Journal Cover – Impact in Agriculture

Impact in Agriculture

Peer-Reviewed • Open Access e-ISSN: 3122-735X

Submit Your Manuscript

Mitigating Spatial Scale Loss in CNN-Based Fine-Grained Image Classification: Application to Date Fruit Grading

Ziaul Haque 1 ORCID , Murat Koklu 2 ORCID , Mohammed Aquil Mirza 3 , Marwan Omar 4 ORCID , Saidova Mukhayyokhon 5
1 Department of Plant Protection, Faculty of Agricultural Sciences, Aligarh Muslim University, Aligarh 202002, India
2 Technology Faculty, Department of Computer Engineering, Selcuk University, Konya 42031, Türkiye
3 Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Kowloon PQ806, Hong Kong
4 ITM Department, Illinois Institute of Technology, Chicago, IL60616, USA
5 Ground transport systems, Tashkent State Technical University, Tashkent 100095, Uzbekistan
DOI: https://doi.org/10.65500/agriculture-2025-005
Received: 17 November 2025 | Revised: 2 December 2025 | Accepted: 13 December 2025 | Published: 30 December 2025
315 views | 47 downloads

Abstract

Accurate classification of date fruit varieties and size grades is critical for automated grading and post-harvest quality assessment. However, conventional image preprocessing techniques based on uniform resizing often distort size-dependent visual cues, leading to misclassification among size levels within the same variety. To address this limitation, this study proposes a size-preserving rescaling strategy for deep learning–based date fruit classification. Experiments are conducted on a curated dataset comprising 5,836 images distributed across 12 classes, representing four date varieties (Aseel, Dandhi, Karblain, and Kupro), each categorized into three size levels: large, medium, and small. Five convolutional neural network architectures—MobileNetV3, DenseNet121, InceptionV3, ResNet101, and VGG16—are evaluated using identical training, validation, and test splits under a supervised learning framework. When standard resized inputs are used, the highest classification accuracy achieved is 82.18%, with macro F1-scores close to 0.82. In contrast, incorporating the proposed size-preserving rescaling approach leads to substantial performance improvements across all models. The best results are obtained with ResNet101, achieving an accuracy of 94.44%, a macro precision of 0.9476, and a macro F1-score of 0.9446, followed closely by DenseNet121 with 94.32% accuracy. These findings demonstrate that preserving size information during preprocessing significantly enhances class separability and reduces size-level confusion, making the proposed approach well suited for practical date fruit grading systems.

Keywords: date fruit; size-preserving rescaling; deep learning; image classification; automated fruit grading

