Klasifikasi Kematangan Buah Kelapa Sawit Dengan SimCLR Berbasis HSV Controlled Color Augmentasi
DOI:
https://doi.org/10.30865/jurikom.v13i3.9794Keywords:
Contrastive Learning, Eta-Squared, HSV Augmentation, Maturity Classification, Oil Palm, Self-Supervised LearningAbstract
Self-supervised learning with the SimCLR method requires appropriate data augmentation as the foundation for contrastive representation learning. In the task of classifying oil palm fruit maturity, color is the main discriminative feature, so the standard RGB-based ColorJitter augmentation has the potential to distort critical color information. This study proposes an augmentation framework based on the HSV color space with eight parameter configurations (C1–C8) determined in a data-driven manner through Eta-squared (η²) analysis, designed to preserve the semantic integrity of maturity color while generating varied positive pairs. Experiments were conducted on 1,016 oil palm fruit images across three classes (Unripe, Ripe, Overripe) using ResNet-18 as the SimCLR encoder with a linear evaluation protocol. The results show that all HSV configurations outperform the Baseline (82.22%), with HSV_C1 being the best configuration, achieving a test accuracy of 94.44% and Macro F1-Score of 94.46% (+12.22 pp). The η² analysis confirms that the Hue component is the most discriminative feature between classes, so constraining it during augmentation proves essential for the quality of the resulting representations. The proposed framework consistently improves SimCLR performance in color-based classification domains with minimal labeled data requirements.
References
[1] “Kelapa Sawit Sebagai Pahlawan Devisa Indonesia - Beranda.” Accessed: Dec. 21, 2025. [Online]. Available: https://www.bpdp.or.id/kelapa-sawit-sebagai-pahlawan-devisa-indonesia
[2] Ministry of Agriculture, “Palm Oil Outlook,” pp. 1–23, 2024.
[3] D. R. Sulistyaningrum, M. A. Azahari, B. Setiyono, and D. Adzkya, Identification of the Maturity Level of Oil Palm Fruit Using a Combination of the You Only Look Once Version 8 Model and Convolutional Neural Network, vol. 2024, no. Ictaff 2024. Atlantis Press International BV, 2025. doi: 10.2991/978-94-6463-825-7_13.
[4] A. W. Setiawan, “Palm Oil Fresh Fruit Bunch Grading System Using Multispectral Image Analysis in HSV,” pp. 85–88, 2020.
[5] Afrisawati, “Pemilihan buah kelapa sawit unggul untuk dijadikan cpo menggunakan metode mfep di pks sei mangkei ptpn iv,” J. Sci. Soc. Res., vol. 4307, no. 1, pp. 52–56, 2025.
[6] S. I. & Uyun, S. Guslianto, “Klasifikasi Kematangan Buah Sawit Berdasarkan,” vol. 9, no. 3, pp. 407–414, 2023.
[7] R. Triyogi, R. Magdalena, and B. Hidayat, “Mendeteksi Kematangan Buah Kelapa Sawit Menggunakan Convolution Neural Network Deep Learning,” vol. 1, no. 1, pp. 22–27, 2023.
[8] X. Zhou, X. Hu, and J. Sun, “A review of fruit ripeness recognition methods based on deep learning,” Cyber-Physical Syst., vol. 11, no. 4, pp. 508–542, Oct. 2025, doi: 10.1080/23335777.2025.2467639;WGROUP:STRING:PUBLICATION.
[9] S. Sornapudi and R. Singh, “Self-Supervised Backbone Framework for Diverse Agricultural Vision Tasks,” 2024, [Online]. Available: http://arxiv.org/abs/2403.15248
[10] J. Zulkarnain and T. Hidayat, “Klasifikasi Tingkat Kematangan Tandan Buah Segar Kelapa Sawit Menggunakan Pendekatan Deep Learning,” vol. 12, no. 3, pp. 748–758, 2023.
[11] S. Nur et al., “Image Detection and Classification of Oil Palm Fruit Bunches,” pp. 108–113, 2022.
[12] H. Li et al., “An improved YOLOv5s model for assessing apple graspability in automated harvesting scene,” Front. Plant Sci., vol. 14, no. December, pp. 1–15, 2023, doi: 10.3389/fpls.2023.1323453.
[13] J. Li et al., “Label-efficient learning in agriculture: A comprehensive review,” Comput. Electron. Agric., vol. 215, p. 108412, Dec. 2023, doi: 10.1016/J.COMPAG.2023.108412.
[14] T. Chen, S. Kornblith, M. Norouzi, and G. Hinton, “A Simple Framework for Contrastive Learning of Visual Representations,” no. Figure 1, 2020.
[15] S. Bunyang et al., “Self-supervised learning advanced plant disease image classification with SimCLR,” Adv. Comput. Intell. 2023 35, vol. 3, no. 5, pp. 18-, Oct. 2023, doi: 10.1007/S43674-023-00065-Z.
[16] L. A. Varga, H. Frank, and A. Zell, “Self-supervised Pretraining for Hyperspectral Classification of Fruit Ripeness,” pp. 97–108.
[17] S. Zini, A. Gomez-villa, M. Buzzelli, and M. Bicocca, “Planckian Jitter : countering the color-crippling effects of color jitter on self-supervised training,” vol. 1, pp. 1–15.
[18] M. Haziq, I. Azmi, F. H. Hashim, A. B. Huddin, and M. S. Sajab, “Correlation Study between the Organic Compounds and Ripening Stages of Oil Palm Fruitlets Based on the Raman Spectra,” 2022.
[19] R. Nasirly, F. Arsy, and R. Qolby, “Comparison of Machine Learning Algorithms for Palm Oil Fresh Fruit Bunch ( FFB ) Ripeness,” vol. 69, no. 1, pp. 39–48, 2025.
[20] S. Zolfagharnassab, A. Rashid, B. Mohamed, R. Ehsani, H. Z. Jaafar, and I. Bin Aris, “Classification of Oil Palm Fresh Fruit Bunches Based on Their Maturity Using Thermal Imaging Technique,” pp. 1–20, 2022.
[21] M. L. Marszalek, B. Le Saux, P. P. Mathieu, A. Nowakowski, and D. Springer, “Self-Supervised Learning - a Way To Minimize Time and Effort for Precision Agriculture?,” Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. - ISPRS Arch., vol. 43, no. B3-2022, pp. 1327–1333, 2022, doi: 10.5194/isprs-archives-XLIII-B3-2022-1327-2022.
[22] V. Margapuri and M. Neilsen, “Classification of Seeds using Domain Randomization on Self-Supervised Learning Frameworks,” 2021 IEEE Symp. Ser. Comput. Intell. SSCI 2021 - Proc., 2021, doi: 10.1109/SSCI50451.2021.9659998.
[23] K. Nguyen, Y. Nguyen, and B. Le, “Semi-Supervising Learning, Transfer Learning, and Knowledge Distillation with SimCLR,” 2021, [Online]. Available: http://arxiv.org/abs/2108.00587
[24] J. Y. Goh, Y. Md Yunos, and M. S. Mohamed Ali, “Fresh Fruit Bunch Ripeness Classification Methods: A Review,” Food Bioprocess Technol., vol. 18, no. 1, pp. 183–206, 2025, doi: 10.1007/s11947-024-03483-0.
