KLASIFIKASI KEMATANGAN BUAH TOMAT BERBASIS CNN DENGAN ARSITEKTUR MOBILENETV2 DAN TRANSFER LEARNING
Abstract
Classifying tomato ripeness is a crucial aspect of post-harvest processing and agricultural distribution. Manual ripeness determination is subjective and potentially inconsistencies. This study aims to classify tomato ripeness using a deep learning approach based on a Convolutional Neural Network (CNN) with the MobileNetV2 architecture and transfer learning techniques. The dataset, consisting of tomato images, was classified into three classes: unripe, ripe, and overripe. Preprocessing included image resizing and normalization before model training. The MobileNetV2 model was used as a feature extractor, while a fully connected layer was applied for classification. Test results showed that the model was able to classify tomato ripeness with good performance based on classification evaluation metrics. Overall, the proposed approach shows good potential for RGB image-based tomato ripeness classification.
Klasifikasi tingkat kematangan buah tomat merupakan aspek penting dalam proses pascapanen dan distribusi hasil pertanian. Penentuan kematangan secara manual masih bersifat subjektif dan berpotensi menimbulkan ketidakkonsistenan. Penelitian ini bertujuan untuk mengklasifikasikan tingkat kematangan buah tomat menggunakan pendekatan deep learning berbasis Convolutional Neural Network (CNN) dengan arsitektur MobileNetV2 dan teknik transfer learning. Dataset berupa citra buah tomat diklasifikasikan ke dalam tiga kelas, yaitu tidak matang, matang, dan terlalu matang. Tahapan preprocessing meliputi proses resizing dan normalisasi citra sebelum dilakukan pelatihan model. Model MobileNetV2 digunakan sebagai feature extractor, sedangkan lapisan fully connected diterapkan untuk proses klasifikasi. Hasil pengujian menunjukkan bahwa model mampu mengklasifikasikan tingkat kematangan buah tomat dengan performa yang baik berdasarkan metrik evaluasi klasifikasi. Secara keseluruhan, pendekatan yang diusulkan menunjukkan potensi yang baik untuk klasifikasi tingkat kematangan buah tomat berbasis citra RGB
Full Text:
PDFReferences
Appe, S. R. N., Arulselvi, G., & Balaji, G. N. (2023). Tomato Ripeness Detection and Classification using VGG based CNN Models. IJISAE : International Journal of Intelligent Systems and Applications in Engineering, 11(1), 296–302. https://www.ijisae.org/index.php/IJISAE/article/view/2538
Ayunda, N. A., Haryatmi, E., & Riyadi, T. A. (2023). Classification of Tomato Ripeness Based on Convolutional Neural Network Methods. Journal of Information Systems and Informatics, 5(4), 1658–1675. https://doi.org/10.51519/journalisi.v5i4.613
Choirunisa, S., & Supatman. (2025). Klasifikasi Tingkat Kematangan Citra Buah Tomat Menggunakan Densenet-121. JITET : Jurnal Informatika Dan Teknik Elektro Terapan, 13(3), 1998–2003. https://doi.org/10.23960/jitet.v13i3.6652
Fajar, M., Sulthan, M. B., & Wahyudi, I. (2023). Klasifikasi Tingkat Kematangan Buah Tomat Menggunakan Fitur Rgb Dan Hsi Berbasis Backpropagation. JATIM : Jurnal Aplikasi Teknologi Informasi Dan Manajemen, 4(1), 84–95. https://doi.org/10.31102/jatim.v4i1.2177
Husna, M., & Fatah, Z. (2026). Klasifikasi Kematangan Tanaman Buah Tomat Menggunakan Teachable Machine: Pendekatan Berbasis Gambar. JAMASTIKA : Jurnal Mahasiswa Teknik Infiormatika, 5(1), 92–97. https://doi.org/10.35473/jamastika.v5i1.4599
Mardianto, Y., Dewi, T., & Risma, P. (2024). Analisis Klasifikasi Kematangan Buah Tomat dengan Pendekatan Transfer Learning Model EfficientNet. Techno Bahari, 11(1), 20–25. https://doi.org/10.52234/tb.v11i1.306
Mutahar, M., Kannan, S., Jafer, M. M., & Ragavendra K, M. (2024). Deep Learning-Based Tomato Ripeness Detection: A ResNet-152 Approach. IJSRST : International Journal of Scientific Research in Science and Technology, 11(1), 34–41. https://doi.org/10.32628/IJSRST5241113
Rosalina, Husodo, A. Y., & Wijaya, I. G. P. S. (2025). Development of a Convolutional Neural Network Method for Classifying Ripeness Levels of Servo Variety Tomatoes. JUTIF : Jurnal Teknik Informatika, 6(2), 501–520. https://doi.org/10.52436/1.jutif.2025.6.2.4168
Rumbekwan, J. I. W., & Aryanto, J. (2025). Application of Convolutional Neural Networks for Tomato Fruit Ripeness Identification. JSRET : Journal of Scientific Research, Education, and Technology, 4(1), 61–78. https://doi.org/10.58526/jsret.v4i1.645
Samual, M. A., & Wijanarko, S. (2026). Comparative Analysis of CNN and Random Forest for Cashew Plant Disease Classification. Sistemasi: Jurnal Sistem Informasi, 15(3), 961–970. https://doi.org/10.32520/stmsi.v15i3.6100
Santoso, K. A., Kamsyakawuni, A., & Izza, S. V. R. (2024). Comparison Classification Of Tomatoes Ripeness Based On RGB, HSV And CMYK Colors Based On Correlation Coefficient. Journal of Computers and Digital Business, 3(3), 112–120. https://doi.org/10.56427/jcbd.v3i3.410
Saparudin, H., Ramdi, M. A., & Alfarizi, F. S. (2025). Implementasi Convolutional Neural Network dan ResNet-18 untuk Klasifikasi Kerusakan Jalan Berbasis Citra. JAPTIKA : Jurnal Aplikasi Informatika Dan Multimedia, 1(1), 27–31. https://doi.org/10.64878/japtika.v1i1.53
Sholihin, I., & Sunyoto, A. (2025). Improving Tomato Ripeness Classification Using Knowledge Distillation and Hyperparameter Optimization with Optuna. Jeecom : Journal of Electrical Engineering and Computer, 7(2), 282–290. https://doi.org/10.33650/jeecom.v7i2.11266
DOI: https://doi.org/10.56486/jeis.vol6no2.1113
Article Metrics
Abstract view : 2 timesPDF - 2 times
Refbacks
- There are currently no refbacks.
Copyright (c) 2026 Mochamad Fathur Milzam

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
TERINDEKS OLEH :






