Minor 1 Review2

DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING
SCHOOL OF COMPUTING
10214CS601 MINOR PROJECT -1
SUMMER SEMESTER(2023-2024)
REVIEW-II
“LEAF DISEASE DETECTION USING CNN ALGORITHM”
SUPERVISED BY
PRESENTED BY
Dr.S.Lalitha,B.Tech.,M.E.,Ph.D.,
1.T.Narasimha Reddy (VTU19381)(REG NO:21UECS0466)
2.T.Dharma Reddy (VTU19934)(REG NO:21UECS0477)
3.N.Ravindra Babu (VTU20580)(REG NO:21UECS0553)
January 22, 2024 DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING / LEAF DISEASE DETECTION USING CNN 1
OVERVIEW
ABSTRACT
OBJECTIVE
INTRODUCTION
LITERATURE REVIEW
DESIGN AND METHODOLOGIES
IMPLEMENTATION
TESTING
INPUT AND OUTPUT
CONCLUSION
WEB REFERENCES LINK
PLAGIARISM REPORT OF PPT
REFERENCES
ABSTRACT
• Leaf detection plays a crucial role in ensuring the health and productivity of crops in farming. In
this study, we propose a novel approach for disease detection in crops.
• The system is designed to be trained through supervised learning, where a dataset of labeled
crop images, consisting of both healthy and diseased samples, is used to train a predictive
model.
• The proposed system utilizes advanced computer vision techniques to analyze images of crops
and accurately identify signs of diseases.
• Deep learning algorithms are employed to extract meaningful features from the images,
enabling the model to learn complex patterns and discriminate between healthy and diseased
plants.
• The training process involves optimizing the model parameters to minimize the prediction error
and enhance the system's accuracy.
OBJECTIVES
Aim of the Project:
• The aim of this project is developing sustainable and eco-friendly solutions for crop
disease management.
• The ultimate goal of this project is to create an actionable framework for farmers and
promoting the adoption of sustainable solutions to mitigate crop diseases and secure food
production in a changing world.
Scope of the Project:
• The scope for “Leaf Disease Detection Using CNN Algorithm" involves developing eco-
friendly approaches to mitigate the impact of diseases on crops.
• This includes exploring organic pesticides, resistant crop varieties, precision agriculture
technologies, and integrated pest management strategies.
TIMELINE OF THE PROJECT
INTRODUCTION
• Agriculture is a crucial sector in the Indian economy, providing employment to nearly 50% of the
workforce.
• Approximately 70% of the population in India depends on agriculture, with 80% of farmers being
small-scale or marginal.
• Almost 50% of crop loss is attributed to plant diseases, highlighting the importance of disease
detection in the agriculture sector.
• The following outlines the key aspects of the project, from its purpose to the methodologies employed
in creating a system that adapts to the ever-changing educational needs of the community.
• Early detection of plant diseases is crucial as it can prevent significant losses and enable timely
intervention.
• This introduction explores the vital role of plant disease detection systems in modern agriculture
• The need for sustainable agriculture practices is pressing, and early detection of plant diseases.
LITERATURE REVIEW
Author’s Name Paper name and Year of Main content of the paper
publication details publication
E. M. H. I. Ekanayaka, P. P. N. Machine Learning Approach 2022 The research emphasizes leveraging

V. Kumara for New Crop Disease Predict Machine Learning to predict and classify
and Alert System crop diseases in Sri Lanka, advocating for
an alert system to mitigate economic
losses for farmers and the nation.
Vijay Choudhary Comparative Analysis of 2021 The research delves into the economic
Machine Learning importance of agriculture in India,
Techniques for Disease proposing the application of machine
Prediction in Crops learning algorithms to advance early
prediction and control of crop diseases,
fostering sustainability in
agricultural practices.
Author’s Name Paper name and Year of Main content of the paper
publication details publication
Akshay Dhande Empirical Study of Crop- 2022 The paper reviews crop-imagery
disease Detection and Crop- algorithms, focusing on selecting the
yield Analysis Systems most effective algorithm based on
statistical parameters to expedite
system design for improved crop
disease detection and yield prediction
DESIGN AND METHODOLOGIES
MODULE 1:DATA COLLECTION AND MANIPULATION

