Classification of Avocado Ripeness Levels Using Transfer Learning Based on VGG16 and VGG19
DOI:
https://doi.org/10.46984/9vmst020Keywords:
Avocado Ripeness, Deep Learning, Transfer Learning, CNN, VGGAbstract
The determination of avocado ripeness is still commonly performed manually, which is subjective and often inaccurate due to its reliance on human visual perception. Traditional methods, such as pressing the fruit surface, may damage avocado quality and are inefficient for large-scale distribution and marketing. This study aims to automatically classify avocado ripeness levels using a deep learning approach based on transfer learning. The proposed method employs transfer learning using Convolutional Neural Network architectures, namely VGG16 and VGG19, which have been pre-trained on the ImageNet dataset. The research stages include image pre-processing such as resizing, normalization, and data augmentation to enhance input quality. Subsequently, model training and testing are conducted by comparing the performance of both architectures using evaluation metrics. The dataset used in this study is obtained from the Kaggle platform and consists of avocado images with various ripeness levels. Experimental results indicate that both models are capable of classifying avocado ripeness with high accuracy, precision, recall, and F1-score, with the VGG19 model achieving the best performance. These findings demonstrate that the deep learning approach effectively addresses the subjectivity and inaccuracy associated with manual avocado ripeness determination. This study contributes to the development of an accurate, objective, and practical image-based avocado ripeness classification system with potential applications in agriculture and fruit distribution
References
Abbas, A., Qureshi, W. S., Khan, M. A., & Sharif, M. (2023). Deep learning-based fruit maturity classification using convolutional neural networks. Computers and Electronics in Agriculture, 205, 107589. https://doi.org/10.1016/j.compag.2023.107589
Alzubaidi, L., Fadhel, M. A., Al-Shamma, O., Zhang, J., & Duan, Y. (2023). A review of transfer learning in medical and agricultural image classification. Artificial Intelligence Review, 56(4), 3401–3443. https://doi.org/10.1007/s10462-022-10268-1
Chen, Y., Li, X., Wang, Z., & Zhang, H. (2024). Fruit ripeness detection using deep convolutional neural networks and transfer learning. Expert Systems with Applications, 236, 121180. https://doi.org/10.1016/j.eswa.2023.121180
Elmasry, G., Cubero, S., & Blasco, J. (2023). Machine vision systems for fruit quality and maturity assessment: Recent advances. Postharvest Biology and Technology, 199, 112291. https://doi.org/10.1016/j.postharvbio.2023.1122 91
García, R., Torres, F., & Ruiz, L. (2024). Deep learning-based classification of fruit maturity using RGB images. Sensors, 24(3), 945. https://doi.org/10.3390/s24030945
Hossain, M. S., Rahman, M. M., & Islam, M. R. (2023). Transfer learning approaches for agricultural image analysis: A comparative study. IEEE Access, 11, 84532 - 84545. https://doi.org/10.1109/ACCESS.2023.3291145
Koirala, A., Walsh, K. B., Wang, Z., & McCarthy, C. (2023). Deep learning for real-time fruit detection and maturity classification. Biosystems Engineering, 224, 45–59. https://doi.org/10.1016/j.biosystemseng.2023.01 .005
Liu, S., Wang, Y., Chen, J., & Xu, D. (2024). Comparative performance of VGG16 and VGG19 for image classification tasks in agriculture. Computers and Electronics in Agriculture, 213, 108195.
https://doi.org/10.1016/j.compag.2024.108195
Nisar, H., Khan, M. A., Sharif, M., & Saba, T. (2023). Transfer learning-based deep CNN models for fruit quality classification. Multimedia Tools and Applications, 82(12), 18641–18658. https://doi.org/10.1007/s11042-022-14255-6
Pratama, A. R., Wijaya, A., & Santoso, B. (2024). Penerapan deep learning untuk klasifikasi kematangan buah berbasis citra digital. Jurnal Teknologi Informasi dan Ilmu Komputer, 11(2), 215–224.
Putra, D. P., Kurniawan, A., & Saputra, R. (2024). Analisis metode non-destruktif dalam penentuan kematangan buah alpukat. Jurnal Ilmu Pertanian Indonesia, 29(1), 55–63.
Rahman, M. M., Hossain, M. A., & Hasan, M. K. (2025). Performance evaluation of deep CNN architectures for fruit ripeness classification. Applied Artificial Intelligence, 39(1), 1–18. https://doi.org/10.1080/08839514.2024.230112 4
Santos, T. T., Silva, D. F., & Gomes, F. S. (2023). Automated fruit maturity assessment using computer vision and deep learning. Journal of Food Engineering, 343, 111090. https://doi.org/10.1016/j.jfoodeng.2023.111090
Singh, R., Kumar, A., & Verma, P. (2025). Deep transfer learning for fruit ripeness detection under varying lighting conditions. Neural Computing and Applications, 37(2), 1453–1466. https://doi.org/10.1007/s00521-024-09321-7
Wang, X., Zhang, L., & He, Y. (2023). Maturity detection of avocado fruit using deep convolutional neural networks. Postharvest Biology and Technology, 201, 112340.
https://doi.org/10.1016/j.postharvbio.2023.1123 4
Wijaya, R., Nugroho, A., & Prasetyo, E. (2023). Klasifikasi tingkat kematangan buah menggunakan CNN berbasis citra RGB. Jurnal RESTI, 7(6), 1203–1210.
Zhang, Y., Liu, J., & Zhao, H. (2024). Feature extraction performance analysis of VGG-based CNN architectures. Pattern Recognition Letters, 177, 60–67.
https://doi.org/10.1016/j.patrec.2023.12.012 Zhou, Y., Chen, K., & Li, P. (2023). Deep learning approaches for food quality inspection: A review. Trends in Food Science & Technology, 137, 1–15.
https://doi.org/10.1016/j.tifs.2023.04.003
Kurniawan, F., Siregar, D., & Hartono, R. (2024). Evaluasi performa CNN pada klasifikasi kualitas buah tropis. Jurnal Informatika, 18(3), 301–310. Singh, S., Patel, N., & Desai, V. (2024). Image-based fruit quality assessment using VGG-based transfer learning. International Journal of Intelligent Systems, 39(6), 10987–11002. https://doi.org/10.1002/int.23045.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Ibnu Luthfi, Yuhandri Yuhandri, Gunadi Widi Nurcahyo
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors retain all their rights to the published works, such as (but not limited to) the following rights; Copyright and other proprietary rights relating to the article, such as patent rights, The right to use the substance of the article in own future works, including lectures and books, The right to reproduce the article for own purposes, The right to self-archive the article
