Drone Technologies Lab, MURTI Research Centre, Department of Artificial Intelligence and Data Science, GITAM School of Technology, GITAM (Deemed to be) University, Bengaluru, Karnataka, India.
The paper aims to develop an efficient deep learning algorithm to classify the coconut harvesting level stages by using the various images of the coconuts. The system uses the images of the various types of coconuts to find, evaluate, and harvest coconuts at the best phases of maturity i.e. tender, snowball, or mature, based on the domain of applications. Using characteristics like color, size, and texture, from the images taken from the existing images of coconuts the proposed Deep Learning model identifies and categorize coconuts, assuring accurate harvesting for products like oil, copra, and coconut water. The proposed methodology using VGG19 algorithm demonstrates the high accuracy to automatically predict the various harvesting stages like tender, snowball and copra using a various feature s from the coconut images captured. The proposed deep learning model was trained on the various existing coconut image datasets using data augmentation to enhance the VGG19 based CNN-model. The proposed model performance is valuated using metrics like precision, recall, specificity and F1-score. Results reveal that the image augmentation, the transformation methods with the VGG19 model attained the testing accuracy 98.94% and validation accuracy of 97.68%. Our research contributes best on the classification of various harvesting stages that will benefit and help the farmers job of various harvesting stages while promoting the economic growth.
Keywords
Deep Learning, CNN, VGG19, Image Augmentation, Harvesting.
V. Krishnakumar, P. K. Thampan, and M. A. Nair, Eds., The Coconut Palm (Cocos nucifera L.) - Research and Development Perspectives. Springer Singapore, 2018. doi: 10.1007/978-981-13-2754-4.
R. Pandiselvam, A. C. Khanashyam, R. Dakshayani, F. C. Beveridge, S. Karouw, and M. R. Manikantan, “Harvest and Postharvest Management of Coconut,” The Coconut, pp. 99–110, Jan. 2024, doi: 10.1079/9781789249736.0007.
A. A. Mana, A. Allouhi, A. Hamrani, S. Rehman, I. el Jamaoui, and K. Jayachandran, “Sustainable AI-based production agriculture: Exploring AI applications and implications in agricultural practices,” Smart Agricultural Technology, vol. 7, p. 100416, Mar. 2024, doi: 10.1016/j.atech.2024.100416.
S. Varur, S. Mainale, S. Korishetty, A. Shanbhag, U. Kulkarni, and M. S. M, “Classification of Maturity Stages of Coconuts using Deep Learning on Embedded Platforms,” 2023 3rd International Conference on Smart Data Intelligence (ICSMDI), pp. 343–349, Mar. 2023, doi: 10.1109/icsmdi57622.2023.00067.
Anjali et al., “State-of-the-art non-destructive approaches for maturity index determination in fruits and vegetables: principles, applications, and future directions,” Food Production, Processing and Nutrition, vol. 6, no. 1, Feb. 2024, doi: 10.1186/s43014-023-00205-5.
R. K. Megalingam, S. K. Manoharan, and R. B. Maruthababu, “Integrated fuzzy and deep learning model for identification of coconut maturity without human intervention,” Neural Computing and Applications, vol. 36, no. 11, pp. 6133–6145, Jan. 2024, doi: 10.1007/s00521-023-09402-2.
U. Usman, “Improving Classification Accuracy of Local Coconut Fruits with Image Augmentation and Deep Learning Algorithm Convolutional Neural Networks (CNN),” Journal of Applied Data Sciences, vol. 6, no. 1, pp. 1–19, Jan. 2024, doi: 10.47738/jads.v6i1.389.
G. Hou, H. Chen, M. Jiang, and R. Niu, “An Overview of the Application of Machine Vision in Recognition and Localization of Fruit and Vegetable Harvesting Robots,” Agriculture, vol. 13, no. 9, p. 1814, Sep. 2023, doi: 10.3390/agriculture13091814.
I. W. Sudiarta et al., “Improvement of Processing and Marketing of Innovative Coconut and Nut-Based Products at the Sari Nadhi Business Study Group, Carangsari Village, Badung,” AJARCDE (Asian Journal of Applied Research for Community Development and Empowerment), vol. 9, no. 1, pp. 83–86, Jan. 2025, doi: 10.29165/ajarcde.v9i1.525.
H. Bhaskar, K. Dwivedi, D. P. Dogra, M. Al-Mualla, and L. Mihaylova, “Autonomous detection and tracking under illumination changes, occlusions and moving camera,” Signal Processing, vol. 117, pp. 343–354, Dec. 2015, doi: 10.1016/j.sigpro.2015.06.003.
B. M. Kumar and T. K. Kunhamu, “Nature-based solutions in agriculture: A review of the coconut (Cocos nucifera L.)-based farming systems in Kerala, ‘the Land of Coconut Trees,’” Nature-Based Solutions, vol. 2, p. 100012, Dec. 2022, doi: 10.1016/j.nbsj.2022.100012.
J. A. Caladcad and E. J. Piedad, “Acoustic dataset of coconut (Cocos nucifera) based on tapping system,” Data in Brief, vol. 47, p. 108936, Apr. 2023, doi: 10.1016/j.dib.2023.108936.
