Please use this identifier to cite or link to this item: http://hdl.handle.net/10603/449354
Full metadata record
DC FieldValueLanguage
dc.coverage.spatialIntroduction Agriculture field plays an important role in economy of any country. As India is one of the developing country agriculture is one of the backbone of economy. Having diseases in plants is a natural process. In traditional practice farmer try to evaluate the diseases by his past experience. Or in other case the expert observe the plant organs like leaves and stems for any diseases. It is very time consuming and costly method. We require an early identification to protect crop from diseases. This study perform classification techniques to identify mung bean plant leaf diseases using machine learning and deep learning techniques. Chapter 1 Introduction to Plant Disease Detection System This chapter gives overview of the research work, its scope, objectives, need etc. in detail. Also chapter covers details of common mung bean plant diseases and diseases covered in this study. Application area of agriculture image processing, Crop/Plant diseases selection, image processing techniques is also covered in this chapter. The summary of the overall thesis is also discussed. Chapter 2 Literature Review Study of the previously done work up to now in the area of plant disease recognition for numerous plants and its organs is discussed in this chapter. It includes journal articles, conference articles, electronic documents, web resources. Chapter 3 Plant Foliar Disease Identification Model In this chapter design of the foliar/leaf disease detection model is discussed in detail. Numerous components and subcomponents of model are explained in detail in this chapter. Design and development of a model to classify crop foliar diseases Atmiya University, Rajkot, Gujarat, India Page 2 of 2 Chapter 4 Development of Plant Foliar Disease Identification Model (PFDIM) This chapter describes component development of the model presented in chapter 3 in detail. Input and output of the model Plant Foliar Disease Identification Model is discussed in this chapter. Chapter 5 Results and Conclusion This chapter converses result of the projected PFDIM model applied on mung leaf dataset collected to quantity the success of projected research work. Moreover this chapter presents conclusion of projected research work along with path for future scope in the present research space. Conclusion Results and conclusion are discussed in detail in chapter 5 based on various parameters. This chapter presented the results concerning to the numerous proposed models. In agriculture, one of the developing research area is computerization of identification and classification of various mung leaf diseases. The computerization may help to improve quantity and quality of the crop yield. Manual identification method is very time consuming and may also provide lack of accuracy for the farmers. Therefore, it requires an image processing technique for timely and accurately detection and classification of plant diseases. In large farms, it is not possible to monitor the crop using manual or traditional methods. The computerized technique of image processing is adapted for the disease detection. On mung bean plant leaves, which uses color information to detect the disease on mung bean plant leaf. From the stated information from the thesis, an interface is encouraged to the farmers of mung bean for the early recognition of mung bean plant leaf diseases. It has been achieved by considering three different mung bean plant leaf diseases such as, CercosporaLeaf Spot, Powdery Mildew, and Yellow Mosaic Virus. The key contribution of the presented study is the early detection of mung bean plant leaf diseases. The study will help mung bean farmers who generally depend on the agricultural experts or advisors for the disease diagnosis.-
dc.date.accessioned2023-01-18T12:03:20Z-
dc.date.available2023-01-18T12:03:20Z-
dc.identifier.urihttp://hdl.handle.net/10603/449354-
dc.description.abstracta controlled environment is a data item (image) that comprises only a single subject (leaf) and newlinea white background. In an uncontrolled environment, an image contains the Mung leaf, newlinebackground noise like stems, ground, other Mung leaves, etc. In combined environment images newlineof both the controlled and uncontrolled environments are merged together. Seven different newlineclassifiers namely Support Vector Machine (SVM), KNN (K Nearest Neighbor), AdaBoost newline(Adaptive Boosting), GaussianNB (Gaussian Naive Bayes), DTC (Decision Tree Classifier), newlineLogisticRegression and Custom CNNs with different architectures have been trained and newlinecompared to each other. newlineResearcher aims at detecting 3 mung leaf disease categories and a healthy leaf category. newlineThe model extracts complex features of various diseases. Early detection will help farmers to newlineimprove their productivity. The main objective was to automate Mung Leaf disease newlineidentification using advanced machine learning and deep learning approaches and image data. newlineAmong all the classifiers the custom CNN achieved performs well and achieved highest newlineaccuracy in all the three environments. Custom CNN achieves 99.24% of training and 95.05% newlineof testing accuracy in controlled environment. In uncontrolled environment custom CNN newlineachieves 99.69% training and 87.88% of testing accuracy. In combined environment custom newlineCNN achieves 98.81% of training and 90.68% of testing accuracy. The results shows high newlinepotentiality of machine vision for recognition of diseased leaves. An interface is developed newlinewhere user can input and image. Here are user can select image from either single leaf newline(controlled environment), photo captured from the field itself (uncontrolled environment). newlineImage given as input by interface will be given to model for classification whether it is healthy newlineor having disease and if it is affected by disease then which disease the leaf has i.e. amongst newlinethe three Cercospora Leaf Spot, Powdery Mildew, and Yellow Mosaic Virus. Interface is just a medium to interact with model, and model works as an-
dc.format.extent245-
dc.languageEnglish-
dc.relation126-
dc.rightsuniversity-
dc.titleDesign and Development of A Model to Classify Crop Foliar Diseases-
dc.creator.researcherNaik, Akruti N-
dc.subject.keywordComputer Science-
dc.subject.keywordComputer Science and Image Processing-
dc.subject.keywordComputer Science Artificial Intelligence-
dc.subject.keywordCrop Disease-
dc.subject.keywordDecision Tree-
dc.subject.keywordEngineering and Technology-
dc.subject.keywordKNN-
dc.subject.keywordLogistic Regression-
dc.subject.keywordMoong Leaf-
dc.subject.keywordSVM-
dc.contributor.guideThaker, Hetal R-
dc.publisher.placeRajkot-
dc.publisher.universityAtmiya University-
dc.publisher.institutionComputer Science-
dc.date.registered2019-
dc.date.completed2022-
dc.date.awarded2022-
dc.format.dimensionsA4 Size-
dc.format.accompanyingmaterialDVD-
dc.source.universityUniversity-
dc.type.degreePh.D.-
Appears in Departments:Computer Science

Files in This Item:
File Description SizeFormat 
01_title.pdfAttached File223.76 kBAdobe PDFView/Open
02_prelim pages.pdf1.3 MBAdobe PDFView/Open
03_content.pdf453.06 kBAdobe PDFView/Open
04_abstract.pdf368.02 kBAdobe PDFView/Open
05_chapter 1.pdf2.55 MBAdobe PDFView/Open
06_chapter 2.pdf696.7 kBAdobe PDFView/Open
07_chapter 3.pdf1.12 MBAdobe PDFView/Open
08_chapter 4.pdf6.79 MBAdobe PDFView/Open
09_chapter 5.pdf735.61 kBAdobe PDFView/Open
10_annexures.pdf6.36 MBAdobe PDFView/Open
80_recommendation.pdf453.88 kBAdobe PDFView/Open


Items in Shodhganga are licensed under Creative Commons Licence Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).

Altmetric Badge: