Klasifikasi Penyakit Tanaman Tomat Melalui Citra Daun Menggunakan Metode Convolutional Neural Network

Ahmad Choirul  Anwari

doi:10.70294/jimu.v2i03.421

Penulis

Ahmad Choirul Anwari Universitas Muhammadiyah Ponorogo

DOI:

https://doi.org/10.70294/jimu.v2i03.421

Kata Kunci:

Tomato Plants, Deep Learning, Convolutional Neural Network

Abstrak

This study aims to classify tomato plant diseases through leaf imagery using the Convolutional Neural Network (CNN) method. Tomatoes are a major commodity in the agricultural industry that are susceptible to various diseases, such as root rot and leaf blight, which can damage crop yields and farmers' economies. Disease classification has traditionally been often inefficient and inaccurate. Therefore, the CNN method is applied in this study to identify tomato leaf disease effectively. The dataset used consisted of 4000 images of tomato leaves divided into four categories: bacterial spot, early blight, healthy, and late blight. The results showed that the developed CNN model had an accuracy of 88% on training and validation data. This model is also able to classify diseases with a good level of accuracy in the test data, namely bacterial spot (90%), early blight (100%), healthy (70%), and late blight (80%). This study proves that the CNN method is effective in classifying diseases in tomato leaves, so that it can be used as an accurate diagnostic tool for farmers.

Unduhan

Data unduhan belum tersedia.

Referensi

M. Muslih dan A. D. Krismawan, “Klasifikasi Penyakit Daun Tomat Berbasis Algoritma K-Nearest Neighbor,” semnasristek, vol. 8, no. 01, Jan 2024, doi: 10.30998/semnasristek.v8i01.7141.

S. Sheila, I. Permata Sari, A. Bagas Saputra, M. Kharil Anwar, dan F. Restu Pujianto, “Deteksi Penyakit Pada Daun Padi Berbasis Pengolahan Citra Menggunakan Metode Convolutional Neural Network (CNN),” Jurnal Multimedia Networking Informatics, vol. 9, no. 1, hlm. 27–34, Apr 2023, doi: 10.32722/multinetics.v9i1.5255.

K. I. Nauval dan S. Lestari, “Implementasi Deteksi Objek Penyakit Daun Kentang dengan Metode Convolutional Neutral Network,” jatim, vol. 3, no. 2, hlm. 136–149, Nov 2022, doi: 10.31102/jatim.v3i2.1576.

A. M. Tama dan R. C. N. Santi, “Klasifikasi Jenis Tanaman Hias Menggunakan Metode Convolutional Neural Network (CNN),” INTECOMS, vol. 6, no. 2, hlm. 764–770, Sep 2023, doi: 10.31539/intecoms.v6i2.7002.

A. Pribadi dan Ade Kurniawan, “Deteksi Penyakit Sawit Menggunakan Metode Deep Learning,” JUSIT, vol. 5, no. 2, hlm. 72–76, Des 2022, doi: 10.59061/jsit.v5i2.86.

P. Palupiningsih, A. R. Sujiwanto, dan R. R. B. P. Prawirodirjo, “Analisis Perbandingan Performa Model Klasifikasi Kesehatan Daun Tomat menggunakan arsitektur VGG, MobileNet, dan Inception V3,” JIKA, vol. 10, no. 1, hlm. 98–110, Jun 2023, doi: 10.29244/jika.10.1.98-110.