CFO-RetinaNet: Convolutional Feature Optimization for Oil Palm Ripeness Assessment in Precision Agriculture

Authors

DOI:

https://doi.org/10.26555/jiteki.v11i2.30753

Keywords:

Deep Learning, RetinaNet optimisation, Ordinal regression, Multi-scale CNN, Agricultural automation

Abstract

Accurate ripeness assessment of oil palm fruit bunches (FFB) is critical for optimizing yield and quality in the palm oil industry, yet manual grading remains subjective and labor-intensive. This study proposes CFO-RetinaNet, an enhanced RetinaNet framework integrating deformable convolutions and hybrid attention mechanisms to optimize multi-scale convolutional features for robust ripeness classification under variable field conditions. Our key contribution is threefold: (1) a novel dataset of 4,728 high-resolution, expert-annotated FFB images spanning five ripeness stages (Immature to Decayed), collected under diverse lighting and occlusion scenarios in Central Kalimantan, Indonesia; (2) a feature optimization pipeline combining adaptive feature fusion and dynamic focal loss to improve discriminative capability for nuanced inter-class distinctions; and (3) a scalable deep learning solution validated through rigorous field testing. The model achieves a mean average precision (mAP) of 83.6% and an F1-score of 98.3%, outperforming YOLOv5 (82.5% mAP) and Faster R-CNN (76.4% mAP), with 18.5% fewer misclassifications than standard RetinaNet. It retains 99% accuracy in low-light conditions and reduces labor costs by automating error-prone grading tasks. By publicly releasing the dataset and framework, this work advances precision agriculture standards, offering a transferable solution for ordinal maturity classification in perennial crops while supporting sustainable palm oil production through optimized harvesting decisions.

Author Biography

Muhammad Alkam Alfariz, Universitas Mercu Buana

Muhammad Alkam Alfariz is a dedicated and ambitious student in the Computer Science program at Mercu Buana University, Jakarta, Indonesia. In his final year, he maintains an impressive academic record with a GPA of 3.91/4.00. His professional experience includes internships at RS EMC Alam Sutera and Halodoc, where he honed his IT support, automation scripting, and hardware maintenance skills. Additionally, he has served as a seasonal instructor for the Ministry of Industry and as a computer laboratory assistant at ASLAB Fasilkom UMB. Alfariz is proficient in programming languages such as C++, Python, and Java and possesses strong soft skills in leadership, critical thinking, and teamwork. His academic and professional endeavours reflect a passion for leveraging technology to solve real-world problems

References

[1] E. Cisneros, K. K. -Katos, and N. Nuryartono, “Palm oil and the politics of deforestation in Indonesia,” J Environ Econ Manage, vol. 108, p. 102453, Jul. 2021, https://doi.org/10.1016/j.jeem.2021.102453.

[2] M. S. Mahmud and K. P. Chong, “Effects of Liming on Soil Properties and Its Roles in Increasing the Productivity and Profitability of the Oil Palm Industry in Malaysia,” Agriculture, vol. 12, no. 3, p. 322, Feb. 2022, https://doi.org/10.3390/agriculture12030322.

[3] V. J. Reiss-Woolever, S. H. Luke, J. Stone, G. E. Shackelford, and E. C. Turner, “Systematic mapping shows the need for increased socio-ecological research on oil palm,” Environmental Research Letters, vol. 16, no. 6, p. 063002, Jun. 2021, https://doi.org/10.1088/1748-9326/abfc77.

[4] M. N. Akhtar, E. Ansari, S. S. N. Alhady, and E. A. Bakar, “Leveraging on Advanced Remote Sensing- and Artificial Intelligence-Based Technologies to Manage Palm Oil Plantation for Current Global Scenario: A Review,” Agriculture, vol. 13, no. 2, p. 504, Feb. 2023, https://doi.org/10.3390/agriculture13020504.

[5] L. M. Ayompe, M. Schaafsma, and B. N. Egoh, “Towards sustainable palm oil production: The positive and negative impacts on ecosystem services and human wellbeing,” J Clean Prod, vol. 278, p. 123914, Jan. 2021, https://doi.org/10.1016/j.jclepro.2020.123914.

