Journal Cover – Impact in Agriculture

Impact in Agriculture

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

Submit Your Manuscript
Article Open Access

A Comparative Benchmark of Deep Learning Architectures for Guava Disease Classification Using Fruit and Leaf Images

Amani Tahsin Yasin 1 ORCID , Sabat Abdhulhameed Ali 2 ORCID , Elham Tahsin Yasin 3 ORCID
1 Nutrition and Dietetics Department, Faculty of Applied Science, Tishk International University, Erbil 44001, Iraq
2 School of science and engineering, department of computer science and engineering, University of Kurdistan Hewler, Erbil 44001, Iraq
3 Graduate School of Natural and Applied Sciences, Department of Computer Engineering, Faculty of Technology, Selcuk University, Konya 42100, Türkiye
Journal Impact in Agriculture
Volume 2
Article Number 3
Pages 1–14
Received 23 February 2026
Revised 5 April 2026
Accepted 9 April 2026
Published 17 April 2026
DOI https://doi.org/10.65500/agriculture-2026-003
Views 566
Downloads 109
Download PDF DOI

Abstract

The diseases of the guava plant are harmful to both yield and fruit quality. Recognizing diseases in the early stages is crucial for orchard management. Comparing deep learning studies published is a challenging task, since they often involve different data sets, preprocessing steps, training procedures, and evaluation methodologies. This study benchmarks the current state of the art in the field of deep learning based on a curated public database (521 images) categorized into five classes related to the healthy and diseased states of the guava plant. Specifically, this study compares ResNet50, DenseNet121, EfficientNet B0, EfficientNetV2 S, ConvNeXt Tiny, MobileNetV3 Large, Swin Transformer Tiny, DeiT Tiny, MaxViT Tiny, and GhostNet algorithms using a curated database of 521 images. Each algorithm was trained using the same data split, pre-processing steps, hyperparameters, and evaluation protocol. Accuracy, balanced accuracy, Macro F1 score, and Matthews Correlation Coefficient (MCC) were calculated. Additionally, confusion matrices, receiver operating characteristics and precision-recall curves were generated, and the efficacy of each algorithm was evaluated using efficiency and statistical tests. ConvNeXt Tiny and ResNet50 produced the highest observed point estimates: accuracy 98.73%, balanced accuracy 98.89%, Macro F1 score 98.78%, MCC 98.43%, and one wrong prediction for the test data set. GhostNet, EfficientNet B0, DenseNet121, and MaxViT Tiny achieved a similar result with a Macro F1 score of 98.74%. MobileNetV3 Large and GhostNet were the fastest algorithms and required 4.75 and 4.76 ms per image for processing, respectively. Overall, ConvNeXt Tiny showed a favorable relationship between predictive performance and computational requirements under the adopted fixed-partition protocol.

Keywords

Guava disease recognition deep learning benchmark study computer vision precision agriculture plant disease classification vision transformers

Funding

This research received no external funding.

