Analisis Kinerja Arsitektur ResNet50 untuk Klasifikasi Varietas Mangga Berbasis Citra Digital

Authors

  • MOHAMAD FAJAR A'LA UDIN Universitas Nusantara PGRI Kediri Indonesia
  • DANIEL SWANJAYA Universitas Nusantara PGRI Kediri Indonesia
  • RESTY WULANNINGRUM Universitas Nusantara PGRI Kediri Indonesia

DOI:

https://doi.org/10.29407/55ecd124

Abstract

Penelitian ini membahas penerapan arsitektur ResNet50 untuk klasifikasi varietas mangga berbasis citra digital. Identifikasi varietas mangga secara manual masih memiliki keterbatasan karena kemiripan visual antar kelas. Penelitian ini menggunakan pendekatan transfer learning dengan model ResNet50 berbobot awal ImageNet. Dataset terdiri dari tiga kelas, yaitu GADUNG, MANALAGI, dan PODANG, yang dibagi menjadi data training, validation, dan testing. Tahap preprocessing dilakukan melalui resize citra menjadi 224 × 224 piksel, normalisasi, dan augmentasi data. Untuk mengurangi overfitting, diterapkan dropout, batch normalization, regularisasi L2, dan early stopping. Hasil pengujian menunjukkan bahwa model memperoleh akurasi testing sebesar 93,64%. Hasil ini menunjukkan bahwa ResNet50 efektif digunakan untuk klasifikasi varietas mangga berbasis citra digital dengan performa yang stabil.

Keywords:

citra digital, klasifikasi, mangga, ResNet50, transfer learning

##plugins.themes.default.displayStats.downloads##

##plugins.themes.default.displayStats.noStats##

References

[1] I. Ahmad et al., "Automated Mango Variety Classification Using Deep Feature Extraction and Machine Learning Classifier Integration," Foods, vol. 15, no. 3, Feb. 2026, doi: 10.3390/foods15030414.

[2] M. M. A. Zaid, A. A. Mohammed, and P. Sumari, "Remote Sensing Image Classification Using Convolutional Neural Network (CNN) and Transfer Learning Techniques," Journal of Computer Science, vol. 21, no. 3, pp. 635-645, 2025, doi: 10.3844/jcssp.2025.635.645.

[3] L. Chuquimarca, B. Vintimilla, and S. Velastin, "Classifying healthy and defective fruits with a multi-input architecture and CNN models," in 2024 14th International Conference on Pattern Recognition Systems (ICPRS), IEEE, 2024, pp. 1-7, doi: 10.1109/ICPRS62101.2024.10677833.

[4] K. He, X. Zhang, S. Ren, and J. Sun, "Deep Residual Learning for Image Recognition," in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770-778, doi: 10.1109/CVPR.2016.90.

[5] H. E. Kim, A. Cosa-Linan, N. Santhanam, M. Jannesari, M. E. Maros, and T. Ganslandt, "Transfer learning for medical image classification: a literature review," BMC Med. Imaging, vol. 22, no. 1, p. 69, 2022.

[6] J. Plested, M. Phiri, and T. Gedeon, "Deep transfer learning for image classification: a survey," Dec. 2025, doi: 10.1007/s10462-026-11491-z.

[7] A. K. Ratha, N. K. Barpanda, P. K. Sethy, and S. K. Behera, "Automated Classification of Indian Mango Varieties Using Machine Learning and MobileNet-v2 Deep Features.," Traitement du Signal, vol. 41, no. 2, 2024.

[8] G. Yehulu et al., "Mango Fruit Disease Detection and Classification Using MobileNetV3_large Model," Sci. Afr., vol. 30, p. e03061, Oct. 2025, doi: 10.1016/j.sciaf.2025.e03061.

[9] A. Auni and E. Sugiharti, "Optimization of Mango Plant Leaf Disease Classification Using Concatenation Method of MobileNetV2 and DenseNet201 CNN Architectures," Scientific Journal of Informatics, vol. 11, pp. 1023-1034, Feb. 2025, doi: 10.15294/sji.v11i4.15169.

[10] B. Peón, J. Torres Gómez, and A. Márquez, "CNN-based solution for mango classification in agricultural environments," 2025, doi: 10.48550/arXiv.2507.23174.

[11] R. Sujana, P. Indah, N. Vinta, and R. Setiaji, "Evaluasi Model Klasifikasi Motif Batik Lasem Menggunakan Xgboost, Lightgbm, Resnet50, dan Efficientnet-B0," Jurnal Ilmiah Teknik Informatika dan Komunikasi, vol. 6, pp. 76-93, Apr. 2026, doi: 10.55606/juitik.v6i2.2137.

Downloads

Published

2026-07-20

Issue

Vol. 10 No. 1 (2026): Prosiding Seminar Nasional Inovasi Teknologi Tahun 2026

Section

Articles

License

Creative Commons 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:

  1. Copyright on any article is retained by the author(s).
  2. 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.
  3. 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.
  4. 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.
  5. The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License

How to Cite

Analisis Kinerja Arsitektur ResNet50 untuk Klasifikasi Varietas Mangga Berbasis Citra Digital. (2026). Prosiding SEMNAS INOTEK (Seminar Nasional Inovasi Teknologi), 10(1), 629-638. https://doi.org/10.29407/55ecd124