SIDDAGANGA INSTITUTE OF TECHNOLOGY,
TUMKUR
Department of Computer
Mini project presentation on
Science and
Engineering
“CROP DIESEASE DETECTION”
BATCH ID : A5
Presented by:
ANUSHEKHAR NAIK S 1SI21CS016
BHARATH T S 1SI21CS029
MITHUN G N 1SI21CS062
Under the guidance of:
[Link] S
Assistant Professor
Agenda
Introduction
Motivation
Literature Survey
Problem Statement
Aim & Objectives
High Level Design
Tools and Technology
Expected Outcomes
Conclusion
Introduction to the
project
This work presents a machine learning model, in the form of a
Jupyter Notebook. The project aims to utilize machine learning
for crop disease detection, addressing the critical issue of
identifying and mitigating plant diseases. By leveraging
advanced algorithms, the system will analyze images of crops to
diagnose diseases accurately, enabling timely intervention and
improved yield. Additionally, it will contribute to sustainable
agricultural practices and food security. This provides young
farmers with a variety of options of crops that can be cultivated.
Motivation to Project
The agriculture system is supported by farmers. Agriculture, as is well known, is
an integral part of a country's development. Agriculture is very important in
India's economy and job market. One of the most common problems faced by
Indian farmers is that they do not choose the appropriate crop for their soil. One
of the most popular issues that Indian farmers face is failing to protect their
crops/plants in time from diseases.
Addressing Crop Sustainable Improving Food
Losses Agriculture Security
Using machine learning By detecting diseases Efficient disease
for crop disease accurately, sustainable detection can
detection can help and eco-friendly contribute to stable
farmers identify and agricultural practices food production,
address diseases early, can be encouraged, enhancing global food
reducing crop losses. benefiting both farmers security and addressing
and the environment. hunger challenges.
Literature survey
Research Paper Name Description
"A review on machine learning-based This review paper presents an extensive survey of machine learning techniques used
crop disease identification" for crop disease identification. It categorizes different approaches based on feature
by H. Mehta et al. extraction methods, classification algorithms, and datasets used. The paper also
discusses the challenges and future directions in the field of crop disease
identification using machine learning.
"Deep learning for plant disease This review paper explores the recent advancements in deep learning techniques for
detection and diagnosis: A review" plant disease detection and diagnosis. It discusses the utilization of convolutional
by P. Singh et al. neural networks (CNNs) and other deep learning architectures for analyzing plant
images. The paper also addresses the challenges associated with large-scale dataset
acquisition and model interpretability.
"Using deep learning for image-based This research article presents a study on the application of deep learning algorithms,
plant disease detection" by particularly CNNs, for image-based plant disease detection. It describes the
S. Mohanty et al. development of a large-scale dataset of plant images and the training of CNN models
for disease classification. The paper evaluates the performance of different CNN
architectures and discusses the potential for real-world deployment of the
developed models.
Survey on crop disease detection This survey paper provides a comprehensive overview of various machine learning
using machine learning techniques" techniques employed for crop disease detection. It covers topics such as feature
by A. Kumar et al. extraction methods, classification algorithms, and dataset characteristics. The paper
also discusses the challenges and future research directions in the field of crop
disease detection.
Problem Statement
Plant diseases have turned into a dilemma as it
can cause significant reduction in both quality
and quantity of agricultural products.
Challenges in Crop Disease Detection:
Limited availability of labeled training data for
various crop diseases.
Impact on Agriculture: The delay in disease
identification affects crop yield and quality,
leading to economic losses.
The proposed system is a software solution for
automatic detection and classification of plant
leaf diseases.
Aim
The aim of our project is to focus on one of the main challenges in agricultural
land i.e., disease prediction. The disease in crop plants affects agricultural
production, so a model is proposed to automate a method for the prediction of
disease in the plants.
Objectives
The objectives of the project are to develop, implement, validate, and optimize
the machine learning model for crop disease detection.
To lay the foundation for future research and development in the field of
computer vision and machine learning applications in agriculture.
To train and evaluate various machine learning models, such as Convolutional
Neural Networks (CNNs), Support Vector Machines (SVMs), or Random
Forests, to determine the most effective approach for crop
disease classification.
To conduct thorough testing and validation of the developed system using
diverse datasets, ensuring robustness and reliability under different
environmental conditions and disease stages.
To create a user-friendly interface that allows farmers, agricultural experts, or
researchers to easily upload plant images and receive instant
High Level Design
Tools and Platform
➢ Programming Language Used : Python
Python will serve as the primary programming language for implementing
various components of the project, Including backend development, machine
learning algorithms, and data processing tasks.
➢IDE used:
✶Jupyter Notebook
✶Visual Studio Code
➢ Convolutional Neural Network (CNN):
o CNNs will be employed as the machine learning algorithm for crop
disease detection.
o These neural networks are particularly effective for image classification
tasks, making them well-suited for analyzing images of crops to identify
diseases.
Tools and Platform
➢ Classification Algorithm:
✶ The classification algorithm, specifically CNN in this case, will
categorize images of crops into different classes representing healthy and
diseased states.
✶ This algorithmic approach allows for automated and accurate
identification of crop diseases based on visual patterns in the images.
✶ Algorithms such as: Logistic Regression , Decision tree model ,
Random Forest Classification , Naive Bayes Classification , Support vector
machine.
➢ HTML, CSS, and JavaScript:
✶ HTML: Used for creating the structure and content of the web-
based user interface for the crop disease detection system.
✶ CSS: Utilized to style and format the HTML elements, ensuring a
visually appealing and user-friendly interface.
✶ JavaScript: Provides interactivity and dynamic behavior to the
web application, allowing users to interact with the system and upload
Expected Outcomes
1 Improved Disease Detection
Using machine learning, the project aims to achieve more accurate
and timely detection of crop diseases.
2 Reduced Crop Loss
By identifying diseases early, the project intends to minimize crop
loss and improve overall yield.
3 Enhanced Farming Practices
The expected outcome includes promoting sustainable and
efficient farming practices through technology.
Conclusion
Through our project, we have demonstrated the potential of machine learning algorithms
to accurately identify and classify crop diseases, enabling farmers to swiftly detect and
respond to potential threats to their yields. This not only empowers farmers with timely
information for targeted interventions but also holds the promise of significantly
reducing yield losses and increasing agricultural productivity.
The introduction of the above scheme will aid in the betterment of our country's
agricultural practices. It can also be used to help farmers reduce their losses and
increase crop yields in order to increase their resources in agriculture. The model can be
strengthened by combining it with other departments such as horticulture, sericulture,
and others to help our country's agricultural production.
Thank you for your Attention!