觀察國際間近年研究魚類主題以來，絕大部分都以辨識海洋景觀魚類為主要研究方向，較少研究是以辨識大型經濟魚類做為主題，因此本論文針對台灣近海之四種鮪魚，透過對鮪魚外觀特徵辨識，達成鮪魚和其它十九種非鮪魚的魚類辨識。
本論文在訓練階段時將魚部位手動切割開並個別訓練其對應之分類器(classifier)，並以各魚鰭部位之HOG descriptors個別訓練其對應之分類器(classifier)，增加分類器對於局部影像特徵的辨識能力。辨識階段以本論文提出之二值投影法(binary projection)將魚類身體外觀三種特徵切割出，再透過Histogram of Oriented Gradients (HOG)將切割後的部位影像抓出其特徵描述子(descriptor)，將其結果輸入至訓練階段所得之三種支持向量機分類器(support vector machine)，在最後階段時，則整合三個(第一背鰭、第二背鰭、尾鰭)支持向量機分類結果透過投票(majority voting)機制決定是否為所要辨識的鮪魚種類。實驗結果顯示，四種鮪魚之平均辨識率約為72%，若只採用第二背鰭分類器，則辨識率可上升至80%。

In recent years, most fish recognition algorithm focus on recognizing aquarium fish rather than large commercial fishes. Thus, this thesis focuses on 4 species of tuna in adjacent seas of Taiwan. Through recognizing features of appearance of tuna, the proposed scheme can differentiate 4 species of tuna from 19 species of non-tuna fish.
At the training stage, this thesis segments fish fins manually and train SVM classifiers using the HOG descriptors. Based on the local image features, the method can improve recognition accuracy. In the test stage, this paper proposes to use binary projection for part segmentation. Descriptors of histogram of oriented gradients of three fins are the input of SVM classifiers and the classification results are majority voted for final decisions. Tests show that the recognition accuracy is around 72%. If the classification decision only depends on the feature of the second dorsal fin, the recognition accuracy is around 80%.

[1] Y. Nishida, U. Tamaki, T. Hamatsu, K. Nagahashi, S. Inaba, and T. Nakatani, “Fish Recognition Method using Vector Quantization Histogram for Investigation of Fishery Resources,” in Proc. Oceans - St. John's, St. John's, NL, pp. 1-5, Sept. 2014.
[2] P. X. Huang, B. J. Boom, and R. B. Fisher, “GMM improves the reject option in hierarchical classification for fish recognition,” in Proc. IEEE Winter Conference on Applications of Computer Vision, pp.371-376, March 2014.
[3] 顏寧.(2013). 記錄3.6%黑鮪魚悲歌[Online].Available: http://www.greenpeace.org/taiwan/zh/magazines/issue04/document/
[4] F. Storbeck, and B. Daan, “Fish species recognition using computer vision and a neural network,” Fisheries Research, vol. 51, no. 1, pp. 11-15, Apr. 2001.
[5] W. P. Lee, M. A. Osman, A. Z. Talib, J. C. Burie, J. M. Ogier, K Yahya, J. Mennesson, “Recognition of fish based on generalized color Fourier descriptor,” in Proc. Science and Information Conference , pp. 680-686, July 2015.
[6] 邵廣昭.(2016). 台灣魚類資料庫 [Online]. Available: http://fishdb.sinica.edu.tw/chi/home.php
[7] Stanford Vision Lab. 2014). ImageNet [Online]. Available: http://www.image-net.org/
[8] J. Hu, D Li, Q. Duan, Y. Han, G. Chen, and X. Si, “Fish species classification by color, texture and multi-class support vector machine using computer vision,” Computers and Electronics in Agriculture, vol. 88, pp.133-140, Oct. 2012.
[9] R. M. Haralick, K. Shanmugam, and I. Dinstein, “Textural features for image classitication,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 3, no.6, pp. 610-621, Nov. 1973.
[10] M. C. Chuang, J. N. Hwang, F. F. Kuo, M. K. Shan, and K. Williams, “ Recognizing live fish species by hierarchical partial classification based on the exponential benefit,” in Proc. IEEE International Conference on Image Processing, ICIP, Paris, pp. 5232-5236, Oct 2014.
[11] B.E. Boser, I. Guyon, and V. Vapnik, “A training algorithm for optimal margin classifiers," in Proc. ACM Conference on Learning Theory, pp. 144-152, July 1992.
[12] A. W. Moore. (2001). “Support Vector Machines”. [Online]. Available: http://www.autonlab.org/tutorials/svm15.pdf. File: svm15.pdf
[13] C. J. C. Burges, “A tutorial on support vector machines for pattern recognition,” Data mining and knowledge discovery, vol. 2, no. 2, pp.121-167, Jan. 1998.
[14] Smola, J. Alex, and S. Bernhard, “A tutorial on support vector regression,” Statistics and Computing, vol. 14, no. 3, pp. 199-222, Aug. 2004.
[15] N. Dalal and B.Triggs, “Histograms of Oriented Gradients for Human Detection,” in Proc. IEEE International Conference on Computer Vision and Pattern Recognition, vol. 1, pp.886-893, June 2005.
[16] G. Hoffmann, “Interpolations for Image Warping,” University of Applied Sciences in Emden. 2013
[17] Chih-Chung Chang and Chih-Jen Lin, LIBSVM : a library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2:27:1--27:27, 2011. Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm
[18] C. W. Hsu, C. C. Chang, and C. J. Lin (2016). “A Practical Guide to Support Vector Classification”. [Online]. Available: https://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf. File: guide.pdf
[19] N. Otsu, “A threshold selection method from gray-level histograms,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 9, no.1, pp. 62-66, Jan. 1979.
[20] D. M. W. Powers, “Evaluation: from precision, recall and F-measure to ROC,” Journal of Machine Learning Technologies, vol.2, no. 1, pp. 37-63, Dec. 2007