Hautiere, “Fast visibility restoration from a single color or gray level image,” in Proceeding of the 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2201–2208, 2009.
[25] K. Nishino, L. Kratz, and S. Lombardi, “Bayesian defogging,” International Journal of Computer Vision, vol. 98, no. 3, pp. 263–278, Jul. 2012.
[26] A. Levin, D. Lischinski, and Y. Weiss, “A closed form solution to natural image matting,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 30, no. 2, pp. 228–242, Feb. 2008.
[27] K. Gibson, and T. Nguyen, “An analysis of single image defogging methods using a color ellipsoid framework,” EURASIP Journal on Image and Video Processing, vol. 1, no. 37, Jul. 2013.
[28] R. Fattal, “Dehazing Using Color-Lines,” ACM Transactions on Graphics, vol. 34, no. 1, Nov. 2014.
[29] C. O. Ancuti, and C. Ancuti, “Single Image Dehazing by Multi-Scale Fusion,” IEEE Transactions on Image Processing, vol. 22, no. 8, pp. 3271–3282, Jan. 2013.
[30] H. B. Liu, J. Yang, Z. P. Wu, and Q. N. Zhang, “Fast Single Image Dehazing Based on Image Fusion,” Journal of Electronic Imaging, vol. 24, no. 1, pp. 013020-1–013020-10, Feb. 2015.
[31] C. Xianzhong, and K. G. Shin, “Direct control and coordination using neural networks,” IEEE Transactions on Systems, Man and Cybernetics, vol. 23, no. 3, pp. 686–697, Jun. 1993.
[32] S. Wu, and KYM. Wong, “Dynamic overload control for distributed call processors using the neural network method,” IEEE Transactions on Neural Networks, vol. 9, no. 6, pp. 1377–1387, Nov. 1998.
[33] T. Yamada, and T. Yabuta, “Dynamic system identification using neural networks,” IEEE Transactions on Systems, Man and Cybernetics, vol. 23, no. 1, pp. 204–211, Feb. 1993.
[34] SW. Lu, and T. Basar, “Robust nonlinear system identification using neural-network models,” IEEE Transactions on Neural Networks, vol. 9, no. 3, pp. 407–429, May 1998.
[35] S. K. Nair, and J. Moon, “Data storage channel equalization using neural networks,” IEEE Transactions on Neural Networks, vol. 8, no. 5, pp. 1037–1048, Sep. 1997.
[36] C. You, and D. Hong, “Nonlinear blind equalization schemes using complex-valued multilayer feedforward neural networks,” IEEE Transactions on Neural Networks, vol. 9, no. 6, pp. 1442–1455, Nov. 1998.
[37] Rajesh K. Agrawal, and Narendra G. Bawane, “Multiobjective PSO based adaption of neural network topology for pixel classification in satellite imagery,” Applied Soft Computing, vol. 28, pp. 217–225, Dec. 2015.
[38] J. G. Wang, S. C. Tai, and C. J. Lin, “A Novel Interactively Recurrent Self-Evolving Fuzzy CMAC and Its Classification Applications,” International Journal of Computational Intelligence and Applications, vol. 14, no. 3, pp. 1550019-1 - 1550019-19, Sept. 2015.
[39] L. Ma, and K. Khorasani, “Facial expression recognition using constructive feedforward neural networks,” IEEE Transactions on Systems, Man and Cybernetics, Part B: Cybernetics, vol. 34, no. 3, pp. 1588–1595, Jun. 2004.
[40] S. C. Kuo, C. J. Lin, and J. R. Liao, “3D Reconstruction and Face Recognition Using Kernel-Based ICA and Neural Networks,” Expert Systems with Applications, vol. 38, no. 5, pp. 5406–5415, May 2011.
[41] T. H. Oong, and N.A.M. Isa, “Adaptive Evolutionary Artificial Neural Networks for Pattern Classification,” IEEE Transactions on Neural Networks, vol. 22, no. 11, pp. 1823–1836, Nov. 2011.
[42] D. L. Peng and T. J. Wu, “A Generalized Image Enhancement Algorithm Using Fuzzy Sets and Its Application,” in Proceedings of the 2002 IEEE Conference on Machine Learning and Cybernetics, pp. 820–823, 2002.
[43] Y. S. Yang, D. K. Park, H. C. Kim; M. H. Choi, and J. Y. Chai, “Automatic identification of human helminth eggs on microscopic fecal specimens using digital image processing and an artificial neural network,” IEEE Transactions on Biomedical Engineering, vol. 48, no. 6, pp. 718–730, Jun. 2001.
[44] C. F. Wu, and C. J. Lin, “Digital Image Stabilization Using a Functional Neural Fuzzy Network,” International Journal of Innovative Computing, Information and Control, vol. 9, no. 1, pp. 99–109, Jan. 2013.
[45] J. G. Wang, S. C. Tai, and C. J. Lin, “Image haze removal using a hybrid of fuzzy inference system and weighted estimation,” Journal of Electronic Imaging, vol. 24, no. 3, pp. 033027-1 - 033027-13, June 2015.
