水下的影像辨識目前尚未被廣泛應用，原因是因為水下的能見度及色偏的問題。許多文獻使用不同的影像處理方法來改善辨識問題，但卻未討論先改善訓練資料。本篇研究利用提高訓練資料的可用度，以提升模組的辨識率。
本研究將利用現有最熱門的演算法Single Shot Detector (SSD)和MobileNets所結合的模型，搭配色彩校正(Color correction)及擴增(Augmentation)技術組成三種個案。每種個案訓練時，均以深度學習(Deep learning)為基底生成模型，利用水中光線稍微不足的區域，驗證及探討不同的個案。
實驗結果驗證，在辨識目標僅一種類別的前提下，經影像處理及不利用擴增技術所生成的模型，辨識效果係所有實驗裡表現最佳的。另外，當辨識目標經過白平衡處理，也可提升辨識效果。

Underwater image recognition has not been widely used because of underwater visibility and color cast. Many literatures use different image processing methods to improve the identification problem, but do not discuss improving the training data first. This study has improved the recognition rate of models by improving the availability of training data.
The study used the combination of the most popular algorithms, Single Shot Detector (SSD) and MobileNets, with color correction (white balance and dehazing) and augmentation techniques to form three cases. Each case is trained with a deep learning model. Different cases were verified and discussed in areas with insufficient light in the water.
Under the premise of identifying only one category, the experimental results verified that the combination of application performed by processed data plus non-augmentation technique can achieve the best results.. In addition, when using the model, the input image can be processed by white balance to improve the recognition rate.

[1] K. He, X. Zhang, S. Ren, and J. Sun, "Deep Residual Learning for Image Recognition," ArXiv e-prints, vol. 1512, Accessed on: December 1, 2015 Available: http://adsabs.harvard.edu/abs/2015arXiv151203385H
[2] D. L. Rizzini, F. Kallasi, F. Oleari, and S. Caselli, "Investigation of Vision-Based Underwater Object Detection with Multiple Datasets," International Journal of Advanced Robotic Systems, vol. 12, no. 6, p. 77, 2015/06/01 2015.
[3] C. L. Braun and S. N. Smirnov, "Why is water blue?," Journal of Chemical Education, vol. 70, no. 8, pp. 612-614, 1993.
[4] E. S. Fry, "Reply to criticisms of the Pope and Fry paper on pure water absorption made in a comment by Quickenden et al," Applied Optics, vol. 39, no. 31, pp. 5843-5846, 2000/11/01 2000.
[5] J. Perez, A. C. Attanasio, N. Nechyporenko, and P. J. Sanz, "A Deep Learning Approach for Underwater Image Enhancement," Cham, 2017, pp. 183-192: Springer International Publishing.
[6] J. S. Romero, L. M. Procel, L. Trojman, and D. Verdier, "Implementation and optimization of the algorithm of automatic color enhancement in digital images," in 2017 IEEE International Autumn Meeting on Power, Electronics and Computing (ROPEC), 2017, pp. 1-6.
[7] N. Limare, J. L. Lisani, J.-M. Morel, A. B. Petro, and C. Sbert, "Simplest Color Balance," IPOL Journal, vol. 1, 2011.
[8] J. Y. Chiang and Y. C. Chen, "Underwater image enhancement by wavelength compensation and dehazing," IEEE Trans Image Process, vol. 21, no. 4, pp. 1756-69, Apr 2012.
[9] H. Lu, Y. Li, and S. Serikawa, "Underwater image enhancement using guided trigonometric bilateral filter and fast automatic color correction," in 2013 IEEE International Conference on Image Processing, 2013, pp. 3412-3416.
[10] E. Jannik Bjerrum, "SMILES Enumeration as Data Augmentation for Neural Network Modeling of Molecules," ArXiv e-prints, vol. 1703, Accessed on: March 1, 2017 Available: http://adsabs.harvard.edu/abs/2017arXiv170307076J
[11] L. Perez and J. Wang, "The Effectiveness of Data Augmentation in Image Classification using Deep Learning," ArXiv e-prints, vol. 1712, Accessed on: December 1, 2017 Available: http://adsabs.harvard.edu/abs/2017arXiv171204621P
[12] J. Yao, "Investigation into underwater object recognition and tracking for the SAUC-E competition," Master, Computer Science, Bath, 2008.
