Rice Leaf Diseases Detection Using Machine Learning

Abstract

One of India's most widely grown crops, rice is susceptible to a wide range of illnesses during the growing process. Due to a lack of training and experience, farmers have a hard time making reliable diagnoses when identifying these illnesses manually. Timely detection of diseases and the application of necessary treatments to afflicted plants are crucial for ensuring healthy and normal development of rice plants. In today's agricultural fields, the detection of leaf diseases is of the utmost importance. Consequently, we may use machine learning to identify diseases in rice leaves by image processing. The agriculture sector is in dire need of a system that can identify rice plant problems automatically. We present a novel convolutional neural network (CNN) model for the classification of prevalent rice leaf diseases. From a variety of picture backdrops and capture situations, our algorithm can identify rice leaf illnesses. Classifying disease pictures in rice leaves with complicated backgrounds and varying lighting conditions is our goal. We reach 95% accuracy with the CNNs based model. The outcomes for disease identification in rice demonstrate the effectiveness of suggested approach. Disease detection, CNN algorithm, rice leaf, and machine learning are index terms.