Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/97802
標題: 應用卷積類神經網路於鵝隻圖像辨識之研究
Study on Goose Image Recognition Using Convolutional Neural Networks
作者: 謝承興
Cheng-Hsing Hsieh
關鍵字: 
機器學習
圖型識別
goose
machine learning
pattern recognition
引用: [1] 行政院農業委員會。2005。台灣農家要覽-畜牧篇。第三版。臺北:豐年社。 [2] 行政院農業委員會。2018。畜禽產品統計資料庫。台北:行政院農業委員會。網址:http://agrstat.coa.gov.tw/sdweb/public/inquiry/InquireAdvance.aspx上網日期:2018-3-3。 [3] 李聯旺、廖珗洲、謝政勳。2012。人工智慧:智慧型系統導論。第三版。臺北:全華圖書。 [4] 林旻蓉、張伸彰、賈玉祥、鄭裕信、範揚廣。2012。白羅曼鵝品系與飼糧營養濃度對鵝隻飛機翼發生之影響。中國畜牧學會會誌 41(3),187-196。台北:中國畜牧學會。 [5] 林大貴。2017。TensorFlow+Keras深度學習人工智慧實務應用。臺北:博碩文化。 [6] 物件檢測詳解。2017。Object Detection論文詳解。網址:https://blog.csdn.net/u011974639/article/details/78053203。上網日期:2018-4-4。 [7] 陳怡睿、謝舜傑、陳景文、倪柏寧。2010。基因演算法自動演化類神經網路應用於山崩災害之評估。碩士論文。台南:長榮大學土地管理與開發學系。 [8] 徐志瑜。2016。光照調控種母鵝非產季生殖性能。碩士論文。台中:國立中興大學動物科學系。 [9] 黃信又。2009。飼養環境、飼糧能量含量與添加抗壞血酸對白羅曼鵝生長性能與屠體性狀之影響。碩士論文。台中:國立中興大學動物科學系 [10] 黃信凱。2016。深度卷積神經網路於混合式整體學習之影像檢索技術。碩士論文。桃園:國立中央大學通訊工程學系。 [11] 黃漢華。2017。年年上演大撲殺,台灣禽流感為何越來越兇?。遠見雜誌370,68-73。台北:遠見天下文化。 [12] 游凱文。2005。不同光照長度與餵飼方式對種鵝強迫換羽與產蛋性狀之影響。碩士論文。台中:國立中興大學動物科學系。 [13] 沈明訢。2017。以階層式深度卷積神經網路實現少樣本的人臉辨識系統。碩士論文。桃園:國立中央大學資訊工程學系。 [14] 曾紹武。2017。以深度類神經網路為基礎之居家生活動作辨識系統。碩士論文。桃園:國立中央大學資訊工程學系。 [15] 葉怡成。1995。類神經網路模式應用與實作。臺北:儒林圖書。 [16] 楊富名。2017。基於稀疏矩陣影像強化和深度學習之目標檢測技術。碩士論文。雲林:國立雲林科技大學資訊工程系。 [17] 劉希玉、劉弘。2008。人工神經網路與微粒群優化。北京:北京郵電大學。 [18] 劉兆峰。2015。深度學習模型於時尚風格視覺元素之探索。碩士論文。高雄:國立高雄應用科技大學資訊工程系。 [19] 劉昭雨。2017。卷積神經網路在金融技術指標之應用。碩士論文。花蓮:國立東華大學資訊工程學系。 [20] 戴邦地。2017。基於深度學習之復健動作辨識系統。碩士論文。桃園:中央大學資訊工程學系。 [21] 韓炳濤。2017。零基礎入門深度學習(4) -卷積神經。網址:https://www.zybuluo.com/hanbingtao/note/485480。上網日期:2018-3-5。 [22] Buckland, R. B., and G. Gérard(Eds.). 2002. Goose production. Rome: Food and Agriculture Organization of the United Nations. [23] Bojarski, M., D. Del Testa, D. Dworakowski, et al. 2017. End to end learning for self-driving cars. IEEE Intelligent Vehicles Stmposium. Los Angeles, CA: IV. [24] Choi, K., G. Fazekas, and M. Sandler. 2016. Automatic tagging using deep convolutional neural networks. The International Society of Music Information Retrieval Paper. New York, NY: ISMIR. [25] Fukushima, K., and S. Miyake. 1982. Neocognitron: A self-organizing neural network model for a mechanism of visual pattern recognition. Lecture Notes in Biomathematics 45: 267-285. [26] Food and Agriculture Organization of the United Nations. 2018. Food and agriculture organization livestock primary database. Rome: Food and Agriculture Organization of the United Nations. Available at: http://www.fao.org/faostat/en/#data/QL. Accessed 5 March 2018. [27] Girshick, R., J. Donahue, T. Darrell, and J. Malik. 2014. Rich feature hierarchies for accurate object detection and semantic segmentation. IEEE Conference on Computer Vision and Pattern Recognition Paper pp. 580-587. Columbus, OH: IEEE. [28] Girshick, R. 2015. Fast r-cnn. IEEE Conference on Computer Vision Paper pp. 1440-1448. Santiago: IEEE. [29] Hubel, D. H., and T. N., Wiesel. 