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:2024/04/20 05:20
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:王昱勝
研究生(外文):Yu-Sheng Wang
論文名稱:利用紋理與顏色特徵進行植物疾病之檢測分類
論文名稱(外文):Detection and Classification of Leaf Diseases using Texture and Color Feature
指導教授:吳國光吳國光引用關係
指導教授(外文):Kuo-Guan Wu
口試委員:溫志煜張呈源
口試委員(外文):Chih-Yu WenCheng-Yuan Chang
口試日期:2019-06-27
學位類別:碩士
校院名稱:國立中興大學
系所名稱:電機工程學系所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2019
畢業學年度:107
語文別:英文
論文頁數:24
中文關鍵詞:植物病害辨識葉片紋理特徵.
外文關鍵詞:plant diseaseidentificationleaf texture features.
相關次數:
  • 被引用被引用:0
  • 點閱點閱:172
  • 評分評分:
  • 下載下載:21
  • 收藏至我的研究室書目清單書目收藏:0
利用植物的葉面特性,進行其病變分析與檢測,不僅有助於農業自動化的發展,更能即時監控植物的生長狀況,以及早發現病蟲害的問題,進而提高作物的收成量.傳統上以人工進行作物疾病,非常耗時且費力.近來,在植物自動檢測疾病的研究上,常用的作法是先切割出葉片中的病變區域,其紋理顏色再透過適當的分類器,分辨出可能感染的疾病類型.
然而,病變區域切割的效果,會直接影響後續疾病偵測的準確度.尤其是在染病初期病變區域較小,或是受到背景光線干擾而影響,皆會造成病變區域切割效能的下降.本文中提出了一種基於葉片紋理的植物病害分類方法,不需進行病變區域的分割處理,直接以GLCM(灰度共生矩陣)參數所得紋理特徵和顏色特徵,然後進行SVM(支持向量機)分類處理,可以達到近95%分類正確率.
Using the leaf characteristics of plants to carry out disease analysis and detection, not only contributes to the development of agricultural automation, but also monitors the growth of plants in an instant, and early detection of pests and diseases, thereby increasing crop yields. Traditionally artificial It is very time-consuming and laborious to carry out crop diseases. Recently, in the research of automatic detection of diseases by plants, it is common practice to first cut out the lesions in the leaves, and the texture color is then passed through an appropriate classifier to distinguish the types of diseases that may be infected.
However, the effect of lesion region segmentation will directly affect the accuracy of subsequent disease detection. Especially in the early stage of the disease, the lesion area is small, or it is affected by the background light, which will cause the segment performance of the lesion area to decrease. A classification method of plant diseases based on leaf texture is proposed. Without the segmentation processing of lesions, the texture features and color features obtained by GLCM (Gray Level Co-occurrence Matrix) parameters are directly obtained, and then SVM (Support Vector Machine) classification processing is performed. Achieve nearly 95% classification accuracy.
摘要.................................................................................................................................i
Abstract..........................................................................................................................ii
Table of Contents..........................................................................................................iii
List of Tables.................................................................................................................iv
List of Figure..................................................................................................................v
1. Introduction................................................................................................................1
2. Background.................................................................................................................3
2.1 Gray Level Co-occurrence Matrix (GLCM).....................................................3
2.2 Evaluation of Speed and Accuracy for Comparison of Texture Classification..................................................................................................................5
2.3 Support Vector Machine (SVM)…...................................................................6
2.3.1 Linear SVM theory……………………………………………………7
2.3.2 The Non-Separable case of SVM…………………………………….10
2.3.3 Extend SVM from Binary Bifurcation to Multivariate Bifurcation….11
3. Proposed Method......................................................................................................12
3.1 Image Acquisition...........................................................................................12
3.2 Image Processing............................................................................................15
3.3 Feature Extraction...........................................................................................17
3.4 Image Classifier(SVM)...................................................................................18
4. Comparative Experiments and Analyses...................................................................19
5. Conclusion................................................................................................................23
6. References................................................................................................................24
[1]Robert M. Haralick, K.Shanmugam, and Its’Hak Dinstein, “Textural features for image classification,” Nov. 1973.
[2]P. Pawar, V. Turkar, and P. Patil, “Cucumber disease detection using artificial neural network,” 26–27, Aug. 2016.
[3] H. Al-Hiary, S. Bani-Ahmad, M. Braik and Z. ALRahamneh, “Detection of leaf diseases and classification using digital image processing,” 17-18 March 2017
[4] S. S. Sannakki, V. S. Rajpurohit, V. B. Nargund, P. Kulkarni, "Diagnosis and classification of grape leaf diseases using neural networks", IEEE 4th ICCCNT, 2013.
[5] J. Yi Tou, K. Kuan Yew Khoo, Y.Haur Tay and P. Yee Lau “Evaluation of speed and accuracy for comparison of texture classification implemention on embedded platform,” 12-13 January 2009.
[6] W. H. Yap, M. Khalid and R. Yusof, “Face verification with Gabor representation and support vector machines,” in IEEE Proc. of the First Asia International Conference on Modeling and Simulation, 2007.
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