Rice Leaf Disease Prediction Using Machine Learning

IEEE BASE PAPER ABSTRACT:

In the realm of agricultural data, automated detection and diagnosis of rice leaf diseases is greatly sought. Machine learning plays an important role here and can handle these difficulties in leaf disease identification rather well. We present a novel rice disease detection approach based on machine learning techniques in this paper. Here we have considered various rice leaf diseases and used different machine learning techniques for the classification of these diseases. In this study we first extract the features of rice leaf disease images. Then we apply various machine learning techniques in order to classify the images and found that an accuracy of 81.8% was achieved using Quadratic SVM classifier. Shape features such as area, roundness, area to lesion ratio, etc; were also used to differentiate between different types of rice diseases. The results obtained were good and met the required expectations.

PROJECT OUTPUT VIDEO:

ALGORITHM / MODEL USED:

MobileNetV2 Architecture.

OUR PROPOSED ABSTRACT:

A 37% annual decline in rice yield has been caused by the effects of rice plant diseases. There is yet no suitable application that has been developed that is capable of effectively diagnosing these rice plant diseases and controlling those diseases, thus it may occur mostly due to a lack of understanding in controlling rice plant diseases. The correct diagnosis of rice infections is essential for avoiding the disease’s substantial detrimental consequences on crop production. However, the current methods for diagnosing diseases in rice are neither precise nor effective, and frequently additional equipment is needed.

This project aims to develop a system that can predict the type of disease present on rice leaves using machine learning technique specifically MobileNetV2 architecture. The system uses image processing techniques and deep learning algorithms to classify the type of disease from the images of rice leaves. The proposed system uses MobileNetV2 architecture, which is a lightweight convolutional neural network (CNN) designed for mobile devices. The system is developed using Python programming language and several libraries such as Keras, TensorFlow etc. The dataset used in this project consists of images of rice leaves infected with four types of diseases: bacterial leaf blight, brown spot, rice leaf blast, and sheath blight.

The dataset is preprocessed to remove noise and improve the quality of the images. The preprocessed images are then used to train the model. The proposed system achieved a training accuracy of 98.34% and a validation accuracy of 95.21%. The system’s performance is evaluated using various performance metrics such as precision, recall, and F1-score. The results show that the proposed system outperforms the existing system, which uses a quadratic SVM classifier.

The proposed system can be used in the agricultural industry to detect diseases in rice crops and help farmers take necessary actions to prevent the spread of diseases. The system’s high accuracy and robustness make it a reliable tool for disease detection and prevention. Overall, the project demonstrates the effectiveness of machine learning techniques and deep learning algorithms in detecting diseases in rice crops. The proposed system’s high accuracy and efficiency make it a valuable tool for the agricultural industry.

SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS:

System : Pentium i3 Processor.
Hard Disk : 500 GB.
Monitor : 15’’ LED
Input Devices : Keyboard, Mouse
Ram : 4 GB

SOFTWARE REQUIREMENTS:

Operating system : Windows 10.
Coding Language : Python 3.8
Web Framework : Flask

REFERENCE:

Varun Pramod Bhartiya, Rekh Ram Janghel, Yogesh Kumar Rathore, “Rice Leaf Disease Prediction Using Machine Learning”, IEEE Conference, 2022.

Python IEEE Projects

Rice Leaf Disease Prediction Using Machine Learning