(3.238.130.97) 您好!臺灣時間:2021/05/18 10:43
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:::

我願授權國圖
: 
twitterline
研究生:林旻宏
研究生(外文):Lin, Min-Hung
論文名稱:植基於智慧型方法之植物病害影像辨識
論文名稱(外文):A Plant Disease Recognition System Using Intelligent Approach
指導教授:蔡正發蔡正發引用關係
指導教授(外文):Tsai, Cheng-Fa
學位類別:碩士
校院名稱:國立屏東科技大學
系所名稱:資訊管理系所
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:2013
畢業學年度:101
語文別:中文
論文頁數:63
中文關鍵詞:HSI灰階共生矩陣支持向量機
外文關鍵詞:HSIGLCMSVM
相關次數:
  • 被引用被引用:2
  • 點閱點閱:1165
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
近年來氣候環境異常,常伴隨作物病害的大量發生,病害會改變植物組織結構與形態,產生視覺化的病徵,病害辨別需專業人員協助,期能藉由視覺影像自動化辨識,進而達到及時防治目的;屏東縣多項作物種植面積及產量居本省之冠,本研究以屏東主要生產作物胡瓜及檸檬為例,取得三種病害影像樣本,胡瓜露菌病、胡瓜炭疽病及檸檬黑點病,利用HSI色彩空間配合門檻值進行植物病害紋理特徵分割,以灰階共生矩陣提取六組特徵向量,以支持向量機完成病害辨識分類,本論文使用智慧型方法經測試辨識度可達90%,實現植物病害自動化辨識之目的。

關鍵字:HSI,灰階共生矩陣,支持向量機

The abnormal climate changes in the recent years have caused large increases of agricultural diseases. These diseases often change crops' botanical structures and forms which generate visual obviousness of the agricultural diseases. It is therefore an ideal way to prevent and cure such diseases by identifying the types of the diseases through automatic visual identifying system, with professionals' assistance. Pingtung County has the largest cultivation area and production in Taiwan in many types of crops. This research focuses on taking visual image samples of the three agriculture diseases, namely downy mildew, anthracnose and citrus melanose, from cucumbers and lemons, the two of the main cultivation corps in Pingtung. HSI colour space associated with thresholds models are employed to analyse agriculture disease pattern phenomena. Six sets of eigenvector are obtained from the gray-level co-occurrence matrix, which support support vector machines to categorise disease identifications. The analytic method employed in this research has an identification rate as high as 90%, which ultimately realises the griculture disease identifying purpose.
Keywords: HSI, GLCM, SVM

目 錄

摘 要 II
Abstract III
目 錄 V
圖表索引 VII
第1章 緒論 1
1.1 研究背景 1
1.2 研究動機與目的 2
1.3 研究流程 3
1.4 研究範圍與限制 5
1.5 論文架構 5
第2章 文獻探討 7
2.1 胡瓜病害簡介 7
2.2 檸檬病害簡介 12
2.3 色彩空間(color space) 14
2.3.1 RGB色彩空間 14
2.3.2 HSI色彩空間 15
2.4灰階共生矩陣(Gray Level Co-occurrence Matrix) 16
2.5 支持向量機(Support Vector Machines) 22
第3章 研究方法 29
3.1 影像辨識流程 29
3.2 影像切割 30
3.3 紋理特徵值提取 40
3.4 病害影像分類 42
第4章 實驗與分析 44
4.1 測試資料 44
4.2 測試結果 45
4.2.1 病害特徵向量值分析 46
4.2.2 持支向量機辨識 54
4.3 實驗結果小結 57
第5章 結論與未來展望 59
5.1 結論 59
5.2 未來展望 60
參考文獻 61

