PENERAPAN CNN VGG16 UNTUK KLASIFIKASI PENYAKIT DAUN PADI BERBASIS CITRA DIGITAL

APPLICATION OF CNN VGG16 FOR CLASSIFICATION OF RICE LEAF DISEASES BASED ON DIGITAL IMAGES

Nur Habib Nasidik
NIM : 212355201016

Supervisor 1 : Lailia Rahmawati, S.Kom.,M.Kom
Supervisor 2 : Winarti, S.Kom.,M.Kom

ABSTRACT

Rice is a major agricultural commodity in Indonesia, yet its productivity is often reduced due to diseases affecting the leaves, such as bacterial leaf blight, rice blast, brown spot, and tungro. Early detection of these diseases is crucial to prevent crop failure. This research aims to develop an automated system for detecting rice leaf diseases using a Convolutional Neural Network (CNN) algorithm with the VGG16 architecture. The dataset used in this study was obtained from Kaggle and consists of 5,932 leaf images classified into four disease categories. The research process includes data collection, preprocessing, model training, classification, and evaluation. The model was implemented using Python programming language and libraries such as TensorFlow and Keras. The evaluation was carried out using the Mean Average Precision (MAP) metric, which resulted in a score of 0.96, indicating that the model performs very well in identifying rice leaf diseases from images. The outcome of this study is expected to assist farmers in accurately and efficiently diagnosing plant diseases.