KLASIFIKASI VARIETAS BIBIT DURIAN MENGGUNAKAN RESNET50: PENDEKATAN DEEP LEARNING UNTUK PERTANIAN DIGITAL
DOI:
https://doi.org/10.24076/joism.2026v7i2.2479Keywords:
ResNet50, Bibit Durian, Citra Daun, Klasifikasi Tanaman, Pertanian DigitalAbstract
Identifikasi varietas bibit durian secara akurat pada fase pembibitan sangat krusial untuk mencegah kerugian ekonomi akibat kesalahan pemilihan varietas unggul. Namun, identifikasi manual berbasis visual memiliki kelemahan pada subjektivitas dan tingkat kesalahan manusia yang tinggi. Penelitian ini mengusulkan model klasifikasi otomatis untuk empat varietas durian populer (Bawor, Duri Hitam, Musang King, dan Super Tembaga) menggunakan arsitektur Deep Residual Network (ResNet50). Peningkatan akurasi dilakukan melalui integrasi teknik prapemrosesan background removal berbasis ambang batas untuk mereduksi noise latar belakang dan penerapan strategi fine-tuning pada lapisan fully connected. Selain itu, optimasi hyperparameter dilakukan secara sistematis untuk menentukan learning rate dan batch size optimal. Hasil eksperimen menunjukkan bahwa model yang diusulkan mencapai performa superior dengan akurasi klasifikasi sebesar 96% dan stabilitas nilai loss pada rentang 0.15–0.20. Hasil ini membuktikan bahwa pendekatan deep learning dengan optimasi prapemrosesan mampu memberikan solusi identifikasi yang lebih objektif dan presisi dibandingkan metode konvensional. Penelitian ini berkontribusi pada pengembangan sistem pertanian digital yang cerdas dalam mendukung standarisasi kualitas bibit durian.
References
[1] Muthulakshmi. A and P. N. Renjith, “Classification of Durian Fruits based on Ripening with Machine Learning Techniques,” in 2020 3rd International Conference on Intelligent Sustainable Systems (ICISS), Thoothukudi, India: IEEE, Dec. 2020, pp. 542–547. doi: 10.1109/ICISS49785.2020.9316006.
[2] N. A. A Aziz and A. M. Mhd Jalil, “Bioactive Compounds, Nutritional Value, and Potential Health Benefits of Indigenous Durian (Durio Zibethinus Murr.): A Review,” Foods, vol. 8, no. 3, p. 96, Mar. 2019, doi: 10.3390/foods8030096.
[3] N. A. H. A. Halim, S. Suhaila, and N. S. A. M Taujuddin, “Durian Tree Type Identification Based on Durian Leaves,” EEEE, vol. Vol. 4, 2023, doi: https://doi.org/10.30880/eeee.2023.04.01.066.
[4] S. A. Wagle, R. Harikrishnan, S. H. M. Ali, and M. Faseehuddin, “Classification of Plant Leaves Using New Compact Convolutional Neural Network Models,” Plants, vol. 11, no. 1, p. 24, Dec. 2021, doi: 10.3390/plants11010024.
[5] P. Jasitha, M. R. Dileep, and M. Divya, “Venation Based Plant Leaves Classification Using GoogLeNet and VGG,” in 2019 4th International Conference on Recent Trends on Electronics, Information, Communication & Technology (RTEICT), Bangalore, India: IEEE, May 2019, pp. 715–719. doi: 10.1109/RTEICT46194.2019.9016966.
[6] M. A. N. Hidayat, “Convolutional Neural Network Pada Identifikasi Varian Tanaman Anggur Menggunakan Resnet-50,” vol. 10, no. 3, 2023.
[7] A. Taslim, S. Saon, A. K. Mahamad, M. Muladi, and W. N. Hidayat, “Plant leaf identification system using convolutional neural network,” Bull. Electr. Eng. Inform., vol. 10, no. 6, pp. 3341–3352, Dec. 2021, doi: 10.11591/eei.v10i6.2332.
