跳到主要內容

臺灣博碩士論文加值系統

(44.210.99.209) 您好!臺灣時間:2024/04/15 14:45
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:王靖惠
研究生(外文):WANG, CHING-HUI
論文名稱:使用深度學習於檢測番茄病害
論文名稱(外文):Using Deep Learning to Detect Tomato Diseases
指導教授:許巍嚴
口試委員:劉長萱蔡志鑫
口試日期:2020-06-18
學位類別:碩士
校院名稱:國立中正大學
系所名稱:資訊管理學系碩士在職專班
學門:電算機學門
學類:電算機一般學類
論文種類:學術論文
論文出版年:2020
畢業學年度:108
語文別:中文
論文頁數:56
中文關鍵詞:深度學習卷積神經網路卷積層池化層優化器
外文關鍵詞:deep learningConvolutional Neural NetworkConvolutional layerPooling layerOptimizer
相關次數:
  • 被引用被引用:3
  • 點閱點閱:304
  • 評分評分:
  • 下載下載:42
  • 收藏至我的研究室書目清單書目收藏:0
為解決番茄病害識別困難的問題,本研究在深度學習GoogLeNet卷積神經網路的基礎上,採用預訓練模型對數據進行訓練,將單純的卷積層跟池化層改成9個Inception架構並在後面接入平均池化替代傳統的全連接層再連接分類器,為了避免梯度消失,還加入了2個輔助分類器用於向前傳導梯度。同時採用Adam優化器,加速模型收斂速度,最終實現番茄病害的識別。為驗證所使用模型的優越性,與DenseNet121、AlexNet、ResNet101、VGG16等深度網路模型的訓練結果相比,GoogleNet具有最高的識別率。在相同的實驗條件下,為了進一步測試GoogLeNet的性能,在測試集的Top1達到99.42%的識別準確度與99.4%的召回率、99.41%的F1-Score,表現出比其他四種網路更好的性能。根據實驗結果,GoogLeNet對蕃茄病害的識別顯示出良好的適用性,滿足了對於番茄病害分類的實際應用要求。
In order to solve the problem of tomato disease recognition difficulty, this study uses the method of pre-training model to train the data on the basis of deep learning GoogLeNet convolutional neural network, and changes the pure convolution layer and pooling layer into 9 Inception architectures. In the back, the average pooling is used to replace the traditional fully connected layer and then connect the classifier. In order to avoid the gradient disappearing, two auxiliary classifiers were added to forward gradient. At the same time, the Adam optimizer can accelerate the model convergence speed and then realize the identification of tomato diseases. In order to identify the superiority of the model used, compared with the training results of deep network models for example DenseNet121、AlexNet、ResNet101、VGG16, GoogleNet has the highest recognition rate. Under the same experimental conditions, to further test the performance of GoogLeNet, Top1 in the test set reached a recognition accuracy of 99.42%, a recall rate of 99.4%, and a F1-Score of 99.41%, showing better performance than the other four networks. According to the experimental results, GoogLeNet's identification of tomato diseases shows good applicability, which meets the practical application requirements for tomato disease classification.
誌謝 i
摘要 ii
Abstract iii
目錄 iv
圖目錄 vi
表目錄 vii
第一章 緒論 1
1.1 研究背景 1
1.2 研究動機 2
1.3 研究問題 3
1.4 研究目的 4
1.5 成果與貢獻 4
第二章 文獻探討 6
2.1 機器學習檢測農作物病害相關文獻 6
2.2 卷積神經網路簡介與相關文獻 9
2.2.1 卷積層 10
2.2.2 池化層 12
2.2.3 ReLu層 13
2.2.4 全連接層 14
2.2.5 反向傳播 16
2.3 農作物病害檢測深度學習相關文獻 17
第三章 材料與研究方法 20
3.1 實驗材料 20
3.2 方法流程圖 23
3.3 樣本平衡與數據擴增 23
3.3.1 調整圖片大小 24
3.3.2 圖像翻轉與色彩調整 24
3.3.3 增加圖像高斯噪音 24
3.4 使用的神經網路-GoogLeNet 28
3.5 深度學習處理流程 32
3.6 超參數設置 32
3.6.1 學習率 33
3.6.2 損失函數 33
3.6.3 優化器 33
第四章 實驗評估與結果 36
4.1 實驗環境 36
4.2 實驗評估指標 36
4.2.1 混淆矩陣 37
4.2.2 召回率(Recall) 38
4.2.3 精準度(Precision) 38
4.2.4 總體準確率(Overall Accuracy) 39
4.2.5 F1-Score 39
4.3 結果 39
第五章 結論與未來展望 42
5.1 結論 42
5.2 研究限制 42
5.3 未來研究方向 43
參考文獻 44
中文文獻 44
英文文獻 45
中文文獻

1. 行政院農委會(民107)。農業統計年報。
2. 林鳳琪、陳怡如、許秀惠(民105)。設施番茄病蟲害綜合管理。農業世界雜誌,393,17。
3. 張瑞璋、邱安隆、陳保良(民100)。蟲媒病害與植物防疫政策。農作物害蟲及其媒介病害整合防治技術研討會專刊,152。


