Scribd
Upload
29 views16 pages

Tomato Disease Detection Using CNN

The document describes a project that uses a convolutional neural network (CNN) to detect diseases in tomato plants from images. The project aims to train a CNN model using a dataset of labeled tomato images to automatically classify images as healthy or diseased, and identify the specific disease. The document outlines the methodology, including collecting a dataset, preprocessing the images, selecting and training a sequential CNN model, and developing a user interface for the system. It presents results showing the model achieved 97.61% accuracy on the tomato disease classification task.

Uploaded by

karnsushantlal
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
29 views16 pages

Tomato Disease Detection Using CNN

The document describes a project that uses a convolutional neural network (CNN) to detect diseases in tomato plants from images. The project aims to train a CNN model using a dataset of labeled tomato images to automatically classify images as healthy or diseased, and identify the specific disease. The document outlines the methodology, including collecting a dataset, preprocessing the images, selecting and training a sequential CNN model, and developing a user interface for the system. It presents results showing the model achieved 97.61% accuracy on the tomato disease classification task.

Uploaded by

karnsushantlal
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 16

Tomato Leaf Diseases Detection

Using CNN
Presented By-
Rajan Mahato [PUR076BCT061]
Shree Krishna Yadav [PUR076BCT082]
Nitesh Kumar Singh [PUR076BCT053]
Rajesh Sharma [PUR076BCT064]
Introduction

 Tomato Disease Detection project use CNN to develop an automated system that can
identify and classify diseases affecting tomato plants.
 By using deep learning algorithms and a diverse dataset of labeled tomato plant images,
the project aims to train a model capable of distinguishing between healthy and diseased
plants, providing timely recommendations for treatment.
What is CNN and Why we used CNN in our
Project?
 CNN stands for Convolutional Neural Network. It is a type of artificial neural network that
is specifically designed for processing and analyzing visual data such as images.
 The key reason we are using CNNs for image analysis is its ability to automatically learn
and extract meaningful features from images.
 Traditional neural networks struggle with image data because they assume that each input
feature (pixel) is independent of the others. However, in images, neighboring pixels often
contain important information and exhibit spatial relationships.
 CNNs are designed to address this issue through two key components: convolutional layers
and pooling layers.
Problem Statement

 Automatic detection of commonly present diseases in tomato plants is essential.


 Automatic detection of the symptoms of diseases as soon as they appear on plant leaves.
 The proposed system is automated software solution for detection and classification of
diseases in tomatoes.
Specific to Tomato Diseases

Significance
 Early Disease Prevention and Control
 More accurate and objective
 Cost effective and Efficient

Limitation

 Depends on Image Quality


 Specific to Tomato Diseases
 Regular updates
Objective

 To create an automated system that can recognize and classify different class of diseases
affecting tomatoes according to patterns found on visual images.
 To Gain hands-on experience in developing and implementing a machine learning model,
specifically a Convolutional Neural Network (CNN), for image analysis.
METHODOLOGY
 Data collection:
 A diverse dataset of tomato plant images was collected from Tomato leaf disease detection
Dataset from Kaggle. The dataset consisted of both healthy and diseased tomato plants,
covering 9 disease types.
 Data preprocessing and augmentation:
 For data preprocessing we have created a input pipeline using tensorflow and for augmentation we have
done random flip and random rotation.
 Model selection
 We have selected sequential model in CNN .

 Model training and evaluation


 For model training we have split dataset into two parts , 80% data for training and 20% data for testing.
In which 10% of data is used for validation and 10% of data is used for testing.
 User Interface and deployment
 The deployment of CNN based classification is implemented through the Website.
Block Diagram of the System.
Flowchart of the System
System Sequence Diagram
Training and validation accuracy graph
Results and Output

Homepage
Conclusion

We have developed a CNN based model to detect the disease in tomato plant. In the CNN
model, there are four convolution and max pooling layers with different filters in each layer,
the tomato leaf image from plant village dataset which have 10 classes including the healthy
leaf images. The dataset we used for the experiment is a three-color channel dataset by
applying various dropout values, augmented, and segmentation techniques. In the first
experiment while we make the epoch size to be 50, the model accuracy would achieve 97.61%
performance results, which is a promising result.
Time Schedule
References
[1] Das, S. Over View of Septoria Diseases on Different Crops and Its
Management. Int. J. Agric. Environ. Biotechnol. 2020, 13, 361–370. [Online]. Available:
https://doi.org/10.1094/PDIS-05-20-1096-PDN. [Accessed Feb. 2, 2023].
[2] Srdjan Sladojevic, Marko Arsenovic, Andras Anderla, Dubravko Culibrk,
Darko Stefanovic, "Deep Neural Networks Based Recognition of Plant Diseases by
Leaf Image Classification", Computational Intelligence and
Neuroscience, vol. 2016, Article ID 3289801, 11 pages, 2016. [Online]. Available:
https://doi.org/10.1155/2016/3289801. [Accessed February 3, 2023].
[3] Durmus, H.; Gunes, E.O.; Kirci, M. Disease Detection on the Leaves of the
Tomato Plants by Using Deep Learning. In Proceedings of the 2017 6th
International Conference on Agro-Geoinformatics, Fairfax, VA, USA, 7– 10 August
2017; IEEE: Piscataway, NJ, USA, 2017; pp. 1–5. [Online]. Available: https
://ieeexplore.ieee.org/document/8047016. [Accessed March 2, 2023]
THANK
YOU

You might also like