References

  1. Tousif, M.I.; Nazir, M.; Saleem, M.; Tauseef, S.; Shafiq, N.; Hassan, L.; Hussian, H.; Montesano, D.; Naviglio, D.; Zengin, G.; et al. Psidium Guajava L. An Incalculable but Underexplored Food Crop: Its Phytochemistry, Ethnopharmacology, and Industrial Applications. Molecules 2022, Vol. 27, Page 7016 2022, 27, 7016 https://doi.org/10.3390/MOLECULES27207016.
  2. Butt, E.; Altemimi, A.B.; Younas, A.; Butt, M.S.; Jalal, M.; Bhatty, M.; Abdi, G.; Aadil, R.M. Guava (Psidium Guajava): A Brief Overview of Its Therapeutic and Health Potential. Food Chemistry: X 2025, 31, 103027 https://doi.org/10.1016/J.FOCHX.2025.103027.
  3. Guava Production by Country 2026 Available online: https://worldpopulationreview.com/country-rankings/guava-production-by-country (accessed on 05 February 2026).
  4. Zakaria, L. Diversity of Colletotrichum Species Associated with Anthracnose Disease in Tropical Fruit Crops—A Review. Agriculture 2021, Vol. 11, Page 297 2021, 11, 297 https://doi.org/10.3390/AGRICULTURE11040297.
  5. Martinelli, F.; Scalenghe, R.; Davino, S.; Panno, S.; Scuderi, G.; Ruisi, P.; Villa, P.; Stroppiana, D.; Boschetti, M.; Goulart, L.R.; et al. Advanced Methods of Plant Disease Detection. A Review. Agronomy for Sustainable Development 2014 35:1 2014, 35, 1–25 https://doi.org/10.1007/S13593-014-0246-1.
  6. Kurniawan, M.B.; Utami, E. Guava Disease Detection and Classification: A Systematic Literature Review. Telematika 2025, 18, 45–61 https://doi.org/10.35671/TELEMATIKA.V18I1.2901.
  7. Singh, R.; Gupta, S.; Aluvala, S.; Riadhwsein, R.; Sharma, G. Proposed Convolutional Neural Network for the Detection of Guava Leaf Diseases. In Proceedings of the 2025 IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation, IATMSI 2025; 2025 https://doi.org/10.1109/IATMSI64286.2025.10985607.
  8. Rangkuti, A.H.; Samiaji, T.A.; Sebastian, J.; Yora, S.; Maulana, M. Guava Disease Detection Using Machine Learning: A Data-Driven Agriculture Solution. In Proceedings of the Proceedings - 2025 8th International Seminar on Research of Information Technology and Intelligent Systems, ISRITI 2025; 2025; pp. 78–83 https://doi.org/10.1109/ISRITI68345.2025.11393115.
  9. Raji, P.J.; Meghalingam, R.K. Automated Guava Fruits Disease Classification Using Deep Learning. In Proceedings of the 2025 IEEE International Conference on Electronics, Computing and Communication Technologies, CONECCT 2025; 2025 https://doi.org/10.1109/CONECCT65861.2025.11306537.
  10. Srinivas; Satheesh; Rama Santosh Naidu; Neelima Prediction of Guava Plant Diseases Using Deep Learning; 2021; Vol. 698; https://doi.org/10.1007/978-981-15-7961-5_135.
  11. Thrimavithana, S.T.; Manukalpa, C.S. FoliumX: An Integrated IoT-AI Framework for Real-Time Crop Disease Detection and Environmental Monitoring for Smallholder Farmers. In Proceedings of the Proceedings - IEEE International Research Conference on Smart Computing and Systems Engineering, SCSE 2026; 2026 https://doi.org/10.1109/SCSE70081.2026.11499762.
  12. Miah, M.A.; Roshni, S.R.; Anamika, F.T.; Kamal, K.M.S.; Reza, A.W. GuavaNet-XAI: A CNN-Based Framework for Accurate and Interpretable Diagnosis of Guava Diseases. In Proceedings of the 2025 28th International Conference on Computer and Information Technology, ICCIT 2025; 2025; pp. 5353–5358 https://doi.org/10.1109/ICCIT68739.2025.11491449.
  13. Pathmanaban; Gnanavel; Anandan, S.S. Guava Fruit (Psidium Guajava) Damage and Disease Detection Using Deep Convolutional Neural Networks and Thermal Imaging. Imaging Science Journal 2022, 70, 102–116 https://doi.org/10.1080/13682199.2022.2163536.
  14. Yasin, E.; Kursun, R.; Koklu, M. Deep Learning-Based Classification of Black Gram Plant Leaf Diseases: A Comparative Study. In Proceedings of the 11th International conference on advanced technologies (ICAT’23); Istanbul-Turkiye, 2023; pp. 59–69 https://doi.org/10.58190/icat.2023.9.
