Rice Plant Disease Detection Using Image Processing and Probabilistic Neural Network

Abstract

Considering the worldwide rice consumption, it is seen that rice has an important place. The rice plant is the most cultivated plant after corn and wheat from the grass family. One of the latest research topics in agriculture is the identification or classification of diseases from images of a plant's leaves. In this study, a computer-aided classification system has been developed to detect whether the rice plant is diseased or not. This developed system consists of four different stages. These are image pre-processing, segmentation, feature extraction, and classification. First, the images were pre-processed with the median filtering method, then OTSU method was used for segmentation. The GLCM (Gray Level Co-occurrence Matrix) method was used to extract the features of the segmented images. Then, it was determined whether the rice plant is diseased from the image by using the Probabilistic Neural Network (PNN), one of the Artificial Neural Networks (ANN) models. An interface has been developed to do all these stages from one place. The accuracy rate of this system, which detects the disease of the rice plants, was determined as 76.8%. © 2022, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.