An IoT based plant health monitoring system implementing image processing

Abstract

The combination of internet of things (IoT) with environmental sensing and image processing device has opened a new era to monitor the health of plants. Classification of plant diseases in early stages using image processing and analyzing environmental sensing data not only helps farmers to get healthy plants but also maximize the production. To monitor and classify plant diseases IoT is essential to send images and give feedback on it. In this paper, a raspberry pi based IoT device is proposed which sends images of plants to classify diseases and updates environmental parameters like air temperature, humidity, soil moisture and pH in MySQL database in real-time. To segment the affected part of plant, k-mean cluster algorithm is used after performing preprocessing stage and converting into L*a*b color space. Multi-class support vector Machine (SVM) is applied to categorize disease using fourteen types of features of color, texture and shape obtained when implementing gray level co-occurrence matrix where the system was able to classify with an accuracy of 97.33%. Thus, classifying diseases and analyzing environment parameters help farms to monitor plant growth efficiently for better production.