  15. Yasin, E.T.; Kursun, R.; Koklu, M. Machine Learning-Based Classification of Mulberry Leaf Diseases. In Proceedings of the Proceedings of International Conference on Intelligent Systems and New Applications; Liverpool, United Kingdom, April 28 2024; Vol. 2, pp. 58–63 https://doi.org/10.58190/ICISNA.2024.91.
  16. Hamid, Y.; Wani, S.; Soomro, A.B.; Alwan, A.A.; Gulzar, Y. Smart Seed Classification System Based on MobileNetV2 Architecture. In Proceedings of the 2022 2nd International Conference on Computing and Information Technology (ICCIT); IEEE, 2022; pp. 217–222.
  17. 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, 1–11 https://doi.org/10.65500/agriculture-2025-003.
  18. Mehdipour, S.; Mirroshandel, S.A.; Tabatabaei, S.A. Vision Transformers in Precision Agriculture: A Comprehensive Survey. Intelligent Systems with Applications 2026, 29, 200617 https://doi.org/10.1016/J.ISWA.2025.200617.
  19. Majdalawieh, M.; Martins, C.; Radi, M.; Alaraj, M.; Khan, S. Precision Agriculture in the Age of AI: A Systematic Review of Machine Learning Methods for Crop Disease Detection. Smart Agricultural Technology 2025, 12, 101491 https://doi.org/10.1016/J.ATECH.2025.101491.
  20. Kanani, I.J.; Kaur, M.; Sridhar, R.; Dhenia, R.N.K.; Kumar, J.; Sharma, G.; Banerjee, D. Towards Sustainable Agriculture: Deep Learning for Natural Guava Disease Detection. In Proceedings of the IETACS 2025 - 2025 International Conference on Innovations and Emerging Technologies in AI and Communication Systems: Unifying AI and Communication for a Smarter Tomorrow; 2025; pp. 341–346 https://doi.org/10.1109/IETACS68750.2025.11385380.
  21. Tewari, V.; Azeem, N.A.; Sharma, S. Automatic Guava Disease Detection Using Different Deep Learning Approaches. Multimedia Tools and Applications 2024, 83, 9973–9996 https://doi.org/10.1007/s11042-023-15909-6.
  22. Ibrahim, N.J.; Khorsheed, F.H.; Mohammed, Z.H.; Latfa, A.M.; Khudhair, W.B.; Hassan, Z.F.; Alkattan, H. Hybrid CNN-ViT Framework for Guava Leaves and Fruits Disease Detection in Precision Agriculture. In Proceedings of the Proceedings of International Conference on Applied Innovation in IT; 2026; Vol. 14, pp. 49–58.
  23. Shrivastava, A.; Habelalmateen, M.I.; Kaur, A.; Praveen; Badhoutiya, A.; Kumar, A. Green Diagnosis: Deep Learning-Based Guava Leaf Disease Classification. In Proceedings of the 2025 IEEE Madhya Pradesh Section Conference, MPCON 2025; 2025; pp. 267–273 https://doi.org/10.1109/MPCON66082.2025.11256545.
  24. Kaur, A.; Kukreja, V.; Upadhyay, D.; Aeri, M.; Sharma, R. Multi-Class Guava Disease Classification Using an Efficient and Fine-Tuned DenseNet Model. In Proceedings of the 2024 IEEE 9th International Conference for Convergence in Technology, I2CT 2024; 2024 https://doi.org/10.1109/I2CT61223.2024.10544267.
  25. Cheekati, H.; Verma, P.; Vaithiyanathan, D. Guava (Psidium Guajava) Disease Detection Using CNN. In Proceedings of the 2025 2nd International Conference on Pioneering Developments in Computer Science and Digital Technologies, IC2SDT 2025 - Proceedings; 2025; pp. 1–6 https://doi.org/10.1109/IC2SDT68218.2025.11383705.
  26. Vijh, S.; Shieh, C.-S.; Jain, V.; Horng, M.-F. Optimized Deep Learning Framework for Plant Disease Detection Using Fine-Tuned Vision Transformers and CNN Model. SN Computer Science 2026, 7 https://doi.org/10.1007/s42979-026-05044-y.
  27. Rajbongshi, A.; Sazzad, S.; Shakil, R.; Akter, B.; Sara, U. Guava Leaves and Fruits Dataset for Guava Disease Recognition through Machine Learning and Deep Learning. 2022, 1 https://doi.org/10.17632/X84P2G3K6Z.1.

Copyright: © 2026 by the authors. Licensee: Impaxon Sdn. Bhd., Malaysia. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY 4.0) License .

Disclaimer: All views, interpretations, and data presented in Impaxon publications are the sole responsibility of the respective authors. These do not necessarily reflect the opinions of Impaxon or its editorial team.

Publisher’s Note: Impaxon remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

✓ Email copied