以電子觀察員發想，研究如何自動判斷漁船甲板上是否有魚，以及是何魚種。本研究分兩步驟探討，第一步驟為使用少量資料做計算架構的設計與測試，第二步驟為使用大量資料的資料導向之架構改進。
第一步驟使用少量資料做計算架構的設計與測試，從漁船監視影片中，擷取魚體與非魚體的影像，作為魚體偵測與魚種分類的訓練資料，並探討如何設置摺積神經網路的結構，以及選擇何種影像輸入效果較佳。實驗結果顯示，若加上梯度強度影像作為輸入，能改善原本單以RGB 影像輸入的魚體偵測率，可由86.1% 提升至95%；在魚種辨識部份，則應分成三種「目標魚種、其他魚、無魚」進行辨識，會比分成兩種「目標魚種、非目標魚種」為佳，以鬼頭刀分類辨識為例，分為兩類的識別率僅73.6%，分為三種則為78.2%；而在摺積神經網路結構探討方面，測試了多種不同結構設定，其中，有無魚的最佳偵測率為96%，鬼頭刀分類最佳識別率為78.4%，鮪魚分類則為84.8%；此外，若與Torch函式庫比較，Torch 的鬼頭刀辨識率為93.7%，鮪魚辨識率則為92.5%。然而使用有無魚偵測率96%的結構掃描實際漁船圖片，誤判情況嚴重。
第二步驟使用大量資料做進一步改善，首先收集更多魚體與非魚體資料，使用Torch的CNN函式庫，針對無魚更加詳細的分類，並對無魚的分類與收集進行改善，成功改善少量資料掃描圖片的嚴重誤判情形，第二步驟的結構比較方面比較兩種，第一種為大圖深結構與小圖淺結構，第二種為輸入有無Sobel梯度強度影響。魚體偵測魚體的辨識率最高為85%，無魚的辨識率最高為99%。魚種辨識方面，鮪魚辨識最佳成功率為83%。

In order to investigate fish detection and recognition, we choose the method of convolutional neural network. This research has two parts. The first part using small amount of data to build and test computing architecture. The Second part using large amounts of data to improve architecture based on data-driven.
In the first part, we capture fish and non-fish image from the video on vessel. Considering how to build architecture of convolutional neural network and which image has better effect. Result of the experiment shows that adding gradient strength on input layer can improve fish detection rate to 95%; In fish detection, there are five kinds of result: three labels fishes, other fish and non-fish. The result is better than two labels include target fish and non-target fish. Fish recognition rate of dolphin is 73.6% in two targets and 78.2% in five targets. We build several architectures. The best fish detection rate is 96% and the best recognition rate is 92.5% in tuna and 93.7% in dolphin. Using the best fish detection CNN to detect images on real vessel still have a lot of false alarms.
In second part, we collect more images and have more output labels of non-fish, which reduces fish detection false alarm. We also build several architectures in second parts. The best fish detection rate is 85% and the best detection rate is 99% in non-fish and 83% in tuna.

[1] J. Bonney, K. McGauley, and A. G. D. Bank, "Testing the use of electronic monitoring to quantify at-sea halibut discards in the central Gulf of Alaska rockfish fishery," Alaska Groundfish Data Bank, Kodiak, Alaska, 2008.
[2] D. Chan, S. Hockaday, R. Tillett, and L. Ross, "A trainable n-tuple pattern classifier and its application for monitoring fish underwater," in Image Processing And Its Applications, 1999. Seventh International Conference on (Conf. Publ. No. 465), pp. 255-259., 1999
[3] R. Collobert, K. Kavukcuoglu, and C. Farabet, "Torch7: A matlab-like environment for machine learning," in BigLearn, NIPS Workshop, 2011.
[4] C.-L. Hsieh, H.-Y. Chang, F.-H. Chen, J.-H. Liou, S.-K. Chang, and T.-T. Lin, "A simple and effective digital imaging approach for tuna fish length measurement compatible with fishing operations," Computers and Electronics in Agriculture, vol. 75, pp. 44-51., 2011.
[5] A. Krizhevsky, I. Sutskever, and G. E. Hinton, "Imagenet classification with deep convolutional neural networks," in Advances in neural information processing systems, pp. 1097-1105., 2012
[6] S. Lawrence, C. L. Giles, A. C. Tsoi, and A. D. Back, "Face recognition: A convolutional neural-network approach," IEEE transactions on neural networks, vol. 8, pp. 98-113., 1997.
[7] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," Proceedings of the IEEE, vol. 86, pp. 2278-2324., 1998.
[8] D. Lee, S. Redd, R. Schoenberger, X. Xu, and P. Zhan, "An automated fish species classification and migration monitoring system," in Industrial Electronics Society, 2003. IECON'03. The 29th Annual Conference of the IEEE, pp. 1080-1085., 2003
[9] D.J. Lee, R. B. Schoenberger, D. Shiozawa, X. Xu, and P. Zhan, "Contour matching for a fish recognition and migration-monitoring system," in Optics East, pp. 37-48., 2003
[10] J. H. Lee, M.-Y. Wu, and Z.-C. Guo, "A tank fish recognition and tracking system using computer vision techniques," in Computer Science and Information Technology (ICCSIT), 2010 3rd IEEE International Conference on, pp. 528-532, 2010
[11] H. McElderry, M. J. Pria, M. Dyas, and R. McVeigh, "A pilot study using EM in the hawaiian longline fishery," 2010
[12] K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition," arXiv preprint arXiv:1409.1556, 2014
[13] C. Spampinato, D. Giordano, R. Di Salvo, Y.-H. J. Chen-Burger, R. B. Fisher, and G. Nadarajan, "Automatic fish classification for underwater species behavior understanding," in Proceedings of the first ACM international workshop on Analysis and retrieval of tracked events and motion in imagery streams, pp. 45-50, 2010
[14] M. Szarvas, A. Yoshizawa, M. Yamamoto, and J. Ogata, "Pedestrian detection with convolutional neural networks," in IEEE Proceedings. Intelligent Vehicles Symposium, 2005., pp. 224-229., 2005.
[15] D. White, C. Svellingen, and N. Strachan, "Automated measurement of species and length of fish by computer vision," Fisheries Research, vol. 80, pp. 203-210., 2006
[16] H. Yao, Q. Duan, D. Li, and J. Wang, "An improved K-means clustering algorithm for fish image segmentation," Mathematical and Computer Modelling, vol. 58, pp. 790-798., 2013
[17] B. Zion, V. Alchanatis, V. Ostrovsky, A. Barki, and I. Karplus, "Real-time underwater sorting of edible fish species," Computers and Electronics in Agriculture, vol. 56, pp. 34-45., 2007
[18] 吳俊樓，“運用影像處理技術擷取延繩釣揚繩作業影片中之漁獲資訊”，碩士論文，國立成功大學，2012。
[19] 陳飛宏，“鮪釣船觀察員自動攝影系統之開發”，碩士論文，國立屏東科技大學，2007。