[6] H. Wei et al., “Agronomic and Physicochemical Properties Facilitating the Synchronization of Grain Yield and the Overall Palatability of Japonica Rice in East China,” Agriculture, vol. 12, no. 7, p. 969, Jul. 2022, https://doi.org/10.3390/agriculture12070969.

[7] I. Bonet, M. Gongora, F. Acevedo, and I. Ochoa, “Deep Learning Model to Predict the Ripeness of Oil Palm Fruit,” in Proceedings of the 16th International Conference on Agents and Artificial Intelligence, pp. 1068–1075, 2024, https://doi.org/10.5220/0012434600003636.

[8] T. Zhang, Y. Cai, P. Zhuang, and J. Li, “Remotely Sensed Crop Disease Monitoring by Machine Learning Algorithms: A Review,” Unmanned Systems, vol. 12, no. 1, pp. 161–171, Jan. 2024, https://doi.org/10.1142/S2301385024500237.

[9] G. N. Elwirehardja, and J. S. Prayoga, “Oil palm fresh fruit bunch ripeness classification on mobile devices using deep learning approaches,” Comput Electron Agric, vol. 188, p. 106359, Sep. 2021, https://doi.org/10.1016/j.compag.2021.106359.

[10] R. Malyala, “Development of a Convolutional Neural Network Model for Automated Ripeness Classification of Palm Oil Fresh Fruit Bunches,” International Journal of Innovative Science and Research Technology (IJISRT), pp. 1040–1046, Nov. 2024, https://doi.org/10.38124/ijisrt/IJISRT24NOV762.

[11] S. Etaati, J. Khoramdel, and E. Najafi, “Automated Wheat Disease Detection using Deep Learning: an Object Detection and Classification Approach,” in 11th RSI International Conference on Robotics and Mechatronics (ICRoM), pp. 116–121, Dec. 2023, https://doi.org/10.1109/ICRoM60803.2023.10412538.

[12] M. J. M. van Eijs et al., “Highly multiplexed spatial analysis identifies tissue-resident memory T cells as drivers of ulcerative and immune checkpoint inhibitor colitis,” iScience, vol. 26, no. 10, p. 107891, Oct. 2023, https://doi.org/10.1016/j.isci.2023.107891.

[13] P. Kiszel et al., “Class switch towards spike protein-specific IgG4 antibodies after SARS-CoV-2 mRNA vaccination depends on prior infection history,” Sci Rep, vol. 13, no. 1, p. 13166, Aug. 2023, https://doi.org/10.1038/s41598-023-40103-x.

[14] S. N. A. B. M. Robi, M. A. B. M. Izhar, M. Bin Sahrim, and N. B. Ahmad, “Image Detection and Classification of Oil Palm Fruit Bunches,” in 4th International Conference on Smart Sensors and Application (ICSSA), pp. 108–113, Jul. 2022, https://doi.org/10.1109/ICSSA54161.2022.9870945.

[15] N. Khamis, H. Selamat, S. Ghazalli, N. I. M. Saleh, and N. Yusoff, “Comparison of Palm Oil Fresh Fruit Bunches (FFB) Ripeness Classification Technique using Deep Learning Method,” in 13th Asian Control Conference (ASCC), pp. 64–68, May 2022, https://doi.org/10.23919/ASCC56756.2022.9828345.

[16] S. Zhang et al., “A calibration method for contact parameters of agricultural particle mixtures inspired by the Brazil nut effect (BNE): The case of tiger nut tuber-stem-soil mixture,” Comput Electron Agric, vol. 212, p. 108112, Sep. 2023, https://doi.org/10.1016/J.COMPAG.2023.108112.

[17] M. Coscia and C. Vandeweerdt, “Posts on central websites need less originality to be noticed,” Sci Rep, vol. 12, no. 1, p. 15265, Sep. 2022, https://doi.org/10.1038/s41598-022-19433-9.

[18] H. H. Wang, Y. C. Wang, B. L. Wee, and S. W. Sim, “Novel Feature Extraction for Oil Palm Bunches Classification,” Journal of Advanced Research in Applied Sciences and Engineering Technology, vol. 34, no. 1, pp. 350–360, Nov. 2023, https://doi.org/10.37934/araset.34.1.350360.

