• Login
    • University Home
    • Library Home
    • Lib Catalogue
    • Advance Search
    View Item 
    •   IR@KDU Home
    • INTERNATIONAL RESEARCH CONFERENCE ARTICLES (KDU IRC)
    • 2023 IRC Articles
    • Computing
    • View Item
    •   IR@KDU Home
    • INTERNATIONAL RESEARCH CONFERENCE ARTICLES (KDU IRC)
    • 2023 IRC Articles
    • Computing
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Disease Detection in Coffee Plants Using Computer Vision

    Thumbnail
    View/Open
    FOC_IRC2023_Proceeding-Book-60-66.pdf (342.8Kb)
    Date
    2023-09
    Author
    Senanayake, DTN
    Maduranga, MWP
    Metadata
    Show full item record
    Abstract
    Coffee is one of the most widely consumed beverages worldwide and an essential crop for many economies However, several illnesses that might negatively affect coffee yield and quality can affect coffee plants. For crop losses to be kept to a minimum, early detection of these diseases is essential. This research suggests a technique that makes use of convolutional neural networks (CNN). The suggested method entails several steps. Gather a dataset of coffee plants first, including both healthy plants and unhealthy plants. After that, the dataset is pre processed to improve the quality of the images. The pre-processed dataset is then used to create and train a CNN architecture. The CNN develops the ability to automatically recognize patterns and traits. Once trained, the CNN model can be used to identify diseases in coffee plants. This forecast can help farmers and agricultural professionals spot sick plants quickly and take appropriate action. Extensive tests and comparative analyses are carried out to assess the performance of the proposed method. The outcomes show how well the CNN-based method for detecting coffee plant diseases performs in terms of accuracy and dependability. The suggested approach provides a potentially effective response to the difficultiesinvolved in manually identifying diseases. Our proposed model with CNN three-layer classifier with a 0.01 learning rate achieved an overall classification accuracy of 0.89% with the 28th iteration of the training process out of a total of 100 planned epochs. This research utilizes the capability of CNNs to construct automated systems for identifying agricultural diseases, ultimately assisting in sustainable coffee production, and securing the livelihoods of coffee producers.
    URI
    http://ir.kdu.ac.lk/handle/345/7388
    Collections
    • Computing [49]

    Library copyright © 2017  General Sir John Kotelawala Defence University, Sri Lanka
    Contact Us | Send Feedback
     

     

    Browse

    All of IR@KDUCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsFacultyDocument TypeThis CollectionBy Issue DateAuthorsTitlesSubjectsFacultyDocument Type

    My Account

    LoginRegister

    Library copyright © 2017  General Sir John Kotelawala Defence University, Sri Lanka
    Contact Us | Send Feedback