Download PDF

References

  1. Date Production by Country 2025 Available online: https://worldpopulationreview.com/country-rankings/date-production-by-country (accessed on 14 December 2025).
  2. Koklu, M.; Kursun, R.; Taspinar, Y.S.; Cinar, I. Classification of Date Fruits into Genetic Varieties Using Image Analysis. Math Probl Eng 2021, 2021, doi:10.1155/2021/4793293.
  3. Nath, B.; Gulzar, Y.; Tamang, S.; Alkanan, M. Comparative Evaluation of Deep Learning Architectures for Brinjal Fruit Disease Classification. Emir J Food Agric 2025, 37, 1–14, doi:10.3897/EJFA.2025.172982.
  4. Gulzar, Y.; Ünal, Z.; Kadir¸ Şahbaz; Alkanan, M. PTL-Inception: Integrating Deep Learning and Taxonomy for Desert Plant Classification. Diversity 2025, Vol. 17, Page 806 2025, 17, 806, doi:10.3390/D17110806.
  5. Gulzar, Y. Applications of Transfer Learning in Sunflower Disease Detection: Advances, Challenges, and Future Directions. Turkish Journal of Biology 2025, 49, 534–549, doi:10.55730/1300-0152.2763.
  6. Nasiri, A.; Taheri-Garavand, A.; Zhang, Y. Image-Based Deep Learning Automated Sorting of Date Fruit. Postharvest Biol Technol 2019, 153, 133–141, doi:10.1016/j.postharvbio.2019.04.003.
  7. Albarrak, K.M.; Gulzar, Y.; Hamid, Y.; Mehmood, A.; Soomro, A.B. A Deep Learning-Based Model for Date Fruit Classification. Sustainability (Switzerland) 2022, 14, doi:10.3390/su14106339.
  8. Altaheri, H.; Alsulaiman, M.M.; Muhammad, G. Date Fruit Classification for Robotic Harvesting in a Natural Environment Using Deep Learning. IEEE Access 2019, 7, 117115–117133, doi:10.1109/ACCESS.2019.2936536.
  9. Faisal, M.; Albogamy, F.R.H.; ElGibreen, H.A.; Algabri, M.; Al-Qershi, F. Deep Learning and Computer Vision for Estimating Date Fruits Type, Maturity Level, and Weight. IEEE Access 2020, 8, 206770–206782, doi:10.1109/ACCESS.2020.3037948.
  10. Faisal, M.; Alsulaiman, M.M.; Arafah, M.A.; Mekhtiche, M.A. IHDS: Intelligent Harvesting Decision System for Date Fruit Based on Maturity Stage Using Deep Learning and Computer Vision. IEEE Access 2020, 8, 167985–167997, doi:10.1109/ACCESS.2020.3023894.
  11. Pérez-Pérez, D.B.; Salomón-Torres, R.; García-Vázquez, J.P. Dataset for Localization and Classification of Medjool Dates in Digital Images. Data Brief 2021, 36, doi:10.1016/j.dib.2021.107116.
  12. Maitlo, A.K.; Shaikh, R.A.; Arain, R.H. A Novel Dataset of Date Fruit for Inspection and Classification. Data Brief 2024, 52, doi:10.1016/j.dib.2023.110026.
  13. Maitlo, A.K.; Shaikh, R.A.; Arain, R.H.; Mujtaba, G. CNN-Based Intelligent System for Date Fruit Classification Using Novel Dataset. VFAST Transactions on Software Engineering 2024, 12, 134–144, doi:10.21015/vtse.v12i4.1987.
  14. Aiadi, O.; Khaldi, B.; Kherfi, M.L.; Mekhalfi, M.L.; Alharbi, A.R. Date Fruit Sorting Based on Deep Learning and Discriminant Correlation Analysis. IEEE Access 2022, 10, 79655–79668, doi:10.1109/ACCESS.2022.3194550.
  15. Alresheedi, K.M.; Aladhadh, S.; Khan, R.U.; Qamar, A.M. Dates Fruit Recognition: From Classical Fusion to Deep Learning. Computer Systems Science and Engineering 2022, 40, 151–166, doi:10.32604/CSSE.2022.017931.
  16. Hassan, E.; Abu-Ghazalah, S.; El-Rashidy, N.M.; Abd El-Hafeez, T.; Shams, M.Y. DenseNet Model with Attention Mechanisms for Robust Date Fruit Image Classification. International Journal of Computational Intelligence Systems 2025, 18, doi:10.1007/s44196-025-00809-4.
  17. Eser, M.; Bilgin, M.; Yasin, E.T.; Koklu, M. Using Pretrained Models in Ensemble Learning for Date Fruits Multiclass Classification. J Food Sci 2025, 90, doi:10.1111/1750-3841.70136.
