Pendekatan computer vision untuk analisis fitur visual dalam estimasi produktivitas tanaman kopi

Jenie Sundari; Ahmad Sinnun; Fuad Nur Hasan; Mulia Rahmayu

doi:10.35760/tr.2026.v31i1.182

Authors

Jenie Sundari Universitas Bina Sarana Informatika Author
Ahmad Sinnun Universitas Bina Sarana Informatika Author
Fuad Nur Hasan Universitas Bina Sarana Informatika Author
Mulia Rahmayu Universitas Bina Sarana Informatika Author

DOI:

https://doi.org/10.35760/tr.2026.v31i1.182

Keywords:

computer vision, coffee productivity, feature extraction, LOOCV, smart agriculture

Abstract

Coffee productivity is an important factor in supporting the sustainability of smallholder plantations, particularly in the Sukabumi region. However, conventional estimation methods that rely on manual observation tend to be subjective and inefficient. Although previous studies have applied computer vision and machine learning for yield prediction, most approaches depend on large-scale datasets and expensive sensing technologies, and often do not integrate multiple visual plant features comprehensively. This indicates a research gap in the use of simple RGB-based imaging for productivity estimation. This study aims to analyze visual features of coffee plants and develop a coffe productivity estimation model using the Random Forest algorithm. The dataset consists of 10 coffee plant images collected directly from field observations, with extracted features including fruit count, fruit maturity percentage, canopy area, leaf color, and leaf texture. Model evaluation is performed using Leave-One-Out Cross Validation (LOOCV) method to optimize data utilization on a limited dataset. The results show that the model achieves a Mean Absolute Error (MAE) of 0.06, a Root Mean Square Error (RMSE) of 0.07, and a coefficient of determination (R²) of 0.91. These results indicate good predictive performance within the available dataset. Feature importance analysis reveals that fruit count and fruit maturity percentage are the most influential factors in determining coffee productivity. This study contributes to the development of a low-cost image-based estimation approach that is practical and potentially applicable for smart agriculture in smallholder coffee plantations, although the findings remain preliminary due to the limited dataset size.

Downloads

Download data is not yet available.

References

[1] A. N. Angelopoulos, J. C. Duchi, and T. Zrnic, “PPI++: Efficient prediction-powered inference,” arXiv Prepr. arXiv:2311.01453, 2024, doi: 10.48550/arXiv.2311.01453.

[2] S. Wolfert, L. Ge, C. Verdouw, and M.-J. Bogaardt, “Big data in smart farming – A review,” Agric. Syst., vol. 153, pp. 69–80, May 2017, doi: 10.1016/j.agsy.2017.01.023.

[3] A. Kamilaris and F. X. Prenafeta-Boldú, “A review of the use of convolutional neural networks in agriculture,” J. Agric. Sci., vol. 156, no. 3, pp. 312–322, Jun. 2018, doi: 10.1017/S0021859618000436.

[4] Z. Cao, S. Sun, and X. Bao, “A review of computer vision and deep learning applications in crop growth management,” Appl. Sci., vol. 15, no. 15. Art. no. 8438, Jul. 2025. doi: 10.3390/app15158438.

[5] B. W. Ligar, “Computer vision for identifying and classifying green coffee beans: A review,” J. CoreIT J. Has. Penelit. Ilmu Komput. Teknol. Inf., vol. 8, no. 1, pp. 11–18, Jun. 2022, doi: 10.24014/coreit.v8i1.17450.

[6] M. Ashfaq, I. Khan, D. Shah, S. Ali, and M. Tahir, “Predicting wheat yield using deep learning and multi-source environmental data,” Sci. Rep., vol. 15, Art. no. 26446, Jul. 2025, doi: 10.1038/s41598-025-11780-7.

[7] S. Khaki and L. Wang, “Crop yield prediction using deep neural networks,” Front. Plant Sci., vol. 10, Art. no. 621, May 2019, doi: 10.3389/fpls.2019.00621.

[8] T. Klompenburg, A. Kassahun, and C. Catal, “Crop yield prediction using machine learning: A systematic literature review,” Comput. Electron. Agric., vol. 177, Art. no. 105709, Oct. 2020, doi: 10.1016/j.compag.2020.105709.

[9] C. A. M. Abreu Júnior et al., “Estimating coffee plant yield based on multispectral images and machine learning models,” Agronomy, vol. 12, no. 12. Art. no. 3195, Dec. 2022. doi: 10.3390/agronomy12123195.

[10] W. Zhang et al., “Deep-learning-based in-field citrus fruit detection and tracking,” Hortic. Res., vol. 9, Art. no. uhac003, Feb. 2022, doi: 10.1093/hr/uhac003.

