Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd Logo
Upload

Welcome to Scribd!

  • 65 views

    CLDDS PPT SHOW Phase2

    Uploaded by

    Pavan K
    This document describes a cotton leaf disease detection system developed by a group of students guided by Dr. Aradhana D. The system uses a CNN model to classify common cotton diseases from images. The objectives are to design a system to detect cotton leaf diseases, classify diseases using texture features, analyze leaf infections, and provide an accurate image processing solution. The system requirements, design diagrams, implementation modules, and references are also outlined.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd

    CLDDS PPT SHOW Phase2

    Uploaded by

    Pavan K
    65 views19 pages
    This document describes a cotton leaf disease detection system developed by a group of students guided by Dr. Aradhana D. The system uses a CNN model to classify common cotton diseases from images. The objectives are to design a system to detect cotton leaf diseases, classify diseases using texture features, analyze leaf infections, and provide an accurate image processing solution. The system requirements, design diagrams, implementation modules, and references are also outlined.

    Original Title

    CLDDS_PPT_SHOW_phase2

    Copyright

    © © All Rights Reserved

    Available Formats

    PPTX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document describes a cotton leaf disease detection system developed by a group of students guided by Dr. Aradhana D. The system uses a CNN model to classify common cotton diseases from images. The objectives are to design a system to detect cotton leaf diseases, classify diseases using texture features, analyze leaf infections, and provide an accurate image processing solution. The system requirements, design diagrams, implementation modules, and references are also outlined.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    65 views19 pages

    CLDDS PPT SHOW Phase2

    Uploaded by

    Pavan K
    This document describes a cotton leaf disease detection system developed by a group of students guided by Dr. Aradhana D. The system uses a CNN model to classify common cotton diseases from images. The objectives are to design a system to detect cotton leaf diseases, classify diseases using texture features, analyze leaf infections, and provide an accurate image processing solution. The system requirements, design diagrams, implementation modules, and references are also outlined.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    You are on page 1of 19

    Cotton Leaf Disease Detection System

    PROJECT MEMBERS
    AMOGH.N 3BR19CS008
    IRSHAD AHMED C 3BR19CS060
    MOHAMMED SABEER 3BR19CS088
    DURGA PRASAD A G 3BR18CS043

    GUIDE
    Dr. Aradhana D
    ABSTRACT
    Cotton is one of the economically significant agricultural products in India, but it
    is exposed to different constraints in the leaf area. Mostly, these constraints are
    identified as diseases and pests that are hard to detect with bare eyes. This
    study focused to develop a model to boost the detection of cotton leaf disease
    and pests using the deep learning technique, CNN. To do so, the researchers
    have used common cotton leaf disease and pests such as bacterial blight, spider
    mite, and leaf miner. K-fold cross-validation strategy was worn to dataset
    splitting and boosted generalization of the CNN model. This developed model is
    implemented using python and the model is equipped on the deep learning
    package called Keras, TensorFlow backed, and Jupyter which are used as the
    developmental environment. This revealed the feasibility of its usage in real-
    time applications and the potential need for IT-based solutions to support
    traditional or manual disease and pest’s identification.
    OBJECTIVES
    ☘ To design system that can detect cotton leaf disease.

    ☘ Classification ofleaf disease by using texture features.

    ☘ To analyse leaf infection.

