Real-Time Agriculture Plant Leaf Monitoring and Disease Identification System using Raspberry Pi

Authors

  • T. Nagaraju, B. Malleswari

DOI:

https://doi.org/10.17762/msea.v70i2.1640

Abstract

The production of agricultural goods is an essential need for any nation. Monitoring the elements in the environment is an important step, but it is not the only way to increasing agricultural yields. The range of crops that may be grown in India is quite broad. More than five hundred different kinds of crops are cultivated there. If plants are afflicted by diseases, then farmers have a very tough work ahead of them in terms of monitoring plant leaves. As a result, the agricultural productivity of the nation and its economic resources are both negatively impacted.The reasons for this include a decrease in the number of specialized farmers and a shortage of human resources in the field of plant pathology. Using methods such as image analysis and accurately predict and detect pests and diseases and pests at an early stage can reduce the workload of farmers and prevent economic losses in advance.In this project use a novel method by combining the both Azure services and IoT will lead to increase the disease identification. This will give a farmer for better results to increase the yield of crops. Raspberry Pi is the brain of our project to do different tasks, in part cares of irrigation and another will take care of plat leaf images. The system has Raspberry Pi along with the camera module. Camera module capture the leaf image and sends for classification result, azure custom vision will play crucial role for classification the disease. IoT Edge will send the information to cloud for action taken. This system gives better results to produce the yield of crops.

Downloads

Published

2021-12-31

How to Cite

T. Nagaraju, B. Malleswari. (2021). Real-Time Agriculture Plant Leaf Monitoring and Disease Identification System using Raspberry Pi. Mathematical Statistician and Engineering Applications, 70(2), 382–399. https://doi.org/10.17762/msea.v70i2.1640

Issue

Section

Articles