Penggunaan Transfer Learning Untuk Peningkatan Akurasi Deteksi Penyakit Tanaman Bunga

Enteng Hardiansyah; Lailan Sofinah Haharap; Muhammad Farros Atiqi

doi:10.61132/mars.v3i6.1264

Authors

Enteng Hardiansyah Universitas Islam Negeri Sumatera Utara
Lailan Sofinah Haharap Universitas Islam Negeri Sumatera Utara
Muhammad Farros Atiqi Universitas Muhammadiyah Sumatra Utara

DOI:

https://doi.org/10.61132/mars.v3i6.1264

Keywords:

Computer Vision, Deep Learning, Flowering Plants, Plant Disease Detection, Transfer Learning

Abstract

Flower disease detection is a significant challenge in modern agriculture, particularly with factors such as changes in leaf color, petal shape and structure, and environmental conditions affecting the accuracy of conventional models. These factors make it difficult to achieve optimal results using traditional methods. Transfer learning is an effective solution to improve image detection performance, especially when data is limited. This study used several pre-trained models, namely VGG16, ResNet50, and EfficientNet-B0, to detect three types of flower diseases: black spot on roses, white powdery mildew, and leaf rust. The research process included data processing, increasing the data volume using augmentation techniques, model training, and evaluation of the results. Experimental results showed that the EfficientNet-B0 model produced the highest accuracy of 97.2%, significantly better than the CNN model built from scratch with an accuracy of 85.1%. This study demonstrates that transfer learning is highly effective in improving the accuracy of flower disease detection, making it a more reliable alternative to methods that do not utilize pre-trained models, especially for agricultural applications that require high levels of accuracy in disease detection.

References

Alam, T. S., Jowthi, C. B., & Pathak, A. (2024). Comparing pre-trained models for deep learning. IEEE Access, 10, 39674–39680. https://doi.org/10.1109/ACCESS.2022.3164510

Alit, F. O., Alit, F. T., Wulanjari, D., & Patricia, S. B. (2019). Introduksi mawar potong untuk meningkatkan pendapatan petani mawar di Desa Karangpring Kecamatan Sukorambi Kabupaten Jember. Jurnal Seminar Nasional, 1–4.

Boulent, J., et al. (2020). Convolutional neural networks in plant phenotyping and disease detection. Computers and Electronics in Agriculture.

Dehbozorgi, P., Ryabchykov, O., & Bocklitz, T. (2024). A systematic investigation of DenseNet121 transfer learning in agriculture focusing on crop leaf disease identification. Applied Computing and Informatics. https://doi.org/10.1108/ACI-03-2024-0132

Efficient leaf disease detection: A study on custom CNN. Journal of Electrical Systems and Information Technology, 11(1), 1–26. https://doi.org/10.1186/s43067-024-00137-1

Image pre-processing on image classification. IEEE Access, 12(February), 64913–64926. https://doi.org/10.1109/ACCESS.2024.3395063

Jaiswal, A., et al. (2020). A survey on deep learning applications in agriculture. International Journal of Advanced Computer Science.

Kumar, T., et al. (2023). Image data augmentation approaches: A comprehensive survey and future directions. IEEE Access, 12(December). https://doi.org/10.1109/ACCESS.2024.3470122

Lanjewar, M. G., Morajkar, P., & P, P. (2024). Modified transfer learning frameworks. Scientific Reports, 13(1), 1–11. https://doi.org/10.1038/s41598-023-46492-3

Liu, H., et al. (2022). TBEM: Testing-based GPU-memory consumption estimation for platinum resistance in ovarian cancer. IEEE Access, 12(March), 41000–41008. https://doi.org/10.1109/ACCESS.2024.3377560

Santoso, H. A., et al. (2024). Comparative analysis of convolutional neural networks and machine learning techniques. Journal of Artificial Intelligence and Data Mining.

Swapno, S. M. M. R., et al. (2025). ViT-SENet-Tom: Machine learning-based novel hybrid squeeze–excitation network and vision transformer framework for tomato fruits classification. Neural Computing and Applications, 5, 7–14. https://doi.org/10.1007/s00521-025-10973-5

Tan, M., & Le, Q. (2020). EfficientNet: Rethinking model scaling for convolutional neural networks. Journal of Machine Learning Research.

Wu, Q., et al. (2023). A classification method for soybean leaf diseases based on an attention mechanism. Multimedia Tools and Applications, 83(17), 50401–50423. https://doi.org/10.1007/s11042-023-17610-0

Zhuang, H., et al. (2024). An attention-based deep learning network for predicting plant diseases. Computers in Biology and Medicine.