DATA AUGMENTATION EFFECTS ON PROTONET FEW-SHOT YELLOW DISEASE SEVERITY IN CHILI LEAVES
DOI:
https://doi.org/10.33480/jitk.v11i3.7458Keywords:
Few-Shot Learning, Prototypical Network, VGG16, Yellow Leaf Curl DiseaseAbstract
Yellow curling disease in chili plants is one of the leading causes of declining horticultural productivity because it reduces the quality and quantity of crops. Variations in symptoms at each level of severity make the identification process difficult, especially when labeled data is minimal. This study proposes a Prototypical Network-based Few-Shot Learning (FSL) approach with VGG16 architecture as a feature extractor. Five augmentation techniques, namely horizontal flip, rotation, zoom, brightness, and contrast adjustment, were used to increase data diversity in data-scarce conditions. Experiments were conducted with N-way K-shot configurations (2–5 classes; 1, 5, and 10 examples per class) to evaluate the impact of augmentation on prototype representation stability. Results show that increasing the number of examples per class consistently improves accuracy from 34.6% in 5-way 1-shot to 49.4% in 5-way 10-shot without augmentation. However, the use of augmentation decreases performance in higher N-way scenarios because it increases intra-class variability. The t-SNE visualization reinforces this study, where the healthy and severely diseased classes are clearly separated, while the intermediate class shows overlap. The novelty of this study is that it is the first to evaluate the impact of augmentation strategies on prototype representation stability in the agricultural domain with limited data. The results of this Few-Shot Learning approach are effective for plant disease classification despite the limited dataset.
Downloads
References
[1] Apriyangsa Gulo, Listari Harefa, and Fitri Julianti Gea, “Efektivitas Penggunaan Mulsa Plastik dalam Meningkatkan Produktivitas Tanaman Cabai (Capsicum annuum L.),” Flora J. Kaji. Ilmu Pertan. dan Perkeb., vol. 2, no. 1, pp. 152–159, Jan. 2025, doi: 10.62951/flora.v2i1.258.
[2] E. P. Yudha and G. C. Vanessa, “Analisis Kinerja Ekspor Cabai Hijau Di Indonesia,” J. Apresiasi Ekon., vol. 10, no. 3, pp. 340–345, 2022, doi: 10.31846/jae.v10i3.506.
[3] R. Albar, M. Chatri, M. Des, D. H. Putri, and Y. B. Paradisa, “Penyakit Geminivirus ( PepYLCV ) pada Tanaman Cabai ( Capsicum sp .) yang Disebabkan oleh Hama Kutu Kebul ( Bemisia tabaci ),” J. Serambi Biol., vol. 8, no. 3, pp. 391–396, 2023.
[4] S. Suprayogi, N. Widyawati, and M. M. Herawati, “The Impact of Yellow Leaf Curl Disease Stage During Vegetative and Generative Phases on The Growth and Yield of Curly Red Chili Pepper OR Twist 42,” J. Tek. Pertan. Lampung, vol. 14, no. 2, pp. 483–493, 2025.
[5] N. Hardina, “Identifikasi Virus Penyebab Penyakit Kuning Keriting pada Cabai di Kabupaten Gowa , Sulawesi Selatan Identification of Virus that Causes Yellow Leaf Curl Disease in Chili in,” J. Agrik., vol. 34, no. 3, pp. 427–434, 2023, [Online]. Available: https://jurnal.unpad.ac.id/agrikultura/article/viewFile/42833/21773.
[6] K. Ye, “Key Intelligent Pesticide Prescription Spraying Technologies for the Control of Pests , Diseases , and Weeds : A Review,” Agric., vol. 15, no. 81, 2025, doi: https://doi.org/10.3390/agriculture15010081.
[7] S. Verma, A. Chug, A. P. Singh, and D. Singh, “Plant Disease Detection and Severity Assessment Using Image Processing and Deep Learning Techniques,” SN Comput. Sci., vol. 5, no. 1, p. 83, Dec. 2023, doi: 10.1007/s42979-023-02417-5.
[8] S. Neto et al., “Machine learning and deep learning techniques to support clinical diagnosis of arboviral diseases : A systematic review,” PLoS Negl. Trop. Dis., vol. 16, no. 1, pp. 1–37, 2022, doi: https://doi.org/10.1371/journal.pntd.0010061.
[9] K. Singh and D. Malhotra, “Meta-Health: Learning-to-Learn (Meta-learning) as a Next Generation of Deep Learning Exploring Healthcare Challenges and Solutions for Rare Disorders: A Systematic Analysis,” Arch. Comput. Methods Eng., vol. 30, no. 7, pp. 4081–4112, 2023, doi: 10.1007/s11831-023-09927-8.