[19] M. S. M. Alfatni, A. R. M. Shariff, O. M. B. Saaed, A. M. Albhbah, and A. Mustapha, “Colour Feature Extraction Techniques for Real Time System of Oil Palm Fresh Fruit Bunch Maturity Grading,” IOP Conf Ser Earth Environ Sci, vol. 540, no. 1, p. 012092, Jul. 2020, https://doi.org/10.1088/1755-1315/540/1/012092.

[20] C. Riefolo, A. Belmonte, R. Quarto, F. Quarto, S. Ruggieri, and A. Castrignanò, “Potential of GPR data fusion with hyperspectral data for precision agriculture of the future,” Comput Electron Agric, vol. 199, p. 107109, Aug. 2022, https://doi.org/10.1016/J.COMPAG.2022.107109.

[21] S. Puttinaovarat, S. Chai-Arayalert, and W. Saetang, “Oil Palm Bunch Ripeness Classification and Plantation Verification Platform: Leveraging Deep Learning and Geospatial Analysis and Visualization,” ISPRS Int J Geoinf, vol. 13, no. 5, p. 158, May 2024, https://doi.org/10.3390/ijgi13050158.

[22] I. M. Shaikh, M. N. Akhtar, A. Aabid, and O. S. Ahmed, “Enhancing sustainability in the production of palm oil: creative monitoring methods using YOLOv7 and YOLOv8 for effective plantation management,” Biotechnology Reports, vol. 44, p. e00853, Dec. 2024, https://doi.org/10.1016/j.btre.2024.e00853.

[23] Y. Yang, X. Li, Y. Guan, H. Wang, C. Kong, and J. Jiang, “LHP: Logical hypergraph link prediction,” Expert Syst Appl, vol. 222, p. 119842, Jul. 2023, https://doi.org/10.1016/J.ESWA.2023.119842.

[24] M. A. Zulkhoiri et al., “Investigation of oil palm fruit bunch ripeness classification using machine learning classifiers,” E3S Web of Conferences, vol. 595, p. 02010, Nov. 2024, https://doi.org/10.1051/e3sconf/202459502010.

[25] G. T. H. Tzuan, F. H. Hashim, T. Raj, A. Baseri Huddin, and M. S. Sajab, “Oil Palm Fruits Ripeness Classification Based on the Characteristics of Protein, Lipid, Carotene, and Guanine/Cytosine from the Raman Spectra,” Plants, vol. 11, no. 15, p. 1936, Jul. 2022, https://doi.org/10.3390/plants11151936.

[26] R. Kurniawan, S. Samsuryadi, F. S. Mohamad, H. O. L. Wijaya, and B. Santoso, “Classification of palm oil fruit ripeness based on AlexNet deep Convolutional Neural Network,” SINERGI, vol. 29, no. 1, p. 207, Jan. 2025, https://doi.org/10.22441/sinergi.2025.1.019.

[27] N. Teimouri, R. N. Jørgensen, and O. Green, “Novel Assessment of Region-Based CNNs for Detecting Monocot/Dicot Weeds in Dense Field Environments,” Agronomy, vol. 12, no. 5, p. 1167, May 2022, https://doi.org/10.3390/agronomy12051167.

[28] J. W. Lai, H. R. Ramli, L. I. Ismail, and W. Z. W. Hasan, “Real-Time Detection of Ripe Oil Palm Fresh Fruit Bunch Based on YOLOv4,” IEEE Access, vol. 10, pp. 95763–95770, 2022, https://doi.org/10.1109/ACCESS.2022.3204762.

[29] M. Rastgou et al., “A technical evaluation on the mathematical attitudes and fitting accuracy of soil moisture retention curve models,” Comput Electron Agric, vol. 215, p. 108347, Dec. 2023, https://doi.org/10.1016/J.COMPAG.2023.108347.

[30] Y. Wang, “Deep Learning Methods Used in Precision Agriculture,” BIO Web Conf, vol. 142, p. 01004, Nov. 2024, https://doi.org/10.1051/bioconf/202414201004.

