Plant Disease Detection System

Authors: Amrita Bharani, Apoorva Tripathi, Aishly Manglani, Anupama Sahu, Pir Mohammad

Certificate: View Certificate

Abstract

One of the most important and tedious tasks in agriculture practices is detection of diseases on crops.It is a noteworthy risk to the growth and quality of the crop and affects the yield of crops. Early detection of these diseases still proves to be troublesome.The recent expansion of deep learning methods has found its application in plant disease detection, offering a robust tool with highly accurate results. This is an efficient step towards sustaining the crop and increasing the yield and thereby giving good profit to the farmers.The main aim of the proposed work is to find a solution to the problem of 38 different classes of plant diseases detection using the simplest approach while making use of minimal computing resources to achieve better results compared to the traditional models. VGG16 training model is deployed for detection and classification of plant diseases. Neural network models employ automatic feature extraction to aid in the classification of the input image into respective disease classes.

Introduction

In India the major population relies on agriculture as their source of income.India ranks second globally in terms of farm yields. It was reported in the year 2018 that agriculture opened the doors of employment for more than 50? of the employees, hence contributing to 18–20% to country's GDP. India has thus proven to be one of the leading nations in terms of agricultural yield and productivity.It becomes very crucial to recognize the problems faced in this sector. There are several challenges faced by the farmers which act as a barrier to their income. The major one is the losses in yield caused by crop diseases. It’s hard to observe and take care of plant diseases manually and needs a good amount of effort and a good expertise in plant diseases which is a barrier to farmers as most of them are illiterate and don’t have the adequate knowledge for those diseases.

Conclusion

Plant diseases have been a significant concern in agriculture for years. Precision agriculture has enabled early disease detection and the minimization of losses through optimal decisions based on the results of DL methods.This paper proposes a CNN based method for plant disease classification using the leaves of diseased plants. Building such a neural network with high efficiency is a complex task. Transfer learning can be employed to achieve greater efficiency . Inception v3 is one of the models available that inherently have the capability to classify images and further can be trained to identify different classes.This project utilized to build 14 different plant leaf disease identification, detection and recognition systems.The neural network is trained with the Plant Village dataset. A Graphical User Interface is designed for this system. This GUI permits the user to choose the images from the dataset. Users can select any image from the dataset and the image gets loaded, following which the prediction of the disease will be shown on the User Interface. Convolutional neural network, trained for identifying and recognizing the plant leaf disease