英文文獻

1. Brahimi, M., Boukhalfa, K., & Moussaoui, A. (2017). Deep learning for tomato diseases: classification and symptoms visualization. Applied Artificial Intelligence, 31(4), 299-315.
2. De Boer, P.-T., Kroese, D. P., Mannor, S., & Rubinstein, R. Y. (2005). A tutorial on the cross-entropy method. Annals of operations research, 134(1), 19-67.
3. Dyrmann, M., Karstoft, H., & Midtiby, H. S. (2016). Plant species classification using deep convolutional neural network. Biosystems Engineering, 151, 72-80.
4. Glorot, X., Bordes, A., & Bengio, Y. (2011). Deep sparse rectifier neural networks. Paper presented at the Proceedings of the fourteenth international conference on artificial intelligence and statistics.
5. He, K., Zhang, X., Ren, S., & Sun, J. (2016, 27-30 June 2016). Deep Residual Learning for Image Recognition. Paper presented at the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
6. Huang, G., Liu, Z., Maaten, L. v. d., & Weinberger, K. Q. (2017, 21-26 July 2017). Densely Connected Convolutional Networks. Paper presented at the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
7. Hughes, D., & Salathe, M. (2015). An open access repository of images on plant health to enable the development of mobile disease diagnostics. arXiv preprint arXiv:1511.08060.
8. Jordan, M. I. (1994). A Statistical Approach to Decision Tree Modeling. In W. W. Cohen & H. Hirsh (Eds.), Machine Learning Proceedings 1994 (pp. 363-370). San Francisco (CA): Morgan Kaufmann.
9. Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
10. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet Classification with Deep Convolutional Neural Networks. Commun. ACM, 60, 84-90.
11. LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278-2324.
12. Lin, M., Chen, Q., & Yan, S. (2013). Network in network. arXiv preprint arXiv:1312.4400.
13. Liu, B., Zhang, Y., He, D., & Li, Y. (2018). Identification of apple leaf diseases based on deep convolutional neural networks. Symmetry, 10(1), 11.
14. Mohanty, S. P., Hughes, D. P., & Salathe, M. (2016). Using deep learning for image-based plant disease detection. Frontiers in plant science, 7, 1419.
15. Oppenheim, D., & Shani, G. (2017). Potato disease classification using convolution neural networks. Advances in Animal Biosciences, 8(2), 244-249.
16. Osuna, E., Freund, R., & Girosit, F. (1997). Training support vector machines: an application to face detection. Computer Vision and Pattern Recognition, 130-136.
17. Pan, W., Qin, J., Xiang, X., Wu, Y., Tan, Y., & Xiang, L. (2019). A smart mobile diagnosis system for citrus diseases based on densely connected convolutional networks. IEEE Access, 7, 87534-87542.
18. Picon, A., Alvarez-Gila, A., Seitz, M., Ortiz-Barredo, A., Echazarra, J., & Johannes, A. (2019). Deep convolutional neural networks for mobile capture device-based crop disease classification in the wild. Computers and Electronics in Agriculture, 161, 280-290.
19. Prince, G., Clarkson, J. P., & Rajpoot, N. M. (2015). Automatic detection of diseased tomato plants using thermal and stereo visible light images. PloS one, 10(4), e0123262.
20. Rawat, W., & Wang, Z. (2017). Deep convolutional neural networks for image classification: A comprehensive review. Neural computation, 29(9), 2352-2449.
21. Sabrol, H., & Kumar, S. (2016). Fuzzy and neural network based tomato plant disease classification using natural outdoor images. Indian Journal of Science and Technology, 9(44), 1-8.
22. Sabrol, H., & Kumar, S. (2016). Intensity based feature extraction for tomato plant disease recognition by classification using decision tree. International Journal of Computer Science and Information Security, 14(9), 622.
23. Sannakki, S. S., Rajpurohit, V. S., Nargund, V. B., & Kulkarni, P. (2013, 4-6 July 2013). Diagnosis and classification of grape leaf diseases using neural networks. Paper presented at the 2013 Fourth International Conference on Computing, Communications and Networking Technologies (ICCCNT).
24. Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. ICLR 2015
25. Szegedy, C., Wei, L., Yangqing, J., Sermanet, P., Reed, S., Anguelov, D., et al. (2015, 7-12 June 2015). Going deeper with convolutions. Paper presented at the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
26. Xie, C., Shao, Y., Li, X., & He, Y. (2015). Detection of early blight and late blight diseases on tomato leaves using hyperspectral imaging. Scientific reports, 5, 16564.
27. Zhang, S., Wang, H., Huang, W., & You, Z. (2018). Plant diseased leaf segmentation and recognition by fusion of superpixel, K-means and PHOG. Optik, 157, 866-872.
28. Zhang, S., Zhang, S., Zhang, C., Wang, X., & Shi, Y. (2019). Cucumber leaf disease identification with global pooling dilated convolutional neural network. Computers and Electronics in Agriculture, 162, 422-430.
29. Zhao, Z.-Q., Zheng, P., Xu, S.-t., & Wu, X. (2019). Object detection with deep learning: A review. IEEE transactions on neural networks and learning systems.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