[31] P. Bharman, S. Ahmad Saad, S. Khan, I. Jahan, M. Ray, and M. Biswas, “Deep Learning in Agriculture: A Review,” Asian Journal of Research in Computer Science, pp. 28–47, Feb. 2022, https://doi.org/10.9734/ajrcos/2022/v13i230311.

[32] Y. Yuliza, R. Muwardi, M. Rhozaly, L. Lenni, M. Yunita, and G. E. Yehezkiel, “Fast Human Recognition System on Real-Time Camera,” Jurnal Ilmiah Teknik Elektro Komputer dan Informatika, vol. 9, no. 4, pp. 895–903, Sep. 2023, https://doi.org/10.26555/jiteki.v9i4.27009.

[33] V. Psiroukis, B. E. -Garcia, A. Chitos, A. Dedousis, K. Karantzalos, and S. Fountas, “Assessment of Different Object Detectors for the Maturity Level Classification of Broccoli Crops Using UAV Imagery,” Remote Sens (Basel), vol. 14, no. 3, p. 731, Feb. 2022, https://doi.org/10.3390/rs14030731.

[34] C. Wang, H. Wang, Q. Han, Z. Zhang, D. Kong, and X. Zou, “Strawberry Detection and Ripeness Classification Using YOLOv8+ Model and Image Processing Method,” Agriculture, vol. 14, no. 5, p. 751, May 2024, https://doi.org/10.3390/agriculture14050751.

[35] W. Zhang, “A Fruit Ripeness Detection Method using Adapted Deep Learning-based Approach,” International Journal of Advanced Computer Science and Applications, vol. 14, no. 9, 2023, https://doi.org/10.14569/IJACSA.2023.01409121.

[36] A. A. Mirani, S. Zaman, R. Chohan, S. Siraj, and S. Lakho, “A Review of the Internet of Things and Deep Learning in Agriculture: A Smart Agriculture Prespective,” Journal of Hunan University Natural Sciences, vol. 50, no. 10, 2023, https://doi.org/10.55463/issn.1674-2974.50.10.18.

[37] S. Jain, “DeepSeaNet: Improving Underwater Object Detection using EfficientDet,” In 4th International Conference on Applied Artificial Intelligence (ICAPAI), pp. 1-11, 2024, https://doi.org/10.1109/ICAPAI61893.2024.10541265.

[38] M. Y. M. A. Mansour, K. D. Dambul, and K. Y. Choo, “Object Detection Algorithms for Ripeness Classification of Oil Palm Fresh Fruit Bunch,” International Journal of Technology, vol. 13, no. 6, p. 1326, Nov. 2022, https://doi.org/10.14716/ijtech.v13i6.5932.

[39] H. H. Wang, Y. C. Wang, B. L. Wee, and S. W. Sim, “Novel Feature Extraction for Oil Palm Bunches Classification,” Journal of Advanced Research in Applied Sciences and Engineering Technology, vol. 34, no. 1, pp. 350–360, Nov. 2023, https://doi.org/10.37934/araset.34.1.350360.

[40] L. Asritha, M. H. Chandra Prasad, K. V. Sai, and M. Jayaraj, “Fruit Ripeness Detection Using Deep Learning,” Interantional Journal Of Scientific Research In Engineering And Management, vol. 7, no. 4, Apr. 2023, https://doi.org/10.55041/IJSREM18758.

[41] G. Chen et al., “A review of global precision land-leveling technologies and implements: Current status, challenges and future trends,” Comput Electron Agric, vol. 220, p. 108901, May 2024, https://doi.org/10.1016/J.COMPAG.2024.108901.

[42] W. Yang et al., “Deformable convolution and coordinate attention for fast cattle detection,” Comput Electron Agric, vol. 211, p. 108006, Aug. 2023, https://doi.org/10.1016/J.COMPAG.2023.108006.

[43] M. Y. M. A. Mansour, “A Review Of Non-Destructive Ripeness Classification Techniques For Oil Palm Fresh Fruit Bunches,” J Oil Palm Res, vol. 35, no. 4, pp. 543-554, Sep. 2022, https://doi.org/10.21894/jopr.2022.0063.

[44] M. Shiddiq et al., “Multispectral imaging and deep learning for oil palm fruit bunch ripeness detection,” Bulletin of Electrical Engineering and Informatics, vol. 13, no. 6, pp. 4168–4181, Dec. 2024, https://doi.org/10.11591/eei.v13i6.8120.