[11] B. D. S. Barbosa, G. A. e S. Ferraz, L. Costa, Y. Ampatzidis, V. Vijayakumar, and L. M. dos Santos, “UAV-based coffee yield prediction utilizing feature selection and deep learning,” Smart Agric. Technol., vol. 1, Art. no. 100010, Dec. 2021, doi: 10.1016/j.atech.2021.100010.

[12] A. Sharifi, “Yield prediction with machine learning algorithms and satellite images,” J. Sci. Food Agric., vol. 101, no. 3, pp. 891–896, Feb. 2021, doi: 10.1002/jsfa.10696.

[13] X. Li et al., “Estimation of soybean yield based on high-throughput phenotyping and machine learning,” Front. Plant. Sci., vol. 15, Art. no. 1395760, Jun. 2024, doi: 10.3389/fpls.2024.1395760.

[14] X. Hu et al., “TasselNetV4: A vision foundation model for cross-scene, cross-scale, and cross-species plant counting,” ISPRS J. Photogramm. Remote Sens., vol. 231, pp. 745–760, Jan. 2026, doi: 10.1016/j.isprsjprs.2025.11.017.

[15] F. Eron, M. Noman, R. R. de Oliveira, and A. Chalfun-Junior, “Computer vision-aided intelligent monitoring of coffee: Towards sustainable coffee production,” Sci. Hortic., vol. 327, Art. no. 112847, 2024. doi: 10.1016/j.scienta.2024.112847.

[16] F. Palacios, M. P. Diago, P. Melo-Pinto, and J. Tardaguila, “Early yield prediction in different grapevine varieties using computer vision and machine learning,” Precis. Agric., vol. 24, no. 2, pp. 407–435, 2023, doi: 10.1007/s11119-022-09950-y.

[17] T. Zrnic and E. J. Candès, “Cross-prediction-powered inference,” Proc. Natl. Acad. Sci., vol. 121, no. 15, Art. no. e2322083121, 2024, doi: 10.1073/pnas.2322083121.

[18] S. Arwatchananukul, D. Xu, P. Charoenkwan, S. A. Moon, and R. Saengrayap, “Implementing a deep learning model for defect classification in Thai Arabica green coffee beans,” Smart Agric. Technol., vol. 9, Art. no. 100680, Nov. 2024, doi: 10.1016/j.atech.2024.100680.

[19] A. A. Maulana, “Sistem deteksi otomatis buah berbasis computer vision menggunakan YOLO,” in Pros. Semin. Nas. Teknol. Sains (STAINS), Kediri, Indonesia, Jan. 24, 2026, vol. 5, no.1, pp. 431–438, doi: 10.25077/jfu.15.1.57-69.2026.

[20] C. Zhang and J. M. Kovacs, “The application of small unmanned aerial systems for precision agriculture: A review,” Precis. Agric., vol. 13, no. 6, pp. 693–712, 2012, doi: 10.1007/s11119-012-9274-5.

[21] A. F. Solis Pino and L. S. Caicedo Apraez, “Artificial intelligence and multispectral imaging in coffee production: A systematic literature review,” Eur. J. Agron., vol. 170, Art. no. 127725, Sep. 2025, doi: 10.1016/j.eja.2025.127725.

[22] H. H. Li, M. Irgau, N. Janmohamed, K. S. Rieckmann, and D. B. Lobell, “Scalable vision-guided crop yield estimation,” in Proc. AAAI Conf. Artif. Intell., Singapore, Jan. 20–27, 2026, vol. 40, no. 1, pp. 615–622, doi: 10.1609/aaai.v40i1.37026.

[23] K. G. Liakos, P. Busato, D. Moshou, S. Pearson, and D. Bochtis, “Machine learning in agriculture: A review,” Sensors, vol. 18, no. 8, Art. no. 2674, 2018, doi: 10.3390/s18082674.

[24] C. H. de Freitas, R. D. Coelho, J. de O. Costa, and P. C. Sentelhas, “Smart coffee: Machine learning techniques for estimating Arabica coffee yield,” AgriEngineering, vol. 6, no. 4, pp. 4925–4942, 2024, doi: 10.3390/agriengineering6040281.

[25] R. O. Almeida, R. B. G. da Silva, and D. Simões, “Cut-to-length harvesting prediction tool: Machine learning model based on harvest and weather features,” Forests, vol. 15, no. 8, Art. no. 1398, 2024, doi: 10.3390/f15081398.

[26] Z. Jin et al., “A transformer-based symmetric diffusion segmentation network for wheat growth monitoring and yield counting,” Agriculture, vol. 15, no. 7, Art. no. 670, 2025, doi: 10.3390/agriculture15070670.