Article Sidebar

Download
PDF
Statistic
Read Counter : 0 Download : 0

Main Article Content

Abstract

Accurate mango leaf disease recognition is important for automated crop-health assessment, but reliable evaluation requires transparent data partitioning, appropriate baseline comparison, and cautious interpretation of severity and explainability outputs. This study presents XLeaf-Net, an explainable deep-learning framework for mango leaf condition classification, image-derived severity assessment, and Grad-CAM-based visual interpretation. Experiments were conducted on the balanced MangoLeafBD dataset using an image-level stratified train-validation-test protocol with file-level integrity and capture/session-group overlap checks. XLeaf-Net was trained from scratch and compared with from-scratch VGG16, ResNet50, and EfficientNetB0 models under the implemented model-specific training configurations. An auxiliary severity model used conservative, image-derived symptom-intensity proxy labels, while Grad-CAM was applied to qualitatively examine class-discriminative regions. XLeaf-Net achieved 98.67% image-level test accuracy and a 98.66% macro F1-score, outperforming the evaluated from-scratch baselines while using 2.52 million parameters. The severity model achieved 78.17% accuracy and an 80.89% macro F1-score. Grad-CAM visualizations frequently overlapped with visually symptomatic leaf regions in representative correctly classified images. These findings demonstrate strong image-level performance within the implemented protocol; however, severity labels were not expert-annotated, and the evaluation was not session-independent. XLeaf-Net should therefore be considered a compact candidate framework requiring further independent validation.

Keywords

XLeaf-Net Mango leaf disease Deep learning Severity assessment Grad-CAM Explainable artificial intelligence

Article Details

How to Cite
Satao, S. A. ., & Maurya, S. R. . (2026). XLeaf-Net: an explainable deep learning framework for mango leaf disease classification and severity assessment using Grad-CAM-based visual interpretation . Future Technology, 5(4), 246–256. Retrieved from https://fupubco.com/futech/article/view/1156
Download Citation
Endnote/Zotero/Mendeley (RIS)
BibTeX
Bookmark and Share

