在水下環境中，吸收與散射是造成影像品質下降的兩大主要議題，導致低對比以及色偏的問題產生，本論文旨在提出一個系統性的水下影像強化架構，針對不同影像衰退成因進行分析與解決，在第一個階段中，應用隨機森林概念來估測透射率，在訓練與估測的過程中，擷取RGB色彩通道、亮度、色彩差值、模糊程度和暗通道作為特徵值，為了面對多變而複雜的水下環境情況，透過集成學習能在估測透射率的表現上，達到更好的效果；在第二個階段中，我們透過顏色補償，並基於深度資訊適應性地進行對比強化，有效改善水下影像之視覺品質。
實驗結果顯示，我們所提出的演算法相較於其他方法，在主觀影像品質與客觀影像評估標準上皆有較好的表現。

Absorption and scattering are the two major distortion issues in underwater environment, leading to the low contrast and color cast problem. According to different factors leading degradation, this Thesis proposes a systematic framework for underwater image enhancement. First, the proposed method estimates transmission with random forest algorithm. RGB values, luminance, color difference, blurriness, and dark channel are regarded as features while training and estimating. To tackle with the various and changing conditions in underwater environment, the transmission can be selected accurately by the ensemble machine learning algorithm. Second, a modified color compensation and contrast enhancement algorithm based on depth information is proposed to improve the visual quality of underwater images.
The experiment results show that the proposed approach has better performance when compared with other methods in both the subjective visual quality and the objective measurement.

[1] K. He, J. Sun, and X. Tang, “Single image haze removal using dark channel prior,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 33, no. 12, pp. 2341-2353, Dec. 2011.
[2] Y.-T. Peng, X. Zhao, and P.C. Cosman, “Single Underwater Image Enhancement using Depth Estimation based on Blurriness,” in Proc. IEEE Int. Conf. on Imag. Process. (ICIP), pp. 4952-4956, Sep. 2015.
[3] A. Galdran, D. Pardo, and A. Picn, “Automatic red-channel underwater image restoration,” J. Vis. Commun. Image R., vol. 26, pp. 132-145, 2015.
[4] C.Y. Li, and J.C. Quo, “Single underwater image restoration by blue-green channels dehazing and red channel correction,” IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), pp. 1731-1735, 2016.
[5] R. Sathya, “Underwater image enhancement by dark channel prior,” International Conference on Electronics and Communication Systems (ICECS), pp1119-1123, 2015.
[6] H. Yang, P. Chen, C. Huang, Y. Zhuang and Y. Shiau, “Low complexity underwater image enhancement based on dark channel prior,” Int. Conf. Innov. in Bio-inspired Comput. and App. (IBICA), pp. 17-20, Dec. 2011.
[7] Min Han, Chao Chen, “Enhancing underwater image by dark channel prior and color correction,” Sixth International Conference on Information Science and Technology (ICIST), pp. 505-510, Dec. 2016.
[8] Hitam, M.S.; Yussof, W.N.J.H.W.; Awalludin, E.A.; Bachok, Z.,“Mixture contrast limited daptive histogram equalization for underwater image enhancement,” Computer Applications Technology (ICCAT), 2013 International Conference on , vol., no., pp.1,5, 20-22, 2013.
[9] X.Y. Fu, P.X. Zhuang“A retinex-based enhancing approach for single underwater image,” IEEE International Conference on Image Processing (ICIP), pp.4572-4576, 2014.
[10] J. Chiang, Y.-C. Chen, “Underwater image enhancement by wavelength compensation and dehazing,” IEEE Trans. Image Process. 21 (4) (2012) 1756–1769.
[11] S. Serikawa, H. Lu, “Underwater image dehazing using joint trilateral filter,” Comput. Electr. Eng. 40 (1) (2014) 41–50.
[12] L. Breiman. Manual on setting up, using, and understanding random forests v3.1, 2002.
[13] Liaw LA, Wiener M (2002). “Classification and Regression by randomForest.” R News, 2(3), pp.18–22.