[46] J. S. Albus, “A new approach to manipulator control: The cerebellar model articulation controller (CMAC),” Journal of Dynamic Systems, Measurement, and Control, vol. 97, no. 3, pp. 220–227, Sep. 1975.
[47] J. S. Albus, “Data storage in the cerebellar model articulation controller (CMAC),” Journal of Dynamic Systems, Measurement, and Control, vol. 97, no. 3, pp. 228–233, Sep. 1975.
[48] Z. J. Lee, Y. P. Wang, and S. F. Su, “A genetic algorithm based robust learning credit assignment cerebellar model articulation controller,” Applied Soft Computing, vol. 4, no. 4, pp. 357–367, Sep. 2004.
[49] S. F. Su, Tao Ted, and T. H. Huang, “Credit assigned CMAC and its application to online learning robust controllers,” IEEE Transactions on Systems, Man, Cybernetics, Part B: Cybernetics, vol. 33, no. 3, pp. 202–213, Apr. 2003.
[50] Y. G. Leu, C. M. Hong, Z. R. Chen, and J. H. Liao, “Compact cerebellar model articulation controller for ultrasonic motors,” International Journal of Innovative Computing, Information and Control, vol. 6, no. 12, pp. 5539–5552, Dec. 2010.
[51] S. Commuri, and F. L. Lewis, “CMAC neural networks for control of nonlinear dynamical systems: structure, stability, and passivity,” Automatics, vol. 33, no. 4, pp. 635–641, Apr. 1997.
[52] J. Wu, and F. Pratt, “Self-organizing CMAC neural networks and adaptive dynamic control,” in Proceeding of the 1999 IEEE International Symposium on Intelligent Control/Intelligent Systems and Semiotics, pp. 259–265, 1999.
[53] K. S. Hwang, and C. S. Lin, “Smooth trajectory tracking of three-link robot: a self-organizing CMAC approach,” IEEE Transactions on Systems, Man, Cybernetics, Part B: Cybernetics, vol. 28, no. 5, pp. 680–692, Oct. 1998.
[54] H. M. Lee, C. M. Chen, and Y. F. Lu, “A self-organizing HCMAC neural-network classifier,” IEEE Transactions on Neural Networks, vol. 14, no. 1, pp. 15–27, Jan. 2003.
[55] C. C. Jou, “A fuzzy cerebellar model articulation controller,” in Proceeding of the 1992 IEEE International Conference on Fuzzy Systems, pp. 1171–1178, 1992.
[56] S. H. Lane, and J. Militzer, “A comparison of five algorithm for the training of CMAC memories for learning control systems,” International Federation of Automatic Control, vol. 28, no. 5, pp. 1027–1035, Sep. 1992.
[57] C. S. Lin, and C. K. Li, “A new neural network structure composed of small CMACs,” in proceeding of the 1996 IEEE Conference on Neural Systems, pp. 1777–1783, 1996.
[58] D. S. Reay, “CMAC and B-spline neural networks applied to switched reluctance motor torque estimation and control,” The 29th Annual Conference of the IEEE Industrial Electronics Society, pp. 323–328, 2003.
[59] S. Chen, and D. Zhangm, “Robust image segmentation using FCM with spatial constraints based on new kernel-induced distance measure,” IEEE Transactions on Systems, Man and Cybernetics, Part B: Cybernetics, vol. 34, no. 4, pp. 1907–1916, Aug. 2004.
[60] J. S. Jang, “ANFIS: Adaptive-Network-Based Fuzzy Inference System,” IEEE Transactions on Systems, Man and Cybernetics, vol. 23, pp. 665–685, 1993.
[61] C. F. Juang, and C. T. Lin, “An On-Line Self-Constructing Neural Fuzzy Inference Network and Its Applications,” IEEE Transactions on Fuzzy Systems, vol. 6, no. 1, pp. 12–31, Feb. 1998.
[62] H. Koschmieder, “Theorie der Horizontalen Sichtweite,” in Beitrage zur Physik der Freien Atmosphare. Munich, Germany: Keim & Nemnich, vol. 12, pp. 171–181, 1924.
[63] E. J. McCartney, “Optics of the Atmosphere: Scattering by Molecules and Particles,” New York, John Wiley and Sons, 1976.
[64] Zadeh, A. Lotfi, “Fuzzy sets,” Information and Control, vol. 8, pp. 338–353, 1965.
[65] Zadeh, A. Lotfi, “Fuzzy logic and the calculus of fuzzy if-then rules,” in Proceeding of the 22nd IEEE International Symposium on Multiple-Valued Logic, May 1992.
[66] N. Hautiere, J. P. Tarel, D. Aubert, and É. Dumont, “Blind Contrast Restoration Assessment by Gradient Ratioing at Visible Edges,” Image Analysis Stereology, vol. 27, no. 2, pp. 87–95, 2008.
[67] X. Zhang, and B. A. Wandell, “Color Image Fidelity Metrics Evaluated Using Image Distortion Maps,” Signal Processing, vol. 70, no. 3, pp. 201–214, 1998.