[45] C. A. Toledo, M. M. Crawford, and M. R. Tuinstra, “Integrating multi-modal remote sensing, deep learning, and attention mechanisms for yield prediction in plant breeding experiments,” Front Plant Sci, vol. 15, Jul. 2024, https://doi.org/10.3389/fpls.2024.1408047.

[46] E. P. Wonohardjo, D. Pratama, T. R. S. Industrial, R. A. A. Computer, “Effect of Pre-processing Dataset on Classification Performance of Deep Learning Model for Detection of Oil Palm Fruit Ripe,” in International Conference on ICT for Smart Society (ICISS), pp. 1–6, Aug. 2022, https://doi.org/10.1109/ICISS55894.2022.9915269.

[47] N. D. Gholba and A. Kumar, “Deep Learning Based Census and Mapping of Oil Palm Plantations from Very High Resolution Satellite Images,” in IGARSS IEEE International Geoscience and Remote Sensing Symposium, pp. 4085–4089, Jul. 2024, https://doi.org/10.1109/IGARSS53475.2024.10642932.

[48] A. Haq, E. S. Cahyadi, M. S. Kasyfillah, R. Sarno, and A. T. Haryono, “Multi-class Oil Palm Trees Condition Detection from UAV Images using Faster R-CNN with EfficientNetV2,” in 2nd International Conference on Technology Innovation and Its Applications (ICTIIA), pp. 1–6, Sep. 2024, https://doi.org/10.1109/ICTIIA61827.2024.10761449.

[49] M. H. Junos, A. S. B. M. Khairuddin, M. I. Kairi, and Y. M. Siran, “Automatic Object Detection in Oil Palm Plantation using a Hybrid Feature Extractor of YOLO-based Model,” AIJR Proceedings, pp. 49–56, 2022, https://doi.org/10.21467/proceedings.141.8.

[50] Z. Chen, S. Elsaid, D. Y. Y. Sim, T. Maul, and I. Y. Liao, “Detection of Oil Palm Fresh Fruit Bunches (FFBS) with Computer Vision Models,” in 2022 International Conference on Mechanical, Automation and Electrical Engineering (CMAEE), pp. 86–91, Dec. 2022, https://doi.org/10.1109/CMAEE58250.2022.00023.

[51] M. Grady Naftali, G. Hugo, and Suharjito, “Palm Oil Counter: State-of-the-Art Deep Learning Models for Detection and Counting in Plantations,” IEEE Access, vol. 12, pp. 90395–90417, 2024, https://doi.org/10.1109/ACCESS.2024.3419835.

[52] N. Aloufi, A. Alnori, V. Thayananthan, and A. Basuhail, “Object Detection Performance Evaluation for Autonomous Vehicles in Sandy Weather Environments,” Applied Sciences, vol. 13, no. 18, p. 10249, Sep. 2023, https://doi.org/10.3390/app131810249.

[53] D. S. Prasvita, D. Chahyati, and A. M. Arymurthy, “Automatic Detection of Oil Palm Growth Rate Status with YOLOv5,” International Journal of Advanced Computer Science and Applications, vol. 14, no. 3, 2023, https://doi.org/10.14569/IJACSA.2023.0140361.

Downloads

Published

2025-05-06

How to Cite

[1]
M. A. Alfariz and H. Santoso, “CFO-RetinaNet: Convolutional Feature Optimization for Oil Palm Ripeness Assessment in Precision Agriculture”, J. Ilm. Tek. Elektro Komput. Dan Inform, vol. 11, no. 2, pp. 251–262, May 2025.

Issue

Vol. 11 No. 2 (2025): June

Section

Articles

License

Copyright (c) 2025 Hadi Santoso, Muhammad Alkam Alfariz

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Authors who publish with JITEKI agree to the following terms:

  1. Authors retain copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC BY-SA 4.0) that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
  2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
  3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.

Lisensi Creative Commons

This work is licensed under a Creative Commons Attribution 4.0 International License

Similar Articles

1 2 3 4 5 > >> 

You may also start an advanced similarity search for this article.