[13] C. M. Barngrover, "Computer Vision Techniques for Underwater Navigation," Master, Computer Science, UNIVERSITY OF CALIFORNIA, 2010.
[14] R. Pérez-Alcocer, L. A. Torres-Méndez, E. Olguín-Díaz, and A. A. Maldonado-Ramírez, "Vision-Based Autonomous Underwater Vehicle Navigation in Poor Visibility Conditions Using a Model-Free Robust Control," Journal of Sensors, vol. 2016, pp. 1-16, 2016.
[15] X. W. Chen and X. Lin, "Big Data Deep Learning: Challenges and Perspectives," IEEE Access, vol. 2, pp. 514-525, 2014.
[16] H. Jun-yan, C. Yi-lin, W. Jing, and W. Xiao-xia, "Robust automatic white balance algorithm using gray color points in images," IEEE Transactions on Consumer Electronics, vol. 52, no. 2, pp. 541-546, 2006.
[17] B. Cai, X. Xu, K. Jia, C. Qing, and D. Tao, "DehazeNet: An End-to-End System for Single Image Haze Removal," IEEE Transactions on Image Processing, vol. 25, no. 11, pp. 5187-5198, 2016.
[18] K. B. Gibson, D. T. Vo, and T. Q. Nguyen, "An investigation of dehazing effects on image and video coding," IEEE Trans Image Process, vol. 21, no. 2, pp. 662-73, Feb 2012.
[19] K. He, J. Sun, and X. Tang, "Single Image Haze Removal Using Dark Channel Prior," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 33, no. 12, pp. 2341-2353, 2011.
[20] J.-H. Kim, W.-D. Jang, J.-Y. Sim, and C.-S. Kim, "Optimized contrast enhancement for real-time image and video dehazing," Journal of Visual Communication and Image Representation, vol. 24, no. 3, pp. 410-425, 2013.
[21] G. Meng, Y. Wang, J. Duan, S. Xiang, and C. Pan, "Efficient Image Dehazing with Boundary Constraint and Contextual Regularization," in 2013 IEEE International Conference on Computer Vision, 2013, pp. 617-624.
[22] M. Bengtsson, "Color adjustment of digital images of clothes for truthful rendering," Master, Computer science and engineering, Halmstad University, 2016.
[23] M. R. Boutell, J. Luo, X. Shen, and C. M. Brown, "Learning multi-label scene classification," Pattern Recognition, vol. 37, pp. 1757-1771, 2004.
[24] P. Domingos, "A few useful things to know about machine learning," Communications of the ACM, vol. 55, no. 10, p. 78, 2012.
[25] Y. LeCun and Y. Bengio, "Convolutional networks for images, speech, and time series," in The handbook of brain theory and neural networks, A. A. Michael, Ed.: MIT Press, 1998, pp. 255-258.
[26] Y. LeCun, L. e. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," in Proceedings of the IEEE, 1998, vol. 86, no. 11, pp. 2278-2324.
[27] A. Krizhevsky, I. Sutskever, and G. E. Hinton, "ImageNet classification with deep convolutional neural networks," presented at the Proceedings of the 25th International Conference on Neural Information Processing Systems - Volume 1, Lake Tahoe, Nevada, 2012.
[28] D. C. Cire et al., "Flexible, high performance convolutional neural networks for image classification," presented at the Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Two, Barcelona, Catalonia, Spain, 2011.
[29] M. v. Gerven and S. Bohte, Artificial Neural Networks as Models of Neural Information Processing. Frontiers, 2018.
[30] B. Schölkopf, A. Smola, and K. Müller, "Nonlinear Component Analysis as a Kernel Eigenvalue Problem," Neural Computation, vol. 10, no. 5, pp. 1299-1319, 1998.