MODULE 2:CNN Algorithm
MODULE 1: DATA COLLECTION AND MANIPULATION
Collection of data
MODULE 2: CNN Algorithm
• Convolutional Neural Networks (CNNs) revolutionize crop disease detection by autonomously extracting
meaningful features from images, streamlining the identification of plant health and diseases.
• In this process, diverse datasets containing labeled images of both healthy and diseased crops are
collected and preprocessed, ensuring uniformity for effective model training.
• The CNN architecture encompasses convolutional layers for detecting low-level features like textures and
edges, activation functions like ReLU for capturing non-linear relationships, and pooling layers to reduce
spatial dimensions while retaining essential information.
• The subsequent flattening and fully connected layers allow the network to learn global patterns and
relationships in the feature space.
• The output layer, typically employing the Softmax activation function, produces final predictions,
distinguishing between healthy crops and specific diseases.
• For real-world applications, the trained model can then predict the health status of crops from new images.
Fine-tuning and transfer learning strategies are employed to optimize model performance, especially when
dealing with limited datasets.
• CNNs, with their ability to automatically learn hierarchical features, prove invaluable in agricultural
contexts for early disease detection and precision farming efforts.
IMPLEMENTATION
Architecture Diagram
Data –Flow Diagram
Use Case Diagram
Class Diagram
Activity Diagram
Sequence Diagram
Collaboration Diagram
E-R Diagram
Architecture Diagram
This diagram illustrates how a smartphone can be used to diagnose the health of a leaf by
capturing, scanning, and processing its image. The system compares the leaf image with a database of
healthy and diseased leaves and returns a result that classifies the leaf as either healthy or diseased, with
a green or red color code. The system also provides a feedback loop that allows the user to adjust the
output until they are satisfied or stop the process.
Data –Flow Diagram
The diagram shows how a user interacts with a system that allows them to upload plant
images. The user first undergoes a check to verify their authorization. If the user is authorized,
they can proceed to upload a plant image and then log out of the system. If the user is not
authorized, they are labeled as an unauthorized user and the process ends. The diagram uses
different shapes and arrows to represent the steps and the flow of data in the process.
Use Case Diagram
The diagram shows how a user interacts with a system for a plant image uploading
application. The user can register, login, upload a plant image, and logout. Each oval
represents a different use case or action that the user can perform. The lines connecting the
“User” icon to each oval indicate that the user has the option to execute these actions
Class Diagram
The diagram shows how a user interacts with a system for a plant image uploading
application. The user can register, login, upload a plant image, and logout. Each oval represents
a different use case or action that the user can perform. The lines connecting the “User” icon to
each oval indicate that the user has the option to execute these actions.
Activity Diagram
The activity diagram shows the steps involved in uploading plant images on a platform. The
process starts with the user registering and logging in to their account. After that, they can upload as
many plant images as they want by selecting the option from the menu. The process ends when the
user logs out of their account. The diagram uses ovals to represent the user and the start and end
points, and rectangles to represent the actions.
Sequence Diagram
This image is a sequence diagram that shows how a user can interact with a database to
register, login, upload a plant image, and logout. The diagram has four numbered arrows that
represent the actions that the user performs and the communication that occurs between the user
and the database. The diagram uses standard symbols such as boxes and arrows to depict the
entities and interactions involved in this process.
E-R Diagram
Collaboration Diagram
The collaboration diagram shows how a User interacts with a Database through four steps:
Register, Login, Upload plant Image, and Logout. The User is an object that initiates the
interaction, and the Database is an object that responds to the messages from the User. The
diagram illustrates the flow of data and control between the User and the Database, as well as
the states of the objects during the interaction. The diagram can help to understand the
requirements and design of the system, as well as to identify potential errors or improvements.
TESTING
UNIT TESTING
INTEGRATION TESTING
FUNCTIONAL TESTING
WHITE BOX TESTING
BLACK BOX TESTING
January 22, 2024 DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING / PROJECT TITLE 21
UNIT TESTING
Unit testing involves the design of test cases that validate that the internal program logic is functioning
properly, and that program inputs produce valid outputs. All decision branches and internal code flow should be
