請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/70846完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 張智星(Jyh-Shing Roger Jang) | |
| dc.contributor.author | Yi-Hsuan Chen | en |
| dc.contributor.author | 陳奕瑄 | zh_TW |
| dc.date.accessioned | 2021-06-17T04:40:46Z | - |
| dc.date.available | 2021-08-13 | |
| dc.date.copyright | 2018-08-13 | |
| dc.date.issued | 2018 | |
| dc.date.submitted | 2018-08-06 | |
| dc.identifier.citation | [1] Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, et al. Imagenet large scale visual recognition challenge. International Journal of Computer Vision, 115(3):211–252, 2015.
[2] Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems, pages 1097–1105, 2012. [3] Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. Imagenet: A large-scale hierarchical image database. In Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on, pages 248–255. IEEE, 2009. [4] Sue Han Lee, Chee Seng Chan, Paul Wilkin, and Paolo Remagnino. Deep-plant: Plant identification with convolutional neural networks. In Image Processing (ICIP), 2015 IEEE International Conference on, pages 452–456. IEEE, 2015. [5] Karen Simonyan and Andrew Zisserman. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014. [6] Sinno Jialin Pan and Qiang Yang. A survey on transfer learning. IEEE Transactions on knowledge and data engineering, 22(10):1345–1359, 2010. [7] Geoffrey E Hinton, Nitish Srivastava, Alex Krizhevsky, Ilya Sutskever, and Ruslan R Salakhutdinov. Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580, 2012. [8] Siang Thye Hang and Masaki Aono. Open world plant image identification based on convolutional neural network. In Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2016 Asia-Pacific, pages 1–4. IEEE, 2016. [9] Hervé Goëau, Pierre Bonnet, and Alexis Joly. Plant identification in an open-world (lifeclef 2016). In CLEF 2016-Conference and Labs of the Evaluation forum, pages 428–439, 2016. [10] Song Yuheng and Yan Hao. Image segmentation algorithms overview. arXiv preprint arXiv:1707.02051, 2017. [11] Nobuyuki Otsu. A threshold selection method from gray-level histograms. IEEE transactions on systems, man, and cybernetics, 9(1):62–66, 1979. [12] Salem Saleh Al-Amri, NV Kalyankar, and SD Khamitkar. Image segmentation by using edge detection. International Journal on computer science and engineering, 2(3):804–807, 2010. [13] John A Hartigan and Manchek A Wong. Algorithm as 136: A k-means clustering algorithm. Journal of the Royal Statistical Society. Series C (Applied Statistics), 28(1):100–108, 1979. [14] Xavier Glorot and Yoshua Bengio. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the thirteenth international conference on artificial intelligence and statistics, pages 249–256, 2010. [15] Herbert Robbins and Sutton Monro. A stochastic approximation method. The annals of mathematical statistics, pages 400–407, 1951. [16] Jack Kiefer and Jacob Wolfowitz. Stochastic estimation of the maximum of a regression function. The Annals of Mathematical Statistics, pages 462–466, 1952. [17] Ning Qian. On the momentum term in gradient descent learning algorithms. Neural networks, 12(1):145–151, 1999. [18] Ilya Sutskever, James Martens, George Dahl, and Geoffrey Hinton. On the importance of initialization and momentum in deep learning. In International conference on machine learning, pages 1139–1147, 2013. [19] SM Aqil Burney and Humera Tariq. K-means cluster analysis for image segmentation. International Journal of Computer Applications, 96(4), 2014. [20] Martín Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, et al. Tensorflow: A system for large-scale machine learning. In OSDI, volume 16, pages 265–283, 2016. [21] Martín Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, Greg S Corrado, Andy Davis, Jeffrey Dean, Matthieu Devin, et al. Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467, 2016. [22] Alfredo Canziani, Adam Paszke, and Eugenio Culurciello. An analysis of deep neural network models for practical applications. arXiv preprint arXiv:1605.07678, 2016. [23] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016. [24] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Identity mappings in deep residual networks. In European Conference on Computer Vision, pages 630–645. Springer, 2016. [25] Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich. Going deeper with convolutions. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2015. [26] Sergey Ioffe and Christian Szegedy. Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167, 2015. [27] Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jon Shlens, and Zbigniew Wojna. Rethinking the inception architecture for computer vision. