Paper Titles
A Dual-Scheme Cointegration Framework for Condition Monitoring and Fault Detection Using Non-Joint and Mixed-Order Time Series
p.269
Vibration-Based Condition Monitoring of Induction Motors in Industrial Applications of Uzbekistan
p.279
Multi-Class Anomaly Detection in an Industrial Robot Arm
p.287
Transforming CMM Inspection Reports into NVH-Relevant Feature Sets
p.293
Non-Destructive Watermelon Ripeness Assessment Using Deep Learning and Field-Based RGB Imagin
p.303
Comparative Study of Microstructural Characteristics of P355NH Transporting Pipelines Exposed to Hydrogen
p.317
Digital Twin Technology for Safety Enhancement of Hydrogen Refuelling Stations
p.329
Hydrogen Embrittlement in Austenitic Stainless Steels: A Review of Testing Methods and Standardization Challenges
p.339
The Municipal Environmental Protection Programme of the Municipality of Dunaújváros
p.355

Non-Destructive Watermelon Ripeness Assessment Using Deep Learning and Field-Based RGB Imagin

Article Preview

Abstract:

Accurate, non-destructive assessment of watermelon ripeness remains a significant challenge in horticultural production, particularly under field conditions where traditional visual and tactile evaluation methods are subjective and often inconsistent. Although mechanical, acoustic, and spectroscopic techniques have demonstrated promising performance, their reliance on controlled laboratory environments limits their practical applicability in real-world agricultural settings. This study presents a field-deployable, AI-assisted computer vision system designed for objective, real-time classification of watermelon ripeness. The proposed prototype combines controlled illumination with RGB imaging and convolutional neural networks trained on thousands of annotated outdoor images collected over multiple growing seasons. A phased development strategy—encompassing proof-of-concept modelling, field integration, and multi-season validation—supports robustness against variable lighting conditions and environmental influences. The anticipated outcome is a reliable, non-destructive decision-support tool for growers, capable of identifying ripe fruit for manual harvesting while providing a technological foundation for future autonomous harvesting and precision agriculture applications.

You might also be interested in these eBooks
International Scientific Conference on Advances in Mechanical Engineering (11th ISCAME) View Preview

Info:

Periodical:

Advances in Science and Technology (Volume 181)

Pages:

303-313

DOI:

https://doi.org/10.4028/p-0yVu2L

Citation:

Cite this paper

Online since:

August 2026

Authors:

István Domokos*, Péter Szilágyi

Keywords:

Artificial Intelligence, Computer Vision, Convolutional Neural Networks (CNNs), Deep Learning, Field-Based Imaging, Fruit Maturity Assessment, Non-Destructive Evaluation, Precision Agriculture, RGB Imaging, Watermelon Ripeness Detection

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

© 2026 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

* - Corresponding Author

References

[1] Abbaszadeh, R., Moosavian, A., Rajabipour, A., & Najafi, G. (2015). An intelligent procedure for watermelon ripeness detection based on vibration signals. Journal of Fo-od Science and Technology.

DOI: 10.1007/s13197-013-1068-x

Google Scholar

[2] Arboleda, E. R., Parazo, K. M., & Pareja, C. M. (2020). Watermelon ripeness detector using near infrared spectroscopy. Jurnal Teknologi dan Sistem Komputer.

DOI: 10.14710/jtsiskom.2020.13744

Google Scholar

[3] Choe, U., Kang, H., Ham, J., & Choe, U. (2022). Maturity assessment of watermelon by acoustic method. Scientia Horticulturae.

DOI: 10.1016/j.scienta.2021.110735

Google Scholar

[4] Diezma-Iglesias, B. et al. (2002). Acoustic impulse response for detecting defects in watermelons. Biosystems Engineering.

Google Scholar

[5] R. B. Paolo Gay, 2002, Innovative Techniques for Fruit Color Grading, Innovative Techniques for Fruit Color Grading, American Society of Agricultural and Biological Engineers.

