An android based mobile application for fungal disease detection in cotton leaf

Our project involves developing an android application which will facilitate the farmer in identifying fungal diseases of cotton leaf by capturing picture of diseased leaf. And with the help of image processing and machine learning techniques the disease present in the leaf will be id

Project Title

An android based mobile application for fungal disease detection in cotton leaf

Project Area of Specialization

Artificial Intelligence

Project Summary

Our project involves developing an android application which will facilitate the farmer in identifying fungal diseases of cotton leaf by capturing picture of diseased leaf. And with the help of image processing and machine learning techniques the disease present in the leaf will be identified. As a result application will suggest the user the necessary remedies(Fungicides) for the treatment of disease. The application also requires the user(farmer) to register into the application by entering his/her necessary information.  

The user can also interact with an agriculture expert for queries and this expert will be provided by our application.  

Project Objectives

The problem is, identifying diseases with naked eye is not always accurate and farmer has to rely on agriculture experts which is sometimes time consuming and can be expensive also. So, the aim of our project is to facilitate the farmer with an easily accessible and inexpensive solution in the form of a mobile application.

Project Implementation Method

The project is being implemented in the following steps:

Firstly, images of fungal diseases are downloaded from internet. These images are used to create dataset which will be further used in classification. Then the aquired image is preprocessed to remove unnecessary noise and then color transformation is applied. After applying all the image preprocessing steps, image segmentation is done to segment the diseased part of leaf. Then features are  extracted from the segmented diseased image. These features are used for the training of SVM model to classify the disease and as a result name of the disease is displayed to the user on the screen. 

To use the application user is required to get registered first. So, all the details of user will be stored in the Firebase database.

Benefits of the Project

This mobile application will benefit both the farmer and the agriculture expert community. The farmers will be made aware of the importance of using IoT in agriculture. The main benefit is that this application is an easy and inexpensive solution for farmers in order to detect diseases in crops.

Technical Details of Final Deliverable

This project involves developing an android application on Android Studio. It also involves using an image processing library for the image preprocessing and segmentation. The image segmentation requires using an unsupervised learning algorithm called k-means clustering. SVM, which a supervised machine learning algorithm, is used for classification purpose. It is implemented in Python using Keras model and then the trained model is deployed in the android studio. 

Final Deliverable of the Project

Software System

Type of Industry

IT , Agriculture

Technologies

Artificial Intelligence(AI)

Sustainable Development Goals

Decent Work and Economic Growth, Industry, Innovation and Infrastructure

Required Resources

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