[8] K. Dong, C. Zhou, Y. Ruan, and Y. Li, “MobileNetV2 Model for Image Classification,” in 2020 2nd International Conference on Information Technology and Computer Application (ITCA), Guangzhou, China: IEEE, Dec. 2020, pp. 476–480. doi: 10.1109/ITCA52113.2020.00106.
[9] R. Metasari, Varietas Durian Unggul yang Potensial. Jakarta: Elementa Agro Lestari, 2023.
[10] B. D. Arfiyanto, F. M. A. Ramadhani, and S. Sajuri, “Analysis of Constant Values of Leaves of the Durian Cultivars Monthong and Bawor Using Digital Image Processing,” J. Appl. Agric. Sci. Technol., vol. 9, no. 3, pp. 449–463, Aug. 2025, doi: 10.55043/jaast.v9i3.462.
[11] J. K. P. Sucipto and D. Prabowo, “Peningkatan Akurasi Identifikasi Varietas Bibit Durian Menggunakan MobileNetV2 dan Teknik Optimasi,” vol. 04, no. 01, 2025.
[12] H. D. Nugroho, R. K. Niswatin, and D. Swanjaya, “Identifikasi Jenis Bibit Durian Berdasarkan Citra Daun Menggunakan YOLOv8 Berbasis Web,” vol. 9.
[13] L. M. M. Fitriani and Y. Litanianda, “CLASSIFICATION OF DURIAN LEAF IMAGES USING CNN (CONVOLUTIONAL NEURAL NETWORK) ALGORITHM,” JIKO J. Inform. Dan Komput., vol. 7, no. 2, pp. 150–157, Aug. 2024, doi: 10.33387/jiko.v7i2.8576.
[14] Didi Kurniawan and Dhani Ariatmanto, “IDENTIFIKASI VARIETAS BIBIT DURIAN MENGGUNAKAN MOBILENETV2 BERDASARKAN GAMBAR DAUN,” J. Inform. Dan Rekayasa Elektron., vol. 7, no. 2, pp. 231–240, Nov. 2024, doi: 10.36595/jire.v7i2.1236.
[15] K. Alomar, H. I. Aysel, and X. Cai, “Data Augmentation in Classification and Segmentation: A Survey and New Strategies,” J. Imaging, vol. 9, no. 2, p. 46, Feb. 2023, doi: 10.3390/jimaging9020046.
[16] M. A. N. Hidayat, “Convolutional Neural Network Pada Identifikasi Varian Tanaman Anggur Menggunakan Resnet-50,” vol. 10, no. 3, 2023.
[17] R. Obuchowicz, M. Strzelecki, and A. Piórkowski, “Clinical Applications of Artificial Intelligence in Medical Imaging and Image Processing—A Review,” Cancers, vol. 16, no. 10, p. 1870, May 2024, doi: 10.3390/cancers16101870.
[18] C. P. Lee, K. M. Lim, Y. X. Song, and A. Alqahtani, “Plant-CNN-ViT: Plant Classification with Ensemble of Convolutional Neural Networks and Vision Transformer,” Plants, vol. 12, no. 14, p. 2642, July 2023, doi: 10.3390/plants12142642.
[19] S. Farhadpour, T. A. Warner, and A. E. Maxwell, “Selecting and Interpreting Multiclass Loss and Accuracy Assessment Metrics for Classifications with Class Imbalance: Guidance and Best Practices,” Remote Sens., vol. 16, no. 3, p. 533, Jan. 2024, doi: 10.3390/rs16030533.
[20] Fery Bayu Aji, Fajri Rakhmat Umbara, and Fatan Kasyidi, “KLASIFIKASI RISIKO KEMATIAN PASIEN BERDASARKAN PENYAKIT PENYERTA DAN USIA PASIEN MENGGUNAKAN METODE C4.5,” J. Inform. Dan Rekayasa Elektron., vol. 6, no. 1, pp. 9–17, Apr. 2023, doi: 10.36595/jire.v6i1.699.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Information System Management (JOISM)
This work is licensed under a Creative Commons Attribution 4.0 International License.