[10] F. A. P. R. Putri, J. P. Tanjung, and N. P. Dharshini, “Implementation of Transfer Learning on CNN using DenseNet121 and ResNet50 for Brain Tumor Classification,” J. Informatics Telecommun. Eng., vol. 7, no. 1, pp. 102–111, 2023, [Online]. Available: https://www.researchgate.net/publication/335117624_Malang_City_Polytechnic_Web_Based_Student_Attendance_Information_System_Telecommunications_Engineering_Study_Program_Using_Fingerprint/fulltext/5d515fe34585153e594ef214/Malang-City-Polytechnic-Web-Based-S.
[11] I. H. Rather, S. Kumar, and A. H. Gandomi, Breaking the data barrier: a review of deep learning techniques for democratizing AI with small datasets, vol. 57, no. 9. Springer Netherlands, 2024.
[12] S. Karthik, P. Revathy, M. S. Kavitha, and R. Sabitha, “Chili Crop Leaf Disease Detection Using Deep Feature Extraction Using Transfer Learning with ResNet50,” 2024 Asian Conf. Intell. Technol. ACOIT 2024, pp. 1–4, 2024, doi: 10.1109/ACOIT62457.2024.10939738.
[13] V. K. Velpula, S. V. S. Prasad, J. Vadlamudi, S. Gurrala, A. V. Priya, and K. Srinidhi, “Chilli Leaf Disease Prediction System using Deep Learning Model,” 2025 Int. Conf. Emerg. Smart Comput. Informatics, ESCI 2025, pp. 1–6, 2025, doi: 10.1109/ESCI63694.2025.10988404.
[14] S. Rozlan and M. Hanafi, “Efficacy of chili plant diseases classification using deep learning: A preliminary study,” Indones. J. Electr. Eng. Comput. Sci., vol. 25, no. 3, pp. 1442–1449, 2022, doi: 10.11591/ijeecs.v25.i3.pp1442-1449.
[15] M. P. Aishwarya and A. P. Reddy, “Dataset of chilli and onion plant leaf images for classification and detection,” Data in Brief, vol. 54. 2024, doi: 10.1016/j.dib.2024.110524.
[16] S. A. Hamim and A. I. Jony, “Enhanced deep learning model architecture for plant disease detection in Chilli plants,” J. Edge Comput., vol. 3, no. 2, pp. 136–146, 2024, doi: 10.55056/jec.758.
[17] W. Suwarningsih et al., “Emphasizing Data Quality for the Identification of Chili Varieties in the Context of Smart Agriculture,” Interdiscip. J. Information, Knowledge, Manag., vol. 19, no. 1, pp. 292–304, 2024, doi: 10.28945/5257.
[18] Y. Wang, Q. Yao, J. T. Kwok, and L. M. Ni, “Generalizing from a Few Examples,” ACM Comput. Surv., vol. 53, no. 3, pp. 1–34, May 2021, doi: 10.1145/3386252.
[19] M. Fazaeli-Javan, R. Monsefi, and K. Ghiasi-Shirazi, “Hard-Positive Prototypical Networks for Few-shot Classification,” IEEE Access, vol. 13, no. February, pp. 41054–41067, 2025, doi: 10.1109/ACCESS.2025.3544638.
[20] W. Fu, L. Zhou, and J. Chen, “Bidirectional Matching Prototypical Network for Few-Shot Image Classification,” IEEE Signal Process. Lett., vol. 29, pp. 982–986, 2022, doi: 10.1109/LSP.2022.3152686.
[21] A. Rachmad, M. Fuad, and E. M. S. Rochman, “Convolutional Neural Network-Based Classification Model of Corn Leaf Disease,” Math. Model. Eng. Probl., vol. 10, no. 2, pp. 530–536, 2023, doi: 10.18280/mmep.100220.
[22] Y. Wu et al., “Improved prototypical network for active few-shot learning,” Pattern Recognit. Lett., vol. 172, pp. 188–194, 2023, doi: 10.1016/j.patrec.2023.06.015.
[23] W. Naftani, “Response of Several Chili Accessions and Molecular Markers to Yellow Leaf Curl Disease,” IPB University, 2023.
[24] M. R. Zarei and M. Komeili, “Interpretable few-shot learning with online attribute selection,” Neurocomputing, vol. 614, p. 128755, Jan. 2025, doi: 10.1016/j.neucom.2024.128755.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Rizal Amegia Saputra, Rusda Wajhillah; Yusti Farlina, Hani Noviani, Saela Nurusysyifa
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
-a.jpg)
-b.jpg)
