Klasifikasi Penyakit Tanaman Padi Berdasarkan Citra Daun Menggunakan Metode Convolutional Neural Network dan Transfer Learning

Zamil, Elsyafia Yasmin Putri (2025) Klasifikasi Penyakit Tanaman Padi Berdasarkan Citra Daun Menggunakan Metode Convolutional Neural Network dan Transfer Learning. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5003211027-Undergraduate_Theses.pdf - Accepted Version Restricted to Repository staff only Download (9MB) | Request a copy

Abstract

Padi merupakan komoditas pangan utama di Indonesia. Berdasarkan data BPS, produksi padi Indonesia diperkirakan mencapai 52 juta ton pada 2024, menurun dibandingkan tahun 2023 yang menghasilkan sekitar 53 juta ton. Salah satu penyebab penurunan produksi ini adalah penyakit tanaman padi. Penelitian ini bertujuan untuk mengembangkan model klasifikasi penyakit tanaman padi berdasarkan citra daun menggunakan metode Convolutional Neural Network (CNN) dan Transfer Learning, dengan arsitektur ResNet50 dan VGG16, untuk membantu pendeteksian penyakit. Data yang digunakan dalam penelitian ini adalah citra daun padi yang diperoleh dari platform Mendeley Data, yang mencakup empat kategori: Healthy, Brown Spot, Hispa, dan Leaf Blast. Metodologi yang digunakan melibatkan pengembangan model CNN serta penerapan arsitektur ResNet50 dan VGG16. Model-model ini dilatih dengan berbagai kombinasi hyperparameter untuk memperoleh performa terbaik. Evaluasi kinerja dilakukan menggunakan metrik seperti akurasi, presisi, recall, dan F1-score. Hasil penelitian menunjukkan bahwa ResNet50 menjadi model dengan performa terbaik, diikuti oleh VGG16, kemudian model CNN konvensional. Selain itu, uji coba terhadap gambar dari luar dataset menunjukkan bahwa ResNet50 memiliki kemampuan generalisasi yang baik. Penelitian ini diharapkan dapat memberikan kontribusi dalam pengembangan sistem deteksi penyakit tanaman padi berbasis citra, yang dapat membantu petani dalam pengelolaan penyakit tanaman secara lebih efektif.
=====================================================================================================================================
Rice is a primary food commodity in Indonesia. According to data from Statistics Indonesia (BPS), rice production in 2024 is estimated to reach 52 million tons, a decrease from approximately 53 million tons in 2023. One of the contributing factors to this decline is rice plant diseases. This study aims to develop a classification model for rice plant diseases based on leaf images using Convolutional Neural Network (CNN) and Transfer Learning methods, specifically utilizing the ResNet50 and VGG16 architectures, to support disease detection. The dataset used in this research was obtained from the Mendeley Data platform, comprising four categories: Healthy, Brown Spot, Hispa, and Leaf Blast. The methodology includes the development of a CNN model and the application of the ResNet50 and VGG16 architectures. These models were trained using various combinations of hyperparameters to obtain optimal performance. Model performance was evaluated using metrics such as accuracy, precision, recall, and F1-score. The results indicate that ResNet50 achieved the highest performance, followed by VGG16 and then the conventional CNN model. Furthermore, tests using external images demonstrated that ResNet50 has strong generalization capabilities. This study is expected to contribute to the development of image-based detection systems for rice plant diseases, which can assist farmers in managing crop health more effectively.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Tanaman Padi, Klasifikasi, CNN, Transfer Learning, Rice Plants, Classification, CNN, Transfer Learning
Subjects:	H Social Sciences > HD Industries. Land use. Labor > HD108 Classification (Theory. Method. Relation to other subjects ) Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines. Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science)
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User:	Elsyafia Yasmin Putri Zamil
Date Deposited:	01 Aug 2025 05:44
Last Modified:	01 Aug 2025 05:44
URI:	http://repository.its.ac.id/id/eprint/124798

Actions (login required)

View Item