Klasifikasi Penyakit Padi berdasarkan Citra Daun Menggunakan Model
Terlatih Resnet101

Klasifikasi Penyakit Padi berdasarkan Citra Daun Menggunakan Model
Terlatih Resnet101

Classification, Disease, Rice, Image, Pretrained model, ResNet101.

Rice is a staple food source for most countries in the world, including Indonesia. The problem of rice disease is a problem that
is quite crucial and is experienced by many farmers. Approximately 200,000 - 300,000 tons per year the amount of rice attacked
by pests in Indonesia. Considerable losses are caused by the disease of rice plants that are too late to be diagnosed so that
they reach a severe stage and cause crop failure. Ignorance of farmers as well as limited and lack of information about diseases
and proper treatment are factors that cause delays in handling rice diseases. Therefore, in this study the developed model can
classify three types of rice plant diseases using Rice Leaf Disease images. The three types of disease include: Bacterial Leaf
Blight, Brown Spot, and Leaf Smut. The model developed using the transfer learning method with a pretrained model of
Resnet101 with additional architectural layer in the Fully Connected Layer section in the form of: Dense Layer, Dropout
Layer, and Batch Normalization Layer. The proposed method shows a classification performance of 100% on validation data,
with a loss value of 5.61%.

Ulfah Nur Oktaviana
1
, Ricky Hendrawan
2
, Alfian Dwi Khoirul Annas3
, Galih Wasis Wicaksono4

Universitas Muhammadiyah Malang

: 31-12-2021

Fajar bagus W

PDF

Indonesia

Text