DOI: 10.13031/2013.10549

Google Scholar

[6] Jumadi, N. A., & Mat Saat, A. F. (2020). Development of watermelon ripeness grading system based on colour histogram.

Google Scholar

[7] Nourain, J., Ying, Y., Wang, J., & Rao, X. (2006). Firmness evaluation of melon using its vibration characteristic and finite element analysis. International Journal of Postharvest Technology and Innovation.

DOI: 10.1504/IJPTI.2006.011663

Google Scholar

[8] Sugiyama, J., Otobe, K., Hayashi, S., & Usui, S. (1994). Firmness measurement of muskmelons by acoustic impulse transmission. Transactions of the ASAE.

DOI: 10.13031/2013.28201

Google Scholar

[9] Zeng, W., Huang, X., Müller Arisona, S., & McLoughlin, I. V. (2014). Classifying wa-termelon ripeness by analyzing acoustic signals using mobile devices. Personal and Ubiquitous Computing.

DOI: 10.1007/s00779-013-0706-7

Google Scholar

[10] Zhang, Y. et al. (2019). Watermelon ripeness detection via extreme learning machine with kernel principal component analysis. International Journal of Pattern Recognition and Artificial Intelligence.

DOI: 10.1142/S0218001419510029

Google Scholar

[11] Pálinkás, S., Juhász, G., & Szodrai, F. (2020). Development of analysis of loss sources of vehicles. International Journal of Engineering and Management Sciences, 5(1), 733–737.

DOI: 10.21791/IJEMS.2020.1.62

Google Scholar

[12] Nemes, D., Hajdu, S. (2025). Flexibly Parameterizable Vehicle Dynamics Models. De-signs.

DOI: 10.3390/designs9020046

Google Scholar

[13] Sun, T. et al. (2023). Object localization methodology in occluded agricultural environments through deep learning and active sensing. Computers and Electronics in Agriculture.

DOI: 10.1016/j.compag.2023.108141

Google Scholar

[14] Kamilaris, A., & Prenafeta-Boldú, F. X. (2018). Deep learning in agriculture: A survey. Computers and Electronics in Agriculture.

DOI: 10.1016/j.compag.2018.02.016

Google Scholar

[15] Sharma, A., Kumar, V., & Longchamps, L. (2024). Comparative performance of YOLOv8, YOLOv9, YOLOv10, YOLOv11 and Faster R-CNN models for detection of multiple weed species. Smart Agricultural Technology.

DOI: 10.1016/j.atech.2024.100648

Google Scholar

[16] Shin, H.-C., et al. (2016). Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Transactions on Medical Imaging.

DOI: 10.1109/TMI.2016.2528162

Google Scholar

[17] He, K., Girshick, R., & Dollár, P. (2018). Rethinking ImageNet pre-training. arXiv preprint.

Google Scholar

[18] Pálinkás, S. (2025). Analysis of loss factors in passenger car motion using artificial intelligence. Accepted paper, 650th EUROMECH Colloquium (Applied Mechanics through Artificial Intelligence Applications). To be published in Mechanisms and Machine Science (Springer).

Google Scholar

[19] Shi, H., Liu, J., Huang, Y., Li, J., 2024. Non-destructive judgment of watermelon ripeness based on multi-feature fusion of image. Proceedings of the 20th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD), Guangzhou, China, p.1–8.

DOI: 10.1109/ICNC-FSKD64080.2024.10702304

Google Scholar

[20] Zhang, Z., Xie, H., Zhang, K., Yang, L., Zhang, D., Cui, T., He, X., 2025. Multi-audio feature maps fusion for watermelon quality detection. Journal of Food Engineering 391, 112452.

DOI: 10.1016/j.jfoodeng.2024.112452

Google Scholar

[21] Zou, X., Zhang, J., Huang, X., Zheng, K., Wu, S., 2019. Distinguishing watermelon maturity based on acoustic characteristics and near infrared spectroscopy fusion technology. Transactions of the Chinese Society of Agricultural Engineering 35 (9).

Google Scholar