    ☘ Providing fast, automatic and accurate image-processing solution for the task can be of great
    significance.
    PROBLEM STATEMENT
    "To design and develop user friendly web based Cotton leaf detection
    system using Deep Learning"
    Requirements:
    Functional Requirements:
    There are a lot of software requirements specifications included in the functional
    requirements of the
    Cotton leaf disease detection system which contains various process like input the image,
    pre-processing, training the images, classification, providing description about the disease
    and pesticides.
    ∙ Input : The system enables the user to select the cotton leaf image as the input either by
    the live camera or by the stored image in the device.
    ∙ Pre-Processing : Pre-processing refers to the transformations applied to our data before
    feeding it to the algorithm. Data Preprocessing is a technique that we used to convert
    the raw data into a clean data set.
    ∙ Training : Training images will be providing the data that models use to learn and
    improve. When used, training images have been made our models to achieve better
    results and be more accurate.
    ∙ Classification : Our model will be able to classify whether the give input cotton leaf is
    effected by the disease or not. And also provide which type of disease has been effected
    to the leaf.
    ∙ Description : The model will provide complete and detailed information about the
    disease that has effected the leaf.
    ∙ Pesticides : Our model will provide the related pesticides or the medicines for the
    particular disease.
    Non-Functional Requirements:
     
    ∙ Usability : The application is user friendly and easy to use for a user it makes user
    to select the input images through live camera or by the stored image.

    ∙ Reliability : The models accuracy is approximately 97.17% and without bugs and
    errors in the application hence the reliability of our system is appropriate and the
    system is available all the time.

    ∙ Scalability :  Serving more users, processing more data, and classifying many
    number of images and almost all diseases have been trained.
    Design:

    DATA FLOW DIAGRAM:


    USE CASE DIAGRAM:
    SYSTEM ARCHITECTURE:
    Sequence Diagram
    Implementation:Description Of Modules

    1. LOAD MODEL:
    ● Displays alert box to choose the model on first time launch.
    ● An user select the model (model.tflite) file.
    ● Selected model will be stored into the app data.
    ● User can upload the updated model.
    2. PICK IMAGE

    ● Allow image to be picked from file picker on Android


    5 to 12. On Android 13+ photo picker will be used.
    ● Allow image to be captured from the camera.
    ● Both functionalities doesn’t requires Camera and
    Internal Storage permission. This app uses SAF
    framework for more privacy.
    ● The image which is picked will be stored in cache
    directory and will be deleted automatically when user
    comes back to the first screen of the app.
    3. SETUP IMAGE CLASSIFIER

    ● Initialize base option builder with some number of threads and


    use Neural Network API for accelerated image classification.
    ● Initialize options with threshold value, max number of output
    and set base option as base option builder.
    ● Use the model path and above options for Image Classifier.
    4. CLASSIFY DISEASE

    ● The picked image will be converted into bitmap image.


    ● The bitmap image is then processed as tensor image.
    ● The image is then resized and normalized.
    ● Classify the disease with confidence.
    5. INFORMATION

    ● Display the information about the classified disease with image.


    ● Control measure option where user can see the control measure for that
    disease.

    6. CONTROL MEASURES

    ● Display the control measures about the classified disease with


    image.
    REFERENCES
    • Deep Neural Networks Based Recognition of Plant Diseases by Leaf Image Classification
    Dubravko Culibrk,2 and Darko Stefanovic1 Hindawi Publishing Corporation
    Computational Intelligence and Neuroscience Volume 2016, Article ID 3289801.

    • J.D Pujari, R. Yakkundimath, and A.S Byadgi, “Identification and classification of fungous
    disease affected on agriculture/horticulture crops using image processing techniques,”
    IEEE International Conference on the Computational Intelligence and Computing
    Research,2014.

    • Balasubramaniam Vijayalakshmi and Vasudev Mohan, “Kernel based PSO and FVRM: An
    automatic plant leaf type detection using texture, shape and color features,” Computer
    and Electronics in Agriculture, vol.125 , pp. 99-112, 2016.

    • S. Arivazhagan,R. Newlin Shebiah,S Ananthi and S. Vishnu Varthini, “Detection of


    unhealthy region of plant leaves and classification of plant leaf disease using texture
    features,” Commision Internationale du Genie Rural(CIGR) journal,vol.15, no.1, pp.211-
    217, 2013.
    Paper Publication Status:
     
    Submission of paper in IEEE platform is done,
    and the paper is under review.
    🍀Thank you🍀

    You might also like