validated. It is the testing of individual software units of the application .it is done after the completion of an
individual unit before integration. This is a structural testing, that relies on knowledge of its construction and is
invasive. Unit tests perform basic tests at component level and test a specific business process, application,
and/or system configuration. Unit tests ensure that each unique path of a business process performs accurately
to the documented specifications and contains clearly defined inputs and expected results.
INTEGRATION TESTING
Integration tests are designed to test integrated software components to determine if they actually run as
one program. Testing is event driven and is more concerned with the basic outcome of screens or fields.
Integration tests demonstrate that although the components were individually satisfaction, as shown by
successfully unit testing, the combination of components is correct and consistent. Integration testing is
specifically aimed at exposing the problems that arise from the combination of components.
SYSTEM TESTING
System testing ensures that the entire integrated software system meets requirements. It tests a
configuration to ensure known and predictable results. An example of system testing is the configuration
oriented system integration test. System testing is based on process descriptions and flows, emphasizing
pre-driven process links and integration points.
FUNCTIONAL TESTING
The functional tests help in providing the systematic representation that functions tested are
available and specified by technical requirement, documentation of the system and the user manual.
INPUT AND OUTPUT
SOURCE CODE
OUTPUT
CONCLUSION
This Project presents an automated, low cost and easy to use end-to-end solution to one of the
biggest challenges in the agricultural domain for farmers – precise, instant and early diagnosis of
crop diseases and knowledge of disease outbreaks - which would be helpful in quick decision
making for measures to be adopted for disease control. This proposal innovates on known prior art
with the application of deep Convolutional Neural Networks (CNNs) for disease classification,
introduction of social collaborative platform for progressively improved accuracy, usage of geocoded
images for disease density maps and expert interface for analytics. High performing deep CNN
model “Inception” enables real time classification of diseases in the Cloud platform via a user facing
mobile app. Collaborative model enables continuous improvement in disease classification accuracy
by automatically growing the Cloud based training dataset with user added images for retraining the
CNN model. User added images in the Cloud repository also enable rendering of disease density
maps based on collective disease classification data and availability of geolocation information
within the images. Overall, the results of this experiments demonstrate that the proposal has
significant potential for practical deployment due to multiple dimensions – the Cloud based
infrastructure is highly scalable.
Plagiarism Report of PPT
REFERENCES
[1] A. Krizhevsky, I. Sutskever and G. E. Hinton, ”Imagenet classification with deep convolutional neural
networks,” in Advances in Neural Information Processing Systems, 2012.
[2] C. B. Wetterich, R. Kumar, S. Sankaran, J. B. Junior, R. Ehsani and L. G. Marcassa, “A comparative study
on application of computer vision and fluorescence
imaging spectroscopy for detection of huanglongbing citrus disease in the USA and Brazil,” in Journal of
Spectroscopy, 2013.
[3] D. L. Hern ́andez-Rabad ́an, F. Ramos-Quintana and J. Guerrero Juk, “Integrating soms and a bayesian
classifier for segmenting diseased plants in uncontrolled environments,” 2014, in the Scientific World Journal,
2014.
[4] D. P. Hughes and and M. Salath ́e, “An open access repository of images on plant health to enable the
development of mobile disease diagnostics through machine learning and crowdsourcing,” in CoRR
abs/1511.08060, 2015.
[5] E. L. Stewart and B. A. McDonald, “Measuring quantitative virulence in the wheat pathogen
Zymoseptoria tritici using high-throughput automated image analysis,” in Phytopathology 104 9, 2014, pp.
985– 992.
[6] S. Raza, G. Prince, J. P. Clarkson and N. M. Rajpoot, “Automatic detection of diseased tomato plants
using thermal and stereo visible light images,” in PLoSONE, 2015.
[7] S. Sankaran, A. Mishra, J. M. Maja and R. Ehsani, “Visible-near infrared spectroscopy for detection of
huanglongbing in citrus orchards,” in Computers andElectronics in. Agriculture 77, 2011, pp. 127–134.
THANK YOU
January 22, 2024 DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING / SUSTAINABLE SOLUTIONS FOR CROP DISEA 33
SE MANAGEMENT

Minor 1 Review2

Uploaded by

Document Information

Original Description:

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Minor 1 Review2

Uploaded by

Copyright:

Available Formats

DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING

“LEAF DISEASE DETECTION USING CNN ALGORITHM”

Aim of the Project:

Scope of the Project:

E. M. H. I. Ekanayaka, P. P. N. Machine Learning Approach 2022 The research emphasizes leveraging

MODULE 1:DATA COLLECTION AND MANIPULATION

You might also like