參考文獻
中文部份
[1] 鍾國亮, 影像處理與電腦視覺. 台北巿: 台灣東華, 2002.
[2] 張真誠, 數位影像處理技術: 松崗出版社, 2001.
[3] 劉敏莉. (2009). 國產優良品牌花胡瓜生產管理技術作業標準. Available: http://www.afa.gov.tw/publish_detail.asp?catid=1462
[4] 陳文雄、鄭安秀, "瓜菜類-胡瓜," in 蔬菜病蟲害綜合防治專輯, 田春門,陳漢洋, 南投: 台灣省政府農林廳, 1999, pp. 36-37.
[5] 鄭安秀. 瓜類病害之發生與管理. Available: http://kmsafe.kinmen.gov.tw/upload/cht/attachment/28fc66d46402a906c764ac1f9287cc8b.pdf
[6] 林益昇、鄧汀欽, "瓜菜類病害," in 台灣農家要覽農作篇(三), 簡芙蓉, 台北: 豐年社, 2005, p. 199.
[7] 陳柏文, "檸檬之產銷調節," 農政與農情, vol. 229, pp. 66-68, 2011.
[8] 蔡雲鵬, "柑橘黑點病," in 植物保護圖鑑系列9, 羅幹成,蔣慕琰, Ed., ed: 防檢局, 2003, p. 181.
[9] 李綺芳, "結合主成份分析與模組化半徑基底函數類神經網路於影像語意內容分析問題," 碩士, 資訊工程研究所, 雲林科技大學, 雲林縣, 2007.
[10] 林宗勳. (2013). Support Vector Machines 簡介. Available: http://www.cmlab.csie.ntu.edu.tw/~cyy/learning/tutorials/SVM2.pdf
英文部分
[11] A. Camargo and J. S. Smith, "An image-processing based algorithm to automatically identify plant disease visual symptoms," Biosystems Engineering, vol. 102, no. 1, pp. 9-21, 2009.
[12] A. Camargo and J. S. Smith, "Image pattern classification for the identification of disease causing agents in plants," Computers and Electronics in Agriculture, vol. 66, no. 2, pp. 121-125, 2009.
[13] T. Rumpf, A. K. Mahlein, U. Steiner, E. C. Oerke, H. W. Dehne, and L. Plümer, "Early detection and classification of plant diseases with Support Vector Machines based on hyperspectral reflectance," Computers and Electronics in Agriculture, vol. 74, no. 1, pp. 91-99, 2010.
[14] msdn. (2013). Color. Available: http://msdn.microsoft.com/en-us/library/windows/desktop/aa511283.aspx
[15] K. S. Robert M. Haralick, Its'Hak Dinstein, "Textural Features for Image Classification," IEEE Trans. on Syst. Man Cybern., vol. 3, no. 6, pp. 610 - 621, 1973.
[16] R. M. Haralick, "Statistical and structural Approaches to Texture," Proceedings of the IEEE, vol. 67, no. 5, pp. 786 - 804, MAY 1979.
[17] V. N. Vapnik, " An overview of statistical learning theory " IEEE Transactions on Neural Networks, vol. 10, no. 5, pp. 988-999, 1999.


[18] A. Ben-Hur, Horn, D., Siegelmann, H.T., Vapnik, V., "Support vector clustering," Journal of Machine Learning Research, vol. 3, no. 4, pp. 125-137, 2001.
[19] C. W. Hsu, C.J. Lin, "A comparison of methods for Multi-class Support Vector Machines," IEEE Transactions on neural networks, vol. 13, no. 4, pp. 415-425, 2002.
[20] Chih-Chung Chang, Chih-Wei Hsu, and Chih-Jen Lin, A Practical Guide to Support Vector Classification, 2003.
[21] wiki. (2013). Support vector machine. Available: https://en.wikipedia.org/wiki/Support_vector_machine
[22] C.J. Lin, C. W. Hsu, "A simple decomposition method for support vector Machine," Machine Learning, vol. 46, no. 1-3, pp. 291-314, 2002.2002.
[23] P. J. Howarth, D. J. Marceau, J .M. Dubois, D .J. Gratton, "Evaluation Of The Grey-level Co-occurrence Matrix Method For Land-cover Classification Using Spot Imagery," IEEE Transactions on Geoscience and Remote Sensing, vol. 28, no. 4, pp. 513-519, 1990.
[24] Chih-Chung Chang and Chih-Jen Lin. (2001). LIBSVM: a library for support vector machines. Available: http://www.csie.ntu.edu.tw/~cjlin/libsvm/

連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top