References

  1. M. A. Rahman, M. T. A. Bhuiyan, F. M. Noori, M. Z. Uddin, and A. K. M. Masum, “MangoLeafNet-XAI: An attention-enhanced deep learning architecture for accurate and interpretable mango leaf disease classification,” Frontiers in Plant Science, vol. 17, Art. no. 1776537, 2026.
  2. D. Faye, I. Diop, and D. Dione, “Mango diseases classification solutions using machine learning or deep learning: A review,” Journal of Computer and Communications, vol. 10, pp. 16–28, 2022, doi: 10.4236/jcc.2022.1012002.
  3. M. Prabu and B. J. Chelliah, “Mango leaf disease identification and classification using a CNN architecture optimized by crossover-based levy flight distribution algorithm,” Neural Computing and Applications, vol. 34, no. 9, pp. 7311–7324, 2022.
  4. S. Jayaweera, P. Sewwandi, P. Tharaka, D. Pallewatta, T. Halloluwa, M. Wickramasinghe, et al., “MangoDB-A TJC mango dataset for deep-learning-based on classification and detection in precision agriculture,” in Proc. 2024 4th Int. Conf. Advanced Research in Computing (ICARC), 2024, pp. 115–120.
  5. D. Banerjee, V. Kukreja, S. Hariharan, and V. Jain, “Enhancing mango fruit disease severity assessment with CNN and SVM-based classification,” in Proc. 2023 IEEE 8th Int. Conf. Convergence in Technology (I2CT), 2023, pp. 1–6.
  6. D. Baresary, A. Saini, R. K. Sharma, D. Bordoloi, R. Sharma, and V. Kukreja, “MangoSpot: A hybrid CNN-SVM model for multi-classification of mango leaf spot disease based on seriousness levels,” in Proc. 2023 3rd Int. Conf. Intelligent Technologies (CONIT), 2023, pp. 1–5.
  7. B. U. Mahmud, A. Al Mamun, M. J. Hossen, G. Y. Hong, and B. Jahan, “Light-weight deep learning model for accelerating the classification of mango-leaf disease,” Emerging Science Journal, vol. 8, no. 1, pp. 28–42, 2024.
  8. M. Mohsin, M. S. A. Hashmi, I. D. Noya, H. Garay, N. Abdel Samee, and I. Ashraf, “Dual-modality fusion for mango disease classification using dynamic attention based ensemble of leaf and fruit images,” Scientific Reports, vol. 15, no. 1, Art. no. 42084, 2025.
  9. V. K. Pratap and N. S. Kumar, “Deep learning based mango leaf disease detection for classifying and evaluating mango leaf diseases,” Fusion: Practice & Applications, vol. 15, no. 2, 2024.
  10. E. Ergün, “Attention-enhanced hybrid deep learning model for robust mango leaf disease classification via ConvNeXt and vision transformer fusion,” Frontiers in Plant Science, vol. 16, Art. no. 1638520, 2025.
  11. G. Kaur, N. Sharma, S. Malhotra, S. Devliyal, and R. Gupta, “Mango leaf disease detection using VGG16 convolutional neural network model,” in Proc. 2024 3rd Int. Conf. Innovation in Technology (INOCON), 2024, pp. 1–6.
  12. C. P. Vijay, K. Pushpalatha, D. R. Janardhana, H. R. Kumar, and K. Puttegowda, “DeepLeafNet: A novel deep learning approach for mango leaf disease segmentation and classification with optimization algorithms,” SN Computer Science, vol. 6, no. 8, Art. no. 951, 2025.
  13. P. D. Rinanda, D. N. Aini, T. A. Pertiwi, S. Suryani, and A. J. Prakash, “Implementation of convolutional neural network (CNN) for image classification of leaf disease in mango plants using deep learning approach,” Public Research Journal of Engineering, Data Technology and Computer Science, vol. 1, no. 2, pp. 56–61, 2024.
  14. C. Chandrashekar, K. Vijayakumar, K. Pradeep, and A. Balasundaram, “MDCN: Modified dense convolution network based disease classification in mango leaves,” Computers, Materials, & Continua, vol. 78, no. 2, p. 2511, 2024.
  15. A. Kaur, V. Kukreja, D. S. Rana, A. Garg, and R. Sharma, “Deep insights into mango scab: An AI-powered approach for detection and classification,” in Proc. 2024 Fourth Int. Conf. Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT), 2024, pp. 1–5.
  16. S. Rahayu and S. F. Romdoni, “Bayesian optimized pretrained CNNs for mango leaf disease classification: A comparative study,” Jurnal Teknik Informatika (Jutif), vol. 6, no. 5, pp. 3051–3078, 2025.
  17. S. B. Porna, M. F. Kabir, M. I. C. Rana, M. S. I. Sajol, T. Roy, M. A. U. Khan, et al., “Hybrid convolutional neural networks for enhanced detection of mango leaf diseases,” in Proc. 2024 IEEE 6th Int. Conf. Cybernetics, Cognition and Machine Learning Applications (ICCCMLA), 2024, pp. 547–552.
  18. N. N. Komah and D. Hermanto, “Classification of mango varieties from leaf images using ResNet-50 CNN architecture,” Brilliance: Research of Artificial Intelligence, vol. 5, no. 1, pp. 559–567, 2025.
  19. S. Dinkar, K. Jayapriya, N. Pallerla, K. D. Jadhav, and A. R. Shet, “Convolutional neural networks for the intelligent and automated detection of mango leaf disease to enhance crop health management,” Agricultural Science Digest, vol. 45, no. 6, 2025.
  20. S. Thaseentaj and S. Ilango, “Deep convolutional neural networks for South Indian mango leaf disease detection and classification,” Computers, Materials, & Continua, vol. 77, no. 3, p. 3593, 2023.
  21. R. Varun, C. S. Chaithra, and S. Siddesha, “DeepMango: Understanding and analysis of deep models in mango leaf disease detection,” in Proc. Int. Conf. Microelectronics, Electromagnetics and Telecommunication, Singapore: Springer Nature Singapore, 2024, pp. 285–295.
  22. S. T. Y. Ramadan, T. Sakib, M. A. Rahat, S. Mosharrof, F. I. Rakin, and R. Jahangir, “Enhancing mango leaf disease classification: ViT, BiT, and CNN-based models evaluated on CycleGAN-augmented data,” in Proc. 2023 26th Int. Conf. Computer and Information Technology (ICCIT), 2023, pp. 1–6.
  23. S. D. Dip, S. Mahapatra, M. J. Naeen, M. U. Mojumdar, R. Sharma, and S. K. Banshal, “Automated disease identification in mango leaves using image analysis,” in Proc. 2025 12th Int. Conf. Computing for Sustainable Global Development (INDIACom), 2025, pp. 1–7.
  24. S. I. Ahmed, M. Ibrahim, M. Nadim, M. M. Rahman, M. M. Shejunti, T. Jabid, and M. S. Ali, “MangoLeafBD: A comprehensive image dataset to classify diseased and healthy mango leaves,” Data in Brief, vol. 47, Art. no. 108941, 2023, doi: 10.1016/j.dib.2023.108941.
  25. S. Ali, M. Ibrahim, S. I. Ahmed, M. Nadim, M. M. Rahman, M. M. Shejunti, and T. Jabid, “MangoLeafBD Dataset,” Mendeley Data, Version 1, 2022, doi: 10.17632/hxsnvwty3r.1.
  26. R. Garg, A. K. Sandhu, B. Kaur, B. Goyal, and A. Dogra, “Design of filtration approach for image quality improvement in mango leaf disease detection and pharmaceutical treatment,” Biomedical and Pharmacology Journal, vol. 17, no. 1, pp. 341–358, 2024.
  27. S. Patil, B. Bisen, S. K. Pandey, R. Bisen, and B. Krishna, “Assessment of variability in stem girth, leaf area, leaf thickness, chlorophyll content, and their correlation in mango hybrids,” International Journal of Plant and Environment, vol. 11, no. 3, pp. 547–556, 2025.
  28. M. A. Al Rahib, N. Sultana, N. Saha, R. Mia, M. Sarker, and A. Sattar, “Image analysis and machine learning techniques for accurate detection of common mango diseases in warm climates,” International Journal of Artificial Intelligence, vol. 14, no. 4, pp. 2935–2944, 2025.
  29. I. Arshad, M. S. Arshad, M. Malik, W. Raza, and Z. Maryam, “An ensemble convolutional neural network framework for automated mango leaf disease detection,” Spectrum of Engineering Sciences, vol. 4, no. 3, pp. 1711–1740, 2026.
  30. P. Das, M. A. Rahman, M. T. Habib, M. A. A. Khan, and M. M. Islam, “An in-depth analysis for machine-vision-based mango leaf diseases recognition,” in Proc. 2025 6th Int. Conf. Mobile Computing and Sustainable Informatics (ICMCSI), 2025, pp. 1571–1576.