[31] C. Youngmin and K. S. Lawrence, "Kernel Methods for Deep Learning," pp. 342--350, 2009.
[32] K. He, J. Sun, and X. Tang, "Guided image filtering," presented at the Proceedings of the 11th European conference on Computer vision: Part I, Heraklion, Crete, Greece, 2010.
[33] K. Tae Keun, P. Joon Ki, and K. Bong Soon, "Contrast enhancement system using spatially adaptive histogram equalization with temporal filtering," IEEE Transactions on Consumer Electronics, vol. 44, no. 1, pp. 82-87, 1998.
[34] R. H. Hahnloser, R. Sarpeshkar, M. A. Mahowald, R. J. Douglas, and H. S. Seung, "Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit," Nature, vol. 405, no. 6789, pp. 947-51, Jun 22 2000.
[35] M. Mohri and A. Rostamizadeh, Foundations of Machine Learning. The MIT Press, 2012.
[36] M. Riesenhuber and T. Poggio, "Hierarchical models of object recognition in cortex," Nature Neuroscience, Article vol. 2, p. 1019, 11/01/online 1999.
[37] D. Cireşan, U. Meier, and J. Schmidhuber, "Multi-column Deep Neural Networks for Image Classification," ArXiv e-prints, vol. 1202, Accessed on: February 1, 2012 Available: http://adsabs.harvard.edu/abs/2012arXiv1202.2745C
[38] Y. LeCun et al., "Backpropagation Applied to Handwritten Zip Code Recognition," Neural Computation, vol. 1, no. 4, pp. 541-551, 1989.
[39] S. Ren, K. He, R. Girshick, and J. Sun, "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks," IEEE Trans Pattern Anal Mach Intell, vol. 39, no. 6, pp. 1137-1149, Jun 2017.
[40] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You Only Look Once: Unified, Real-Time Object Detection," ArXiv e-prints, vol. 1506, Accessed on: June 1, 2015 Available: http://adsabs.harvard.edu/abs/2015arXiv150602640R
[41] W. Liu et al., "SSD: Single Shot MultiBox Detector," ArXiv e-prints, vol. 1512, Accessed on: December 1, 2015 Available: http://adsabs.harvard.edu/abs/2015arXiv151202325L
[42] A. G. Howard et al., "MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications," ArXiv e-prints, vol. 1704, Accessed on: April 1, 2017 Available: http://adsabs.harvard.edu/abs/2017arXiv170404861H
[43] M. Abadi et al., "TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems," ArXiv e-prints, vol. 1603, Accessed on: March 1, 2016 Available: http://adsabs.harvard.edu/abs/2016arXiv160304467A
[44] K. Simonyan and A. Zisserman, "Very Deep Convolutional Networks for Large-Scale Image Recognition," ArXiv e-prints, vol. 1409, Accessed on: September 1, 2014 Available: http://adsabs.harvard.edu/abs/2014arXiv1409.1556S
[45] C. Bishop, Pattern Recognition and Machine Learning, 1 ed. (Information Science and Statistics). Springer-Verlag New York, 2006.
[46] J. Hosang, R. Benenson, and B. Schiele, "Learning non-maximum suppression," ArXiv e-prints, vol. 1705, Accessed on: May 1, 2017 Available: http://adsabs.harvard.edu/abs/2017arXiv170502950H
[47] S. Ioffe and C. Szegedy, "Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift," ArXiv e-prints, vol. 1502, Accessed on: February 1, 2015 Available: http://adsabs.harvard.edu/abs/2015arXiv150203167I
[48] C. F. Bohren and D. R. Huffman, Absorption and Scattering of Light by Small Particles. Willey, 1983.
[49] D. C. Brown, "Decentering distortion of lenses," in Photogrammetric Engineering vol. 32, ed, 1966, pp. 444-462.
[50] N. Otsu, "A Threshold Selection Method from Gray-Level Histograms," IEEE Transactions on Systems, Man, and Cybernetics, vol. 9, no. 1, pp. 62-66, 1979.