S. Parvathi and S. Tamil Selvi, “Detection of maturity stages of coconuts in complex background using Faster R-CNN model,” Biosystems Engineering, vol. 202, pp. 119–132, Feb. 2021, doi: 10.1016/j.biosystemseng.2020.12.002.
A. Nair U. K., S. M. Varghese, and V. R. N. Sinija, “Non-Destructive Testing to Determine Quality and Maturity of Coconut and Coconut Products,” Preservation and Authentication of Coconut Products, pp. 161–179, 2024, doi: 10.1007/978-3-031-64653-9_8.
Y. Fu, Z. Wang, H. Zheng, X. Yin, W. Fu, and Y. Gu, “Integrated detection of coconut clusters and oriented leaves using improved YOLOv8n-obb for robotic harvesting,” Computers and Electronics in Agriculture, vol. 231, p. 109979, Apr. 2025, doi: 10.1016/j.compag.2025.109979.
R. K. Mandava, H. Mittal, and N. Hemalatha, “Identifying the maturity level of coconuts using deep learning algorithms,” Materials Today: Proceedings, vol. 103, pp. 410–414, 2024, doi: 10.1016/j.matpr.2023.09.071.
B. Igried, S. AlZu’bi, D. Aqel, A. Mughaid, I. Ghaith, and L. Abualigah, “An Intelligent and Precise Agriculture Model in Sustainable Cities Based on Visualized Symptoms,” Agriculture, vol. 13, no. 4, p. 889, Apr. 2023, doi: 10.3390/agriculture13040889.
L. Bu, C. Hu, and X. Zhang, “Recognition of food images based on transfer learning and ensemble learning,” PLOS ONE, vol. 19, no. 1, p. e0296789, Jan. 2024, doi: 10.1371/journal.pone.0296789.
Z. Huang et al., “Computer Vision-Based Biomass Estimation for Invasive Plants,” Journal of Visualized Experiments, no. 204, Feb. 2024, doi: 10.3791/66067.
A. K. Maitlo, R. A. Shaikh, and R. H. Arain, “A novel dataset of date fruit for inspection and classification,” Data in Brief, vol. 52, p. 110026, Feb. 2024, doi: 10.1016/j.dib.2023.110026.
Z. Al Sahili and M. Awad, “The power of transfer learning in agricultural applications: AgriNet,” Frontiers in Plant Science, vol. 13, Dec. 2022, doi: 10.3389/fpls.2022.992700.
H. Bichri, A. Chergui, and M. Hain, “Investigating the Impact of Train / Test Split Ratio on the Performance of Pre-Trained Models with Custom Datasets,” International Journal of Advanced Computer Science and Applications, vol. 15, no. 2, 2024, doi: 10.14569/ijacsa.2024.0150235.
S. Anwar, S. R. Soomro, S. K. Baloch, A. A. Patoli, and A. R. Kolachi, “Performance Analysis of Deep Transfer Learning Models for the Automated Detection of Cotton Plant Diseases,” Engineering, Technology & Applied Science Research, vol. 13, no. 5, pp. 11561–11567, Oct. 2023, doi: 10.48084/etasr.6187.
F. Sattar, “Predicting Maturity of Coconut Fruit from Acoustic Signal with Applications of Deep Learning,” The 2nd International Online Conference on Agriculture, p. 16, Mar. 2024, doi: 10.3390/iocag2023-16880.
CRediT Author Statement
The authors confirm contribution to the paper as follows:
Conceptualization: Pushpa T and Vadivel A;
Methodology: Pushpa T;
Software: Pushpa T and Vadivel A;
Data Curation: Vadivel A;
Writing- Original Draft Preparation: Pushpa T and Vadivel A;
Visualization: Vadivel A;
Investigation: Pushpa T and Vadivel A;
Supervision: Vadivel A;
Validation: Pushpa T;
Writing- Reviewing and Editing: Pushpa T and Vadivel A; All authors reviewed the results and approved the final version of the manuscript.
Acknowledgements
Author(s) thanks to Dr. Vadivel A for this research completion and support.
Funding
No funding was received to assist with the preparation of this manuscript.
Ethics declarations
Conflict of interest
The authors have no conflicts of interest to declare that are relevant to the content of this article.
Availability of data and materials
Data sharing is not applicable to this article as no new data were created or analysed in this study.
Author information
Contributions
All authors have equal contribution in the paper and all authors have read and agreed to the published version of the manuscript.
Corresponding author
Pushpa T
Department of Computer Science and Engineering, GITAM School of Technology, Bengaluru, Karnataka, India.
Open Access This article is licensed under a Creative Commons Attribution NoDerivs is a more restrictive license. It allows you to redistribute the material commercially or non-commercially but the user cannot make any changes whatsoever to the original, i.e. no derivatives of the original work. To view a copy of this license, visit https://creativecommons.org/licenses/by-nc-nd/4.0/
Cite this article
Pushpa T and Vadivel A, “Accurate Phase Wise Prediction of Coconut Harvesting Stages Using VGG19 Convolutional Neural Network for Improved Agricultural Automation”, Journal of Machine and Computing, vol.5, no.4, pp. 2160-2170, October 2025, doi: 10.53759/7669/jmc202505167.