  18. Hassan, E.; Abu-Ghazalah, S.; El-Rashidy, N.M.; Abd El-Hafeez, T.; Shams, M.Y. Sustainable Deep Vision Systems for Date Fruit Quality Assessment Using Attention-Enhanced Deep Learning Models. Front Plant Sci 2025, 16, doi:10.3389/fpls.2025.1521508.
  19. Ufuah, D.; Thomas, G.M.; Balocco, S.; Manickavasagan, A. A DATA AUGMENTATION APPROACH BASED ON GENERATIVE ADVERSARIAL NETWORKS FOR DATE FRUIT CLASSIFICATION. Appl Eng Agric 2022, 38, 975–982, doi:10.13031/aea.15107.
  20. Ibrahim, D.M.; Elshennawy, N.M. Improving Date Fruit Classification Using CycleGAN-Generated Dataset. CMES - Computer Modeling in Engineering and Sciences 2022, 130, doi:10.32604/cmes.2022.016419.
  21. Almutairi, A.; Alharbi, J.; Alharbi, S.; Alhasson, H.F.; Alharbi, S.S.; Habib, S. Date Fruit Detection and Classification Based on Its Variety Using Deep Learning Technology. IEEE Access 2024, 12, 190666–190677, doi:10.1109/ACCESS.2024.3433485.
  22. Lipiński, S.; Sadkowski, S.; Chwietczuk, P. Application of AI in Date Fruit Detection—Performance Analysis of YOLO and Faster R-CNN Models. Computation 2025, 13, doi:10.3390/computation13060149.
  23. Yousaf, J.; Abuowda, Z.; Ramadan, S.; Salam, N.; Almajali, E.R.F.; Hassan, T.; Gad, A.; Alkhedher, M.A.; Ghazal, M.A. Autonomous Smart Palm Tree Harvesting with Deep Learning-Enabled Date Fruit Type and Maturity Stage Classification. Eng Appl Artif Intell 2025, 139, doi:10.1016/j.engappai.2024.109506.
  24. Noutfia, Y.; Ropelewska, E. What Can Artificial Intelligence Approaches Bring to an Improved and Efficient Harvesting and Postharvest Handling of Date Fruit (Phoenix Dactylifera L.)? A Review. Postharvest Biol Technol 2024, 213, doi:10.1016/j.postharvbio.2024.112926.
  25. Zangana, H.M.; Li, S.; Wani, S. Diffusion Models for Agricultural Imaging: A Systematic Review of Methods, Applications and Future Prospects. Impact in Agriculture 2025, 1, 3, doi:10.65500/agriculture-2025-003.
  26. Acevedo-Sanchez, G.; Alarcón-Paredes, A.; Yáñez-Márquez, C. Effect of Agriculture-Related Dataset Complexity on Classical Machine Learning and Deep Learning Classifiers Performance. Comput Electron Agric 2025, 239, doi:10.1016/j.compag.2025.110941.
  27. Ayoub, S.; Baig, I.; Ashraf, M.; Okasha, M. Impact of Dataset Quality on Deep Learning Models for Dragon Fruit and Leaf Health Classification. Impact in Agriculture 2025, 1, 1, doi:10.65500/agriculture-2025-001.
  28. Shaikh, R.A.; Mujtaba, G.; Maitlo, A.K.; Ali, D.; Shaikh, H. Size-Based Date Fruit Dataset for Classification. 2025, 1, doi:10.17632/D986HYR2KB.1.
  29. Eser, M.; Bilgin, M.; Yasin, E.T.; Koklu, M. Using Pretrained Models in Ensemble Learning for Date Fruits Multiclass Classification. J Food Sci 2025, 90, e70136, doi:10.1111/1750-3841.70136;WGROUP:STRING:PUBLICATION.
  30. Gulzar, Y. PapNet: An AI-Driven Approach for Early Detection and Classification of Papaya Leaf Diseases. Applied Fruit Science 2025 67:4 2025, 67, 1–11, doi:10.1007/S10341-025-01466-9.
  31. Gulzar, Y. Papaya Leaf Disease Classification Using Pre-Trained Deep Learning Models: A Comparative Study. Applied Fruit Science 2025, 67, 1–10, doi:10.1007/S10341-025-01533-1/METRICS.
  32. Gulzar, Y.; Ünal, Z. Time-Sensitive Bruise Detection in Plums Using PlmNet with Transfer Learning. Procedia Comput Sci 2025, 257, 127–132, doi:10.1016/J.PROCS.2025.03.019.
© 2026 by the authors. Published by Impaxon Publishing.
This article is licensed under the Creative Commons Attribution (CC BY) License .
You are free to share and adapt the material as long as appropriate credit is given.
Publisher’s Note: All claims expressed in this article are solely those of the authors and do not necessarily represent those of Impaxon Publishing or the journal editors. The publisher remains neutral with regard to jurisdictional claims in institutional affiliations.