Komparasi Transfer Learning ResNet-50 dan EfficientNet-B0 pada Klasifikasi Varietas Durian Berdasarkan Morfologi Daun
DOI:
https://doi.org/10.29407/qa9tdj72Abstract
Durian merupakan komoditas buah bernilai ekonomi tinggi yang memiliki berbagai varietas dengan karakteristik morfologi daun yang berbeda. Identifikasi varietas durian secara manual sering mengalami kesulitan karena kemiripan bentuk daun antar varietas dan bergantung pada pengalaman pengamat. Penelitian ini bertujuan membandingkan kinerja metode Deep Learning menggunakan arsitektur ResNet-50 dan EfficientNet-B0 dengan pendekatan transfer learning untuk klasifikasi varietas durian berbasis citra daun. Dataset yang digunakan terdiri dari 1.073 citra daun yang terbagi ke dalam lima kelas, yaitu Bawor, Lokal Sawahan, Montong, Musang King, dan Ripto. Tahapan penelitian meliputi pengumpulan data, preprocessing citra, pelatihan model, serta evaluasi menggunakan confusion matrix, precision, recall, dan F1-score. Hasil pengujian menunjukkan bahwa model ResNet-50 memperoleh performa terbaik dengan akurasi sebesar 89%, macro precision sebesar 0,89, macro recall sebesar 0,90, dan macro F1-score sebesar 0,89. Sementara itu, model EfficientNet-B0 memperoleh akurasi sebesar 82%, macro precision sebesar 0,83, macro recall sebesar 0,82, dan macro F1-score sebesar 0,82. Hasil penelitian menunjukkan bahwa kedua model mampu melakukan klasifikasi varietas durian dengan baik, namun ResNet-50 memberikan performa yang lebih unggul dibandingkan EfficientNet-B0 dalam mengenali karakteristik morfologi daun durian. Temuan ini menunjukkan bahwa ResNet-50 berpotensi diterapkan sebagai solusi identifikasi varietas durian secara otomatis untuk mendukung kegiatan pembibitan dan budidaya tanaman.
Keywords:
CNN, Durian, Klasifikasi Citra, Morfologi Daun, ResNet-50, EfficientNet-B0##plugins.themes.default.displayStats.downloads##
References
[1] L. M. M. Fitriani and Y. Litanianda, “CLASSIFICATION OF DURIAN LEAF IMAGES USING CNN
(CONVOLUTIONAL NEURAL NETWORK) ALGORITHM,” JIKO (Jurnal Informatika dan
Komputer), vol. 7, no. 2, pp. 150–157, Aug. 2024, doi: 10.33387/JIKO.V7I2.8576.
[2] M. Sultan et al., “Convolutional Neural Networks in Detection of Plant Leaf Diseases: A Review,”
Agriculture 2022, Vol. 12, Page 1192, vol. 12, no. 8, p. 1192, Aug. 2022, doi:
10.3390/AGRICULTURE12081192.
[3] M. S. Ikrar Musyaffa, N. Yudistira, M. A. Rahman, A. H. Basori, A. B. Firdausiah Mansur, and J. Batoro,
“IndoHerb: Indonesia medicinal plants recognition using transfer learning and deep learning,” Heliyon,
vol. 10, no. 23, p. e40606, Dec. 2024, doi: 10.1016/J.HELIYON.2024.E40606.
[4] N. P. Maylianti, G. Ngurah, L. Wijayakusuma, P. Chandra, and A. Wiguna, “Comparison of EfficientNetB0 and ResNet-50 for Detecting Diseases in Cocoa Fruit,” Journal of Applied Informatics and Computing,
vol. 9, no. 1, pp. 115–120, Jan. 2025, doi: 10.30871/JAIC.V9I1.8868.
[5] Didi Kurniawan and Dhani Ariatmanto, “IDENTIFIKASI VARIETAS BIBIT DURIAN
MENGGUNAKAN MOBILENETV2 BERDASARKAN GAMBAR DAUN,” Jurnal Informatika dan
Rekayasa Elektronik, vol. 7, no. 2, pp. 231–240, Nov. 2024, doi: 10.36595/JIRE.V7I2.1236.
[6] B. Min, T. Kim, D. Shin, and D. Shin, “Data Augmentation Method for Plant Leaf Disease Recognition,”
Applied Sciences 2023, Vol. 13, Page 1465, vol. 13, no. 3, p. 1465, Jan. 2023, doi: 10.3390/APP13031465.
[7] D. Diana et al., “Convolutional Neural Network Based Deep Learning Model for Accurate Classification
of Durian Types,” Journal of Applied Data Sciences, vol. 6, no. 1, pp. 101–114, Jan. 2025, doi:
10.47738/JADS.V6I1.480.
[8] Ü. Atila, M. Uçar, K. Akyol, and E. Uçar, “Plant leaf disease classification using EfficientNet deep
learning model,” Ecol. Inform., vol. 61, p. 101182, Mar. 2021, doi: 10.1016/J.ECOINF.2020.101182.
[9] K. Shaheed et al., “EfficientRMT-Net—An Efficient ResNet-50 and Vision Transformers Approach for
Classifying Potato Plant Leaf Diseases,” Sensors 2023, Vol. 23, Page 9516, vol. 23, no. 23, p. 9516, Nov.
2023, doi: 10.3390/S23239516.
[10] M. S. A. M. Al-Gaashani, N. A. Samee, R. Alnashwan, M. Khayyat, and M. S. A. Muthanna, “Using a
Resnet50 with a Kernel Attention Mechanism for Rice Disease Diagnosis,” Life 2023, Vol. 13, Page 1277,
vol. 13, no. 6, p. 1277, May 2023, doi: 10.3390/LIFE13061277.
[11] M. M. Daud, A. Abualqumssan, F. ‘Atyka N. Rashid, M. H. Md Saad, W. M. D. W. Zaki, and N. S. Mohd
Satar, “Durian Disease Classification using Vision Transformer for Cutting-Edge Disease Control,”
International Journal of Advanced Computer Science and Applications, vol. 14, no. 12, pp. 446–452, Dec.
2023, doi: 10.14569/IJACSA.2023.0141246.
[12] D. A. Salem, N. A. Hassan, and R. M. Hamdy, “Impact of transfer learning compared to convolutional
neural networks on fruit detection,” Journal of Intelligent and Fuzzy Systems, vol. 46, no. 4, pp. 7791–
7803, Apr. 2024, doi: 10.3233/JIFS-233514.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Copyright on any article is retained by the author(s).
- The author grants the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work’s authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal’s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License
