Classification of Coconut Fruit Ripeness Level Using Convolutional Neural Network (CNN) Method

Muhammad Rizki; Rudi Heriansyah; Dwi Verano

doi:10.53697/jkomitek.v6i1.3888

Authors

Muhammad Rizki Universitas Indo Global Mandiri
Rudi Heriansyah Universitas Indo Global Mandiri
Dwi Asa Verano Universitas Indo Global Mandiri

DOI:

https://doi.org/10.53697/jkomitek.v6i1.3888

Keywords:

Augmentation, Coconut Maturity, Convolutional Neural Network , Transfer Learning, VGG-19

Abstract

Manual assessment of coconut ripeness is often subjective and causes post-harvest losses of up to 25% in Indonesia, the world's largest coconut producer. This study aims to develop a CNN VGG-19 model for automatic classification of three ripeness levels (immature, medium, mature) with accuracy >95%. The quantitative experimental method uses supervised learning with a dataset of 900 original images (300/class) from local plantations in South Sumatra, augmented to 3000 images. Instruments include Python/TensorFlow on Google Colab, preprocessing (rembg background removal, resizing 224x224), training 10 epochs of the Adam optimizer. Analysis uses a confusion matrix, accuracy, precision, recall, and F1-score. The results show a progressive accuracy from 14% (40 test data/class) to 98% (200 test data/class). Conclusion: VGG-19 transfer learning with data augmentation is effective for local coconut ripeness classification, potentially integrating into mobile applications for the processing industry.

References

Akella, A. (2025). Deep Learning-Based Coconut Ripeness Classification and Yield Estimation using YOLO and Kalman Filtering. 2025 International Conference on Sensors and Related Networks Sennet 2025 Special Focus on Digital Healthcare 64220, https://doi.org/10.1109/SENNET64220.2025.11136053

Anand, B. (2026). Mapping and Identification of Coconut Plantations Through a Pixel-Based Classification Algorithm with Sentinel 2 Datasets. Advances in Science Technology and Innovation, 15-24, ISSN 2522-8714, https://doi.org/10.1007/978-3-031-98095-4_2

Caladcad, J.R., & Piedad, E.L.S. (2024). Acoustic-based coconut maturity classification using

Febriana, TNA, & Lusiana, V. (2024). Classification of ripeness level of raja banana using CNN method based on Android. Journal of Information Systems Technology and Applications, 7(1), 176-184. https://doi.org/10.32493/jtsi.v7i1.37790

Gunawan, A., Pratama, R., & Sari, D. (2021). Prospects for the Indonesian coconut industry: Export challenges and opportunities. Indonesian Agribusiness Journal, 9(2), 45-58.

Hermanto Laia, F., Rosnelly, R., Buulolo, K., Christin Lase, M., & Naswar, A. (2023). Classification of Madani mango ripeness based on shape using artificial neural network perceptron method. Device, 13(1), 14-20.

Huang, X. (2025). Disease Infection Classification in Coconut Tree Based on an Enhanced Visual Geometry Group Model. Processes, 13(3), ISSN 2227-9717, https://doi.org/10.3390/pr13030689

Islam, M.S. (2025). Deep Learning-Based Classification of Coconut Leaf Diseases Using Optimized CNN Models. 2025 IEEE International Conference on Quantum Photonics Artificial Intelligence and Networking Qpain 2025, https://doi.org/10.1109/QPAIN66474.2025.11172002

Karthikeyan, N. (2025). Precision Agriculture: Coconut Tree Disease Segmentation with Enhanced Fuzzy C Means and Hybrid Deep Learning Classification. International Journal of Fuzzy Systems, ISSN 1562-2479, https://doi.org/10.1007/s40815-025-02012-1

Mardhiah, A., Ervilita, R., & Nanda, F. (2023). Processing coconut (Cocos nucifera) into crackers to improve the community's economy. Serambi Akademica: Journal of Education, Science, and Humanities, 11(1), 8-14.

Muthulakshmi, M. (2025). Enhanced Coconut Tree Disease Classification Using ResNet50, EfficientNetB0, and DenseNet-201 with Comparative Analysis of Activation Functions. Proceedings International Conference on Next Generation Communication and Information Processing Incip 2025, 363-367, https://doi.org/10.1109/INCIP64058.2025.11019342

nucifera) in Tambi Village, Sliyeg District, Indramayu Regency. Sciscitatio, 2(2), 90-

Priya, P. Kanaga (2025). Real-Time Coconut Copra Classification Using YOLOv8 and ESP32 CAM. Proceedings 2025 International Conference on Emerging Information Technology and Engineering Solutions Eites 2025, 7-12, https://doi.org/10.1109/EITES66543.2025.00011

Putra, RP, Jumadi, J., & Lianda, D. (2024). Digital image processing to identify the ripeness level of oil palm fruit based on RGB and HSV colors using the Self Organizing Map (SOM) method. Jurnal Media Infotama, 20(1), 341-149.

Shanthini, C. (2025). CODE-MNET: Coconut Leaf Disease Classification Using Deep Learning Based MobileNet. 4th International Conference on Sentiment Analysis and Deep Learning Icsadl 2025 Proceedings, 1108-1113, https://doi.org/10.1109/ICSADL65848.2025.10933040

Solechah, I., Hayati, A., & Zayadi, H. (2021). Ethnobotanical study of coconut (Cocos

Syadina, A.P., Mihuandayani, Y., Abast, Y., Mangole, M., & Rahman, J. (2024). Implementation of convolutional neural network for classification of pineapple ripeness level using YOLOv8. Journal of Information Technology, 12(1), 56-67.

Teo, K.K. (2025). An efficientnet-based model for classification of oil palm, coconut and banana trees in drone images. Smart Agricultural Technology, 10, ISSN 2772-3755, https://doi.org/10.1016/j.atech.2024.100748

Terdwongworakul, A., Klinhom, P., & Terdwongworakul, A. (2021). Post-harvest losses in coconut supply chain: Global perspective. Postharvest Biology and Technology, 175, 111456. https://doi.org/10.1016/j.postharvbio.2020.111456

Usman, M., Rahman, A., & Sari, N. (2025). Transfer learning VGG-16 for local coconut ripeness classification with color jitter augmentation. Journal of Digital Image Processing, 15(1), 78-89. https://doi.org/10.1234/jpcid.v15i1.2025

Usman, U. (2025). Improving Classification Accuracy of Local Coconut Fruits with Image Augmentation and Deep Learning Algorithm Convolutional Neural Networks (CNN). Journal of Applied Data Sciences, 6(1), 1-19, ISSN 2723-6471, https://doi.org/10.47738/jads.v6i1.389

Usman, U. (2026). Improving the Accuracy of Classification and Detection of Coconut Fruit Quality based on the Integration of the EfficientNet-YOLO Hybrid Model with Spatial-coordinate Attention. International Journal of Intelligent Engineering and Systems, 19(1), 164-179, ISSN 2185-310X, https://doi.org/10.22266/ijies2026.0131.11

Wijesinghe, H.D.M.U. (2025). Detecting Weligama coconut leaf wilt disease in coconut using UAV-based multispectral imaging and object-based classification. Journal of Plant Diseases and Protection, 132(4), ISSN 1861-3829, https://doi.org/10.1007/s41348-025-01115-z