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 2818–2826, 2016. [28] Christian Szegedy, Sergey Ioffe, Vincent Vanhoucke, and Alexander A Alemi. Inception-v4, inception-resnet and the impact of residual connections on learning. In AAAI, volume 4, page 12, 2017. [29] Andrew G Howard. Some improvements on deep convolutional neural network based image classification. arXiv preprint arXiv:1312.5402, 2013. [30] Pierre Sermanet, David Eigen, Xiang Zhang, Michaël Mathieu, Rob Fergus, and Yann LeCun. Overfeat: Integrated recognition, localization and detection using convolutional networks. arXiv preprint arXiv:1312.6229, 2013. [31] David Arthur and Sergei Vassilvitskii. k-means++: The advantages of careful seeding. In Proceedings of the eighteenth annual ACM-SIAM symposium on Discrete algorithms, pages 1027–1035. Society for Industrial and Applied Mathematics, 2007. [32] Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, and Alan L Yuille. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE transactions on pattern analysis and machine intelligence, 40(4):834–848, 2018. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/70846 | - |
| dc.description.abstract | 本研究的目標為利用卷積神經網路來辨識照片中的植物所歸屬的類別。在模型架構方面採用了知名的VGG-16模型，並使用遷移式學習（transfer learning）來降低學習至參數收斂所需要的時間。本次使用的資料集為擁有500種品種、約10萬張圖片的植物照片資料集。為了對植物特徵或主體較不明顯的圖片更進一步的處理，在一般的辨識過程後，加入了Unseen Category Query Identification辨識法來選取出這些辨識度不足的圖片，之後對選取出的圖片進行圖像分割，嘗試將植物主體與背景或雜訊分離，藉此來強調植物特徵。執行完前述步驟之後，選出包含植物主體的圖片，將其輸入模型進行再辨識，並實行其它實驗來比較這些做法的成效。 | zh_TW |
| dc.description.abstract | In this work, we want to recognize the species of plants in a picture by using Convolutional Neural Networks (CNN). We use the VGG-16 model in our experiments. To make the training process converged efficiently, we train model by leveraging transfer learning. The dataset we use is made up of 500 species consisting of approximate 100,000 plant images. We employ Unseen Category Query Identification (UCQI) after the prediction step and picking those images which don't have obvious features or main bodies. For those picked images, image segmentation is used for separating plant from other objects and background noise. We choose the segmented images containing plant main body for re-classification. Detail comparisons between the proposed method and baselines are shown on the experimental part. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-17T04:40:46Z (GMT). No. of bitstreams: 1 ntu-107-R05922168-1.pdf: 14884633 bytes, checksum: ed8ed17af35120b46870e0f41a09c7b9 (MD5) Previous issue date: 2018 | en |
| dc.description.tableofcontents | 致謝 i
中文摘要 ii Abstract iii 目錄 iv 圖片目錄 vi 表格目錄 viii 1 緒論 1 1.1 研究主題簡介 1 1.2 實驗方法簡介 2 1.3 章節概述 3 2 相關研究介紹 4 2.1 卷積神經網路簡介 4 2.1.1 卷積層 5 2.1.2 池化層 6 2.1.3 全連接層 6 2.1.4 Dropout 6 2.1.5 激勵函數 7 2.1.6 Softmax 層 9 2.2 AlexNet 9 2.3 VGG-16 模型 10 2.4 未知類別的辨識 10 2.5 圖像分割 13 2.5.1 K-平均分群法 13 3 實驗設定 16 3.1 資料集 16 3.2 模型參數設定 17 3.3 圖片前處理 20 3.3.1 資料增強 21 3.4 UCQI 的修改 22 3.5 圖片後處理 24 3.6 實驗環境 26 4 實驗結果與分析 27 4.1 模型架構與訓練方法 27 4.2 圖片再辨識 31 4.2.1 實驗 ─ 新增訓練資料 34 4.2.2 實驗 ─ 背景補色 37 5 結論與未來展望 40 5.1 回顧與結論 40 5.2 改進方向與未來展望 41 5.2.1 模型架構 41 5.2.2 測試方法 42 5.2.3 UCQI 的門檻值 43 5.2.4 圖片後處理 45 參考文獻 48 | |
| dc.language.iso | zh-TW | |
| dc.subject | 機器學習 | zh_TW |
| dc.subject | 卷積神經網路 | zh_TW |
| dc.subject | 植物辨識 | zh_TW |
| dc.subject | 圖像分割 | zh_TW |
| dc.subject | K-means 分群法 | zh_TW |
| dc.subject | VGG模型 | zh_TW |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | K-means clustering | en |
| dc.subject | Machine learning | en |
| dc.subject | Deep learning | en |
| dc.subject | VGG model | en |
| dc.subject | Convolution neuron network | en |
| dc.subject | Image segmentation | en |
| dc.subject | Plant recognition | en |
| dc.title | 以CNN進行植物圖片的辨識以及經過處理後的再辨識 | zh_TW |
| dc.title | Plant Image Recognition with CNN and Re-classification | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 106-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 王鈺強(Yu-Chiang Wang),徐宏民(Winston Hsu) | |
| dc.subject.keyword | 植物辨識,機器學習,深度學習,VGG模型,卷積神經網路,圖像分割,K-means 分群法, | zh_TW |
| dc.subject.keyword | Plant recognition,Machine learning,Deep learning,VGG model,Convolution neuron network,Image segmentation,K-means clustering, | en |
| dc.relation.page | 51 | |
| dc.identifier.doi | 10.6342/NTU201801836 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2018-08-06 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 資訊工程學研究所 | zh_TW |
| 顯示於系所單位： | 資訊工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-107-1.pdf 未授權公開取用 | 14.54 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。