Tomato Ripeness Classification Using Transfer Learning Approach with ResNet50 CNN Model
DOI:
https://doi.org/10.51903/zkncwx43Keywords:
Tomato, Fruit Ripeness, Transfer Learning, ResNet50Abstract
Tomatoes are high-value horticultural commodities requiring accurate ripeness assessment to maintain distribution quality. Conventional visual observation methods are subjective, labor-intensive, and inefficient for large-scale applications. This study developed a tomato ripeness classification system using transfer learning with the ResNet50 architecture. The dataset comprised 2,400 tomato images categorized into three classes: ripe, unripe, and reject. The model was fine-tuned on the last ten layers and optimized using the Adam algorithm with a learning rate of 0.00001. Evaluation showed an average validation accuracy of 98.08% with consistently high precision, recall, and F1-score across all classes. The trained model was further deployed into a web-based application using Streamlit, enabling users to upload tomato images and receive instant classification through a simple interface. With its high accuracy, practicality, and ease of use, this system offers an effective solution for digitalizing tomato sorting, thereby contributing to the broader adoption of artificial intelligence in modern agriculture.
References
[1] D. M. Gatahi, “Challenges and Opportunities in Tomato Production Chain and Sustainable Standards,” International Journal of Horticultural Science and Technology, vol. 7, no. 3, pp. 235–262, Sep. 2020. doi: 10.22059/ijhst.2020.300818.361.
[2] H. S. Mputu, A. Abdel-Mawgood, A. Shimada, and M. S. Sayed, “Tomato Quality Classification Based on Transfer Learning Feature Extraction and Machine Learning Algorithm Classifiers,” IEEE Access, vol. 12, pp. 8283–8295, Jan. 2024, doi: 10.1109/access.2024.3352745.
[3] M. B. S. I. W. Moh. Fajar, “Klasifikasi Kematangan Buah Tomat Menggunakan Fitur RGB dan HSI Berbasis Backpropagation,” Jurnal Aplikasi Teknik dan Informatika (JATIM), vol. 4, no. 1, pp. 84-95, Apr. 2023. doi: https://doi.org/10.31102/jatim.v4i1.2177.
[4] Y. P. Mubarok, T. A. Zurairah, and S. Maryana, “Deteksi Kematangan Buah Tomat Berdasarkan Nilai RGB (Detection of Tomato Ripeness Based on RGB Values),” Jurnal Budidarma Komputer dan Informatika (JUBIKOM), vol. 3, no. 1, pp. 1-6, Feb. 2023. doi: 10.33751/jubikom.v3i1.9324.
[5] M. A. K. Putri and A. F. Rozi, “Implementasi Convolutional Neural Network dalam Menentukan Tingkat Kematangan Mentimun dan Tomat Berdasarkan Warna Kulit,” Jurnal Teknik Informatika (JATI), vol. 8, no. 5, pp. 10388-10394, Oct. 2024. doi: https://doi.org/10.36040/jati.v8i5.11076.
[6] T. Kim, D. H. Lee, K. C. Kim, T. Choi, and J. M. Yu, “Tomato Maturity Estimation Using Deep Neural Network,” Applied Sciences, vol. 13, no. 1, p. 412, Dec. 2022, doi: 10.3390/app13010412.
[7] N. Nafi’iyah and A. Yuniarti, “A Convolutional Neural Network for Skin Cancer Classification,” International Journal of Informatics and Communication Technology (IJ-ICT), vol. 11, p. 76, Apr. 2022, doi: 10.11591/ijict.v11i1.pp76-84.
[8] P. Das, J. K. P. S. Yadav, and L. Singh, “Deep Learning-Based Tomato’s Ripe and Unripe Classification System,” International Journal of Software Innovation, vol. 10, no. 1, pp. 1-20, 2022, doi: 10.4018/ijsi.292023.
[9] F. Syaila, P. Azzahra, and C. Printo, “Tinjauan Literatur Sistematis: Analisis Implementasi Kecerdasan Buatan untuk Verifikasi Dokumen,” Jurnal Ilmiah Sistem Informasi, vol. 4, no. 3, pp. 417–430, Aug. 2025, doi: 10.51903/kjjwk708.
[10] R. Raj and A. Kos, “An Extensive Study of Convolutional Neural Networks: Applications in Computer Vision for Improved Robotics Perceptions,” Sensors, vol. 25, no. 4, p. 1033, Feb. 2025, doi: 10.3390/s25041033.
[11] A. F. Nurjannah, A. S. D. Kurniasari, Z. Sari, and Y. Azhar, “Pneumonia Image Classification Using CNN with Max Pooling and Average Pooling,” Jurnal RESTI, vol. 6, no. 2, pp. 330–338, Apr. 2022, doi: 10.29207/resti.v6i2.4001.
[12] Amelia Salsabisa Hakim, Putri Jihan Mustaqim, and Atha Naufal, “Peran Pendidikan Digital dalam Melindungi Privasi Pengguna dan Mencegah Dampak Sosial,” Jurnal Ilmiah Sistem Informasi, vol. 4, no. 2, pp. 162–174, May 2025, doi: 10.51903/k9cvkc90.
[13] N. D. Miranda, L. Novamizanti, and S. Rizal, “Convolutional Neural Network pada Klasifikasi Sidik Jari Menggunakan ResNet-50,” Jurnal Teknik Informatika (Jutif), vol. 1, no. 2, pp. 61–68, Dec. 2020, doi: 10.20884/1.jutif.2020.1.2.18.
[14] L. Zhang, Y. Bian, P. Jiang, and F. Zhang, “A Transfer Residual Neural Network Based on ResNet-50 for Detection of Steel Surface Defects,” Applied Sciences, vol. 13, no. 9, p. 5260, May 2023, doi: 10.3390/app13095260.
