Artificial Intelligence based Crop Recommendation and Plant Leaf Disease Detection System

Abstract

Identification of plant diseases and providing a remedy is crucial to eliminate farm losses and increase agricultural yield. Every year farmers must bear huge damages due to plant diseases as well as inaccurate choice of crop. The diseases in plants every time cannot be identifies by the naked eye. Also, contacting farm experts is not always feasible. Hence, the use of technology to address the said problems becomes important. Keeping this in mind, the authors have developed a system that tells the farmers the type of crop disease from an image and instantly give a solution for the same. Moreover, suitable crop is also suggested based on the soil type and contents, moisture, temperature, humidity, and other environmental conditions. A deep learning algorithm known as Convolution Neural Network (CNN) is used by authors for detection of plant diseases. Suitable crop is recommended using Random Forest Algorithm. An accuracy of 98% is achieved in plant disease detection, while the crops are being recommended with an accuracy of 99%. The system is developed in the form of a website where the farmers can upload an image and the disease type, and its remedy is displayed immediately. Suitable crop is also being advised to the farmers according to the parameters. A platform to buy and sell products online will help the farmers grow in an increasingly digital world. A discussion forum has also been added so that farmers can have their questions answered by the agricultural experts. This paper aims to ease the life of the farmers.