1962. Receptive fields, binocular interaction and functional architecture in the cat's visual cortex. The Journal of Physiology 160(1): 106-154. [30] Hebb, D. O. 2005. The organization of behavior: A neuropsychological theory. Mahwah: Lawrence Erlbaum Associates. [31] Srivastava, N., G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov. 2014. Dropout: a simple way to prevent neural networks from overfitting. Journal of Machine Learning Research 15(1): 1929-1958. [32] Krizhevsky, A., I. Sutskever, and G. E. Hinton. 2012. Imagenet classification with deep convolutional neural networks. Neural Information Processing Systems Paper pp. 1097-1105. Stateline, NV: NIPS. [33] LeCun, Y., L. Bottou, Y. Bengio, and P. Haffner. 1998. Gradient-based learning applied to document recognition. Proceedings of the IEEE 86(11): 2278-2324. [34] McCulloch, W. S. and W. Pitts. 1943. A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biophysics 5(4): 115-133. [35] Murugan, P. 2017. Feed forward and backward run in deep convolution neural network. Available at: https://arxiv.org/pdf/1711.03278.pdf. Accessed 5 March 2018. [36] Rosenblatt, F. 1957. The perceptron, a perceiving and recognizing automaton Project Para. Buffalo: Cornell Aeronautical Laboratory. [37] Rumelhart, D. E., G. E. Hinton, and R. J. Williams. 1986. Learning representations by back-propagating errors. Nature 323(6088): 533. [38] Romanov, M. N. 1999. Goose production efficiency as influenced by genotype, nutrition and production systems. World's Poultry Science Journal 55(3): 281-294. [39] Raina, R., A. Madhavan, and A. Y. Ng. 2009. Large-scale deep unsupervised learning using graphics processors. International Conference on Machine Learning Paper pp. 873-880. Montreal, QC: ICML. [40] Ren, S., K. He, R. Girshick, and J. Sun. 2015. Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence 39(6): 1137-1149. [41] Redmon, J., S. Divvala, R. Girshick, and A. Farhadi. 2016. You only look once: Unified, real-time object detection. IEEE Conference on Computer Vision and Pattern Recognition Paper pp. 779-788. Las Vegas, NV: IEEE. [42] Scherf, B. D. 2000. World watch list for domestic animal diversity. Rome: Food and Agriculture Organization of the United Nations. [43] Simonyan, K., and A. Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. Asian Conference on Pattern Recognition Paper. Kuala Lumpur: ACPR. [44] Uijlings, J. R., K. E. Van De Sande, T. Gevers, and A. W. Smeulders. 2013. Selective search for object recognition. International Journal of Computer Vision 104(2): 154-171. [45] Wang, C. M., T. D. Way, Y. C. Chang, et al. 2010. The origin of the white Roman goose. Biochemical Genetics 48(11-12): 938-943. [46] Zeiler, M. D., and R. Fergus. 2014. Visualizing and understanding convolutional networks. European Conference on Computer Vision Paper pp. 818-833. Zürich: ECCV.
摘要: 鵝為重要的家禽之一。近年來,「非開放式」的鵝舍興起,反應鵝隻防疫意識的提升,鵝隻行為分析變的重要,但傳統人工觀察方式,存在著不客觀且誤差大的缺點,因此需要新的分析方式解決此問題。本研究透過使用卷積類神經網路與機器學習相關方法,建立鵝隻圖像辨識系統,預測圖像中鵝隻位置,奠定使用圖像分析鵝隻行為的基礎。研究的實驗對象為白羅曼曼鵝,使用的卷積類神網路相關演算法為Faster R-CNN。圖像辨識模型預測結果,平均精確度為0.89,精確度為81%,召回率為82%。在未來,期望以本研究為基礎,開發新的鵝隻行為辨識模式,逐漸取代傳統使用人力的方法。
URI: http://hdl.handle.net/11455/97802
文章公開時間: 10000-01-01
Appears in Collections:生物產業機電工程學系

文件中的檔案:

取得全文請前往華藝線上圖書館



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.