[15] M. B. Hossain, S. M. H. S. Iqbal, M. M. Islam, M. N. Akhtar, and I. H. Sarker, “Transfer Learning with Fine-Tuned Deep CNN ResNet50 Model for Classifying COVID-19 from Chest X-Ray Images,” Inform Med Unlocked, vol. 30, p. 100916, Jan. 2022, doi: 10.1016/j.imu.2022.100916.
[16] A. S. Putra and T. Kristiana, “Analisa Desain UI/UX Website E-Learning MTSN 33 Jakarta Menggunakan Metode User Centered Design,” Jurnal Ilmiah Sistem Informasi, vol. 4, no. 3, pp. 590–606, Oct. 2025, doi: 10.51903/32j40x26.
[17] A. W. Salehi et al., “A Study of CNN and Transfer Learning in Medical Imaging: Advantages, Challenges, Future Scope,” Sustainability, vol. 15, no. 7, p. 5930, Apr. 2023, doi: 10.3390/su15075930.
[18] R. Wardhani and N. Nafi’iyah, “Modification CNN Transfer Learning for Classification MRI Brain Tumor,” Telematika, vol. 16, no. 2, pp. 103–112, Aug. 2023, doi: 10.35671/telematika.v16i2.2272.
[19] J. A. Raj, L. Qian, and Z. Ibrahim, “Fine-tuning -- a Transfer Learning approach,” Nov. 2024, doi: 10.48550/arXiv.2411.03941.
[20] V. Taormina, D. Cascio, L. Abbene, and G. Raso, “Performance of Fine-Tuning Convolutional Neural Networks for HEP-2 Image Classification,” Applied Sciences, vol. 10, no. 19, pp. 1–20, Oct. 2020, doi: 10.3390/app10196940.
[21] B. K. Triwijoyo, A. Adil, and A. Anggrawan, “Convolutional Neural Network with Batch Normalization for Classification of Emotional Expressions Based on Facial Images,” Matrik : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer, vol. 21, no. 1, pp. 197–204, Nov. 2021, doi: 10.30812/matrik.v21i1.1526.
[22] I. G. T. Suryawan and I. P. A. E. D. Udayana, “Optimasi Convolutional Neural Network untuk Deteksi COVID-19 pada X-Ray Thorax Berbasis Dropout,” Jurnal Teknologi Informasi dan Ilmu Komputer (JTIIK), vol. 9, no. 5, pp. 551-558, May 2022. doi: 10.25126/jtiik.202295143.
[23] R. Ramya and P. Kumar, “High-Performance Deep Transfer Learning Model with Batch Normalization Based on Multiscale Feature Fusion for Tomato Plant Disease Identification and Categorization,” Environ Res Commun, vol. 5, no. 12, p. 125015, Dec. 2023, doi: 10.1088/2515-7620/ace594.
[24] I. A. Dewi and M. A. N. E. Salawangi, “High Performance of Optimizers in Deep Learning for Cloth Patterns Detection,” IAES International Journal of Artificial Intelligence, vol. 12, no. 3, pp. 1407–1418, Sep. 2023, doi: 10.11591/ijai.v12.i3.pp1407-1418.
[25] E. Hassan, M. Y. Shams, N. A. Hikal, and S. Elmougy, “The Effect of Choosing Optimizer Algorithms to Improve Computer Vision Tasks: A Comparative Study,” Multimed Tools Appl, vol. 82, no. 11, pp. 16591–16633, May 2023, doi: 10.1007/s11042-022-13820-0.
[26] Y. Mardianto, T. Dewi, and P. Risma, “Analisis Klasifikasi Kematangan Buah Tomat dengan Pendekatan Transfer Learning Model EfficientNet,” Jurnal Techno Bahari, vol. 11, no. 1, pp. 20-25, Mar. 2024, doi: https://doi.org/10.52234/tb.v11i1.306.
[27] K. Marzuki, Apriani, and Q. Mudawil, “Coffee Roaster Maturity Level Classification Based on Convolutional Neural Network,” Mathematical Modelling of Engineering Problems, vol. 12, no. 1, pp. 46–54, 2025, doi: 10.18280/mmep.120106.
[28] Z. Al-Mashhadani and B. Chandrasekaran, “ROS-Based Robotic System for Tomato Disease and Ripeness Classification using Convolutional Neural Networks,” in 2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference, IEMCON 2021, Institute of Electrical and Electronics Engineers Inc., 2021, pp. 420–427. doi: 10.1109/iemcon53756.2021.9623183.
[29] S. Aras, P. Tanra, and M. Bazhar, “Deteksi Tingkat Kematangan Buah Tomat Menggunakan YOLOv5,” Malcom: Indonesian Journal of Machine Learning and Computer Science, vol. 4, no. 2, pp. 623–628, Apr. 2024, doi: 10.57152/malcom.v4i2.1270.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Habibur Rohman, Nur Nafi'iyah, Azza Abidatin Bettaliyah
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All articles published in this journal are open access and licensed under the terms of the Creative Commons Attribution-ShareAlike 4.0 International License (CC BY-SA 4.0).
Under this license:
-
Authors retain copyright of their work.
-
Others are free to:
-
Share — copy and redistribute the material in any medium or format;
-
Adapt — remix, transform, and build upon the material for any purpose, even commercially;
-
-
As long as they:
-
Give appropriate credit to the original author(s) and the source;
-
Provide a link to the license;
-
Indicate if changes were made;
-
Distribute their contributions under the same license as the original.
-
This ensures that derivative works will also remain free and open under the same terms.
.png)