[14] K. He, J. Sun, and X. Tang, “Guided image filtering,” IEEE Trans. Pattern Analysis and machine Intelligence, vol. 35, no. 6, pp. 1397-1409, Jun. 2013.
[15] Leo Breiman, Random Forests, Machine Learning, v.45 n.1, p.5-32, October 1 2001
[16] P. Geurts, D. Ernst, and L. Wehenkel. Extremely randomized trees. Machine Learning, 36(1):3-42, 2006.
[17] K. Zuiderveld, "Contrast Limited Adaptive Histogram Equalization", Graphics Gems IV, pp. 474-485
[18] R. Schettini, S. Corchs. Underwater Image Processing: State of the Art of Restoration and Image Enhancement Methods, EURASIP Journal on Advances in Signal Processing, Vol.2010, pp. 1-15, 2010.
[19] B. L. McGlamery, A Computer Model for Underwater Camera Systems, SPIE Ocean Optics, Vol. 208, pp. 221-231, 1979.
[20] P. Bouguer, Essai d’Optique Sur la Gradation de la Lumiere, Paris, France:Claude Jombert, 1729.
[21] E. Trucco and A. T. Olmos-Antillon, “Self-tuning underwater image restoration,” IEEE J. Ocean. Eng., vol. 31, no. 2, pp. 511–519, Apr. 2006.
[22] J. S. Jaffe, “Computer modeling and the design of optimal underwater imaging systems,” IEEE J. Ocean. Eng., vol. 15, no. 2, pp. 101–111, Apr. 1990.
[23] Yan-Tsung Peng and Pamela C. Cosman, “Underwater Image Restoration based on Image Blurriness and Light Absorption,” IEEE Trans. Image Process., vol.26, pp. 1579-1594, February 2017.
[24] Chongyi Li, Jichang Guo and Runmin Cong, “Underwater Image Enhancement by Dehazing with Minimum Information Loss and Histogram Distribution Prior,” IEEE Trans. Image Process., vol.25, pp. 5664-5677, September 2016.
[25] S. M. Pizer and E. P. Amburn and J. D. Austin and R. Cromartie and A. Geselowitz and T. Greer and B. T. H. Romeny and J. B. Zimmerman and K. Zuiderveld, Adaptive Histogram Equalization and Its Variations, Computer Vision, Graphics, and Image Processing, 39, pp. 355–368, 1987.
[26] K. Zuiderveld, Contrast Limited Adaptive Histogram Equalization, Graphics Gems I”, Academic Press, 1994 .
[27] Y. Y. Schechner and N. Karpel, “Recovery of underwater visibility and structure by polarization analysis,” IEEE Journal of Oceanic Engineering, 2005.
[28] Karen Panetta, Chen Gao, Sos Agaian, “Human-Visual-System-Inspired Underwater Image Quality Measures” IEEE J. Ocean. Eng., Digital Object Identifier 10.1109/JOE.2015.2469915
[29] Shen-Chuan Tai, Ting-Chou Tsai, and Jui-Chiang Wen: "Single Image Dehazing Based on Vector Quantization", International Journal of Computers and Applications, vol. 37, no. 3-4, 83-93 July 2016
[30] J. Bednar and T. L. Watt, “Alpha-trimmed means and their relationship to median filters,” IEEE Trans. Acoust. Speech Signal Process., vol. ASSP-32, no. 1, pp. 145–153, Feb. 1984.
[31] K. Panetta, S. Agaian, Y. Zhou, and E. J. Wharton, “Parameterized logarithmic framework for image enhancement,” IEEE Trans. Syst. Man Cybern. B, Cybern., vol. 41, no. 2, pp. 460–473, Apr. 2011.
[32] Ceriani, L., & Verme, P. (2012). The origins of the Gini index: Extracts from variabilità e mutabilità (1912) by corrado gini. Journal of Economic Inequality, 10, 421–443.