Detection of Tomato Plant Diseases Using Deep Learning

Plant diseases have always been a tricky problem in agricultural production and one of the main factors restricting the sustainable development of agriculture. Our software will be able to detect up to 3 diseases found in tomato plants. This project will be based on deep learning and will use a deep

Project Title

Detection of Tomato Plant Diseases Using Deep Learning

Project Area of Specialization

Artificial Intelligence

Project Summary

Plant diseases have always been a tricky problem in agricultural production and one of the main factors restricting the sustainable development of agriculture. Our software will be able to detect up to 3 diseases found in tomato plants. This project will be based on deep learning and will use a deep learning model to accurately detect the diseases. We will also be using an object detection model to detect the infected areas on the leaf. The datasets used in this project will be from the internet (Plant Village) and we will also be adding our own dataset. It will be divided into three sub-categories, training set, validation set and test set. We will be making a mobile application, in which user can take picture of tomato plant leaf and our app will identify whether the plant is healthy or have any disease in the case of disease it will also recommend its treatment. This proposed project model can efficiently identify up to 3 tomato diseases and the location of the infected part on the leaf. 

Project Objectives

The primary objective of this project is that it should be able to diagnose and detect the three diseases in the tomato plants and recommend their treatment.

A person will take a picture of a tomato plant leaf from his mobile phone using our mobile application and this app will detect whether the plant is healthy or is infected with the above-mentioned diseases. This app also recommends its treatment available in the local Pakistani market.

For this purpose, we will also be going to add our own dataset. In this dataset, we will expertly take 1000 pictures of each disease so that our app will be fine-tuned according to the local Pakistani climate. 

We are using a deep learning model to diagnose the plant leaf image. The accuracy of deep learning models is high and time complexity is low as compared to other traditional models. 

Our aim is to achieve accuracy more than the previous models available for the detection of tomato plant disease. We will be constantly improving our algorithms and datasets to increase accuracy. The scope of this project can also be increased in future by adding other plant diseases
 

Project Implementation Method

Our app is detecting tomato plant diseases using a deep learning model, we are training our model through tensor flow python library which is one of the best techniques to increase the accuracy of our project. After detecting the tomato plant diseases, it may also recommend its treatment. we are using FastApi for our server which use the POST method to send picture from our app to the server. The front end of this mobile app is in react native so our app will run both on android and iOS platforms. In this way, this app will be able to early detect tomato plant diseases that will increase the overall tomato plant 

Benefits of the Project

This application has huge scope in the modernization of the agricultural sector, this application helps in the early detection of tomato plant diseases and recommends its treatment which will be helpful in increasing the overall yield of the tomato plant. Since we are also adding our own dataset so this software is fine-tuned according to our local Pakistani climate

Technical Details of Final Deliverable

We are building our own custom application, which is using deep learning model to detect tomato plant diseases and also recommend their treatment. The major application component is users can take pictures of plant leaves from our app and with the help of a deep learning model users can get information about diseases the plant is suffering from. For this purpose, we are using Plant Village Dataset and we are also trying to add our own dataset. Since we are using the mobile application as a user interface so the front end of our mobile app is built on react native which is a framework of JavaScript and for the backend we are using python through Tensor flow which is a library of machine learning that helps in deep neural networking, for database we are using firebase. The basic application architecture is a user will be using the front end only and which is connected to the back end server which helps in the processing of data and send back result to the front end in this way user get his required result, all the information of the user stored in a database so that only authentic users can enter our app only.

Final Deliverable of the Project

Software System

Core Industry

Agriculture

Other Industries

IT

Core Technology

Artificial Intelligence(AI)

Other Technologies

Others

Sustainable Development Goals

Good Health and Well-Being for People, Decent Work and Economic Growth, Industry, Innovation and Infrastructure

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com