Identification of Rice Leaf Disease Using Convolutional Neural Network Based on Android Mobile Platform

Abstract

Rice is a rice-producing plant that is susceptible to disease so it can make it difficult for farmers to identify the types of diseases that exist in rice leaves. On the other hand, farmers need convenience in identifying diseases that exist in rice leaves more effectively and efficiently. Seeing the development trend of deep learning and mobile android, we need an application that can help farmers to analyze diseases in leaves effectively and efficiently. This research was conducted in several stages including literature study, application design and manufacture, application testing and analysis as well as conclusion drawing and report writing. With deep learning technology, a Convolutional Neural Network (CNN) model was developed on Tensorflow lite and stored in the ML Kit service. Furthermore, the model can be embedded in a detection application built on the android mobile platform. This is to assist farmers in identifying healthy and unhealthy rice leaves. The results of the development of the algorithm and its application to an Android-based mobile application can run well where the level of accuracy generated from the model formed in classifying disease images on rice leaves in this study is 80%.