Analysis of Accuracy and Computational Efficiency of Android-Based Palm Maturity Classification System Using K-Nearest Neighbor Method

Abstract

Accurately determining the ripeness of oil palm Fresh Fruit Bunches (FFB) is crucial to maximizing the quality of Crude Palm Oil (CPO). Conventional methods rely on visual assessment or laboratory tests that are destructive, expensive, and inefficient at the field scale. This study proposes an android-based, non-destructive FFB ripeness classification system that uses color feature extraction and the K-Nearest Neighbors (K-NN) algorithm. A total of 65 FFB images directly from the tree are divided into training data (50 images) and test data (15 images) with three ripeness classes: raw, ripe, and overripe. Features are extracted through multilevel color thresholding segmentation, then calculated using RGB color averages, RGB normalization, and four Vegetation Indices (NDVI, SAVI, EVI, VARI). The test results show that the combination of Vegetation Indices with K-NN achieves the highest accuracy, 98% on the training data and 93.33% on the test data, with only one classification error. The system runs on-device with an average computation time of 3.3 seconds per image, demonstrating sufficient efficiency for real-time applications in plantations. This study concludes that the mobile approach based on K-NN and the Vegetation Index is worthy of adoption as a fast, accurate, and non-destructive harvest decision-support tool. However, further lighting optimization and dataset expansion are still needed for broader generalization.

REFERENCES

Alfatni, M. S. M., Mohamed Shariff, A. R., Ben Saaed, O. M., Albhbah, A. M., & Mustapha, A. (2020). Colour Feature Extraction Techniques for Real Time System of Oil Palm Fresh Fruit Bunch Maturity Grading. IOP Conference Series: Earth and Environmental Science, 540(1). https://doi.org/10.1088/1755-1315/540/1/012092

Bannari, A., Asalhi, H., & Teillet, P. M. (2002). Transformed difference vegetation index (TDVI) for vegetation cover mapping. IEEE International Geoscience and Remote Sensing Symposium, 5, 3053–3055 vol.5. https://doi.org/10.1109/IGARSS.2002.1026867

Barrera, K., Rodellar, J., Alférez, S., & Merino, A. (2023). Automatic normalized digital color staining in the recognition of abnormal blood cells using generative adversarial networks. Computer Methods and Programs in Biomedicine, 240. https://doi.org/10.1016/j.cmpb.2023.107629

Boucetta, C., Hussenet, L., & Herbin, M. (2023). Improved Euclidean Distance in the K Nearest Neighbors Method. In U. R. Krieger, G. Eichler, C. Erfurth, & G. Fahrnberger (Eds.), the 23rd International Conference on Innovations for Community Services (pp. 315–324). Springer Nature Switzerland.

Burge, M. J. (2022). Digital Image Processing: An Algorithmic Introduction. Springer Nature.

Cherie, D., Herodian, S., Ahmad, U., Mandang, T., & Makky, M. (2015). Optical characteristics of oil palm fresh fruits bunch (FFB) under three spectrum regions influence for harvest decision. International Journal on Advanced Science, Engineering and Information Technology, 5(3), 255–263. https://doi.org/10.18517/ijaseit.5.3.534

Huete, A. R. (1988). A soil-adjusted vegetation index (SAVI). Remote Sensing of Environment, 25(3), 295–309. https://doi.org/https://doi.org/10.1016/0034-4257(88)90106-X

Khan, A. I., & Al-Habsi, S. (2020). Machine Learning in Computer Vision. Procedia Computer Science, 167(2019), 1444–1451. https://doi.org/10.1016/j.procs.2020.03.355

Makky, M. (2016). Trend in non-destructive quality inspections for oil palm fresh fruits bunch in Indonesia. International Food Research Journal, 23(1), 81–90. https://doi.org/10.4149/neo_2010_01_079

Makky, M., Soni, P., & Salokhe, V. M. (2014). Automatic non-destructive quality inspection system for oil palm fruits. International Agrophysics, 28(3), 319–329. https://doi.org/10.2478/intag-2014-0022

Naji, S., Jalab, H. A., & Kareem, S. A. (2019). A survey on skin detection in colored images. Artificial Intelligence Review, 52(2), 1041–1087. https://doi.org/10.1007/s10462-018-9664-9

Pertanian RI, K. (2023). Statistik Perkebunan Kelapa Sawit Indonesia 2022. In Direktorat Jenderal Perkebunan. https://ditjenbun.pertanian.go.id

Purbolingga, Y., Ridwan, A., & Putri, D. M. (2025). A Machine Learning-Based Ambiguous Alphabet Recognition for Indonesian Sign Language System (SIBI). CogITo Smart Journal, 11(1), 1–14. https://doi.org/10.31154/cogito.v11i1.816.1-14

Resta, F. S. A., Setiawan, R., Rivai, M., Arif, R. El, Natawijaya, A., & Hadad, A. G. Al. (2026). Multimodal Radar-Vision for Oil Palm Fresh Fruit Bunch Ripeness Classification. IEEE Access, 14, 42975–42991. https://doi.org/10.1109/ACCESS.2026.3675310

Ridwan, A., Purbolingga, Y., & Hanisah, H. (2024). Utilizing Convolutional Neural Network for Learning Web-Based Braille Letter Classification System. Journal of Computer Networks, Architecture and High Performance Computing, 6(1). https://doi.org/10.47709/cnahpc.v6i1.3386

Saad, B., Ling, C. W., Jab, M. S., Lim, B. P., Mohamad Ali, A. S., Wai, W. T., & Saleh, M. I. (2007). Determination of free fatty acids in palm oil samples using non-aqueous flow injection titrimetric method. Food Chemistry, 102(4), 1407–1414. https://doi.org/https://doi.org/10.1016/j.foodchem.2006.05.051

Srivastava, S., & Sadistap, S. (2018). Data processing approaches and strategies for non-destructive fruits quality inspection and authentication: a review. Journal of Food Measurement and Characterization, 12(4), 2758–2794. https://doi.org/10.1007/s11694-018-9893-2

Suharjito, Elwirehardja, G. N., & Prayoga, J. S. (2021). Oil palm fresh fruit bunch ripeness classification on mobile devices using deep learning approaches. Computers and Electronics in Agriculture, 188, 106359. https://doi.org/https://doi.org/10.1016/j.compag.2021.106359

Wang, A. X., Chukova, S. S., & Nguyen, B. P. (2023). Ensemble k-nearest neighbors based on centroid displacement. Information Sciences, 629, 313–323. https://doi.org/https://doi.org/10.1016/j.ins.2023.02.004

Yan, K., Gao, S., Yan, G., Ma, X., Chen, X., Zhu, P., Li, J., Gao, S., Gastellu-Etchegorry, J. P., Myneni, R. B., & Wang, Q. (2025). A global systematic review of the remote sensing vegetation indices. International Journal of Applied Earth Observation and Geoinformation, 139(November 2024), 104560. https://doi.org/10.1016/j.jag.2025.104560