Analisis Perbandingan Kinerja Model EfficientNetV2-S, InceptionV3, dan ResNet50 dalam Klasifikasi Gambar Buah-Buahan
:
https://doi.org/10.32409/jikstik.24.3.3842
Keywords:
Klasifikasi, Deep Learning, Convolutional Neural NetworkAbstract
Dalam berbagai industri, dari agrikultur hingga ritel, klasifikasi citra buah-buahan secara otomatis sangat penting. Tujuan dari penelitian ini adalah untuk melakukan analisis komparatif terhadap kinerja tiga model Convolutional Neural Network (CNN) utama EfficientNetV2-S, InceptionV3, dan ResNet50 dalam konteks tugas klasifikasi gambar buah-buahan. menggunakan dataset "Klasifikasi Buah" yang diperoleh dari platform Kaggle, yang mencakup gambar dari lima varietas buah: Stroberi, Mangga, Anggur, Pisang, dan Apel. Setiap model dilatih dan dinilai menggunakan metrik standar seperti akurasi, presisi, recall, dan skor F1. Hasil penelitian menunjukkan bahwa model InceptionV3 memiliki akurasi yang lebih tinggi sebesar 90.50%, melampaui kinerja EfficientNetV2-S dan ResNet50, yang masing-masing menunjukkan akurasi 52.50%. Kajian lebih lanjut tentang laporan klasifikasi menunjukkan bahwa InceptionV3 juga memiliki kinerja yang lebih baik dalam hal skor F1, recall, dan presisi untuk setiap kategori buah. Studi ini memberikan perspektif tentang pemilihan model yang lebih efektif untuk tugas klasifikasi gambar buah-buahan pada dataset dengan atribut yang sebanding.
Kata Kunci: Klasifikasi Buah, Convolutional Neural Network, EfficientNet, InceptionV3, ResNet, Deep Learning, Kinerja Model.
Downloads
References
J. Liu, X. Wang, and M. Wright, "A comprehensive review on fruit detection and recognition using deep learning," Trends in Food Science & Technology, vol. 138, pp. 102-115, 2023.
A. Koirala, K. B. Walsh, Z. Wang, and C. McCarthy, "Deep learning for fruit detection and counting: A review," Computers and Electronics in Agriculture, vol. 185, p. 106158, 2021.
M. Tan and Q. Le, "EfficientNetV2: Smaller Models and Faster Training," in Proceedings of the 38th International Conference on Machine Learning (ICML), 2021, pp. 10096-10106.
A. R. Putri and H. A. Nugroho, "Performance Analysis of InceptionV3 for Mangosteen Fruit Quality Classification," Journal of Information Systems Engineering and Business Intelligence, vol. 9, no. 1, pp. 85-93, 2023.
A. Septiarini, H. R. Hatta, and Hamdani, "Apple Fruit Diseases Classification Using Transfer Learning with ResNet50," in 2022 International Conference on Data Science and Its Applications (ICoDSA), Bandung, Indonesia, 2022, pp. 1-6.
U. Saxena, "Fruits Classification Dataset," Kaggle, 2023. [Online]. Available: https://www.kaggle.com/datasets/utkarshsaxenadn/fruit s-classification. [Diakses pada: 4 Juni 2025].
X. Ying, "An Overview of Overfitting and its Solutions in Deep Learning," Journal of Physics: Conference Series, vol. 1871, no. 1, p. 012049, 2021.
E. D. Cubuk, B. Zoph, J. Shlens, and Q. V. Le, "RandAugment: Practical automated data augmentation with a reduced search space," in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020, pp. 702-703.
M. S. Hossain, M. Al-Hammadi, and G. Muhammad, "Automatic Fruit Classification Using Deep Learning: A Review," Computers and Electronics in Agriculture, vol. 193, p. 106691, 2022.
L. Zhu, Z. Zhang, and I. Marsic, "Fruit Image Classification with Attention-Based Deep Learning," Sensors, vol. 22, no. 5, p. 1993, 2022.
A. Bhargava and A. Bansal, "Fruits and vegetables image classification using transfer learning," International Journal of Information Technology, vol. 13, no. 4, pp. 1345-1353, 2021.
M. H. Saleem, J. Potgieter, and K. M. Arif, "Plant disease detection and classification by deep learning," Plants, vol. 10, no. 8, p. 1603, 2021.
M. Afonso, H. Fonteijn, F. S. Fiorentin, D. Lensink, M. Mooij, and G. Kootstra, "Tomato fruit detection and counting in greenhouses using a deep convolutional neural network," Frontiers in plant science, vol. 11, p. 571299, 2020.
Y. Majeed, S. Karkhanis, and A. Kulkarni, "FruitNect: A Deep Learning-Based Fruit-Recognition System Using a Custom-Bottleneck Layer," Applied Sciences, vol. 11, no. 16, p. 7380, 2021.
N. Mamat, M. F. Othman, R. Abdulghafor, A. A. Alwan, and O. M. Gul, "Advancements in image processing techniques for fruit quality assessment: A comprehensive review," Heliyon, vol. 9, no. 3, p. e14080, 2023.
C. Wang, B. Zhang, L. Liu, and Y. Zhu, "A review of fruit classification using deep learning and machine vision," Scientia Horticulturae, vol. 296, p. 110894, 2022.
S. S. Rawat, A. Verma, and S. Kumar, "Fruit Classification Using Deep Learning: A Transfer Learning Approach with MobileNetV2," in 2023 International Conference on Disruptive Technologies (ICDT), Greater Noida, India, 2023, pp. 1-6.
Downloads
Published
How to Cite
Issue
Section
Categories
Abstract View: 0 times
