Leveraging Convolutional Neural Networks via Transfer Learning for Robust Multi-Class Disease Identification in Mango Leaves

Manisha Bajpai; Deepshikha; Raj Gaurang Tiwari

doi:10.55524/ijirem.2025.12.3.3

Abstract

Mango leaf disease classification represents a critical agricultural challenge with significant economic implications for global cultivation. This research presents a comprehensive transfer learning framework for automated disease identification in mango leaves, evaluating state-of-the-art deep learning architectures including ConvNeXtBase, VGG19, EfficientNetB7, MobileNetV2, and a custom-designed Convolutional Neural Network(CNN). Leveraging a dataset of 4000 annotated leaf images across 8 categories, we conducted rigorous comparative analysis through k-fold cross-validation and stratified train-test splits. The ConvNeXtBase model demonstrated superior performance, achieving a peak validation accuracy of 0.9969 and test accuracy of 0.9883. These results establish ConvNeXtBase as an optimal solution for scalable precision agriculture systems, providing a robust foundation for mobile-based disease diagnosis in resource-constrained orchard environments.

Keywords

Transfer Learning, Precision Agriculture, Leaf Disease Classification, Field-deployable Models, CNN

References

Balaganesh G. and G. Makarabbi, “An Analysis on Performance of Mango Production in India,” Asian Journal of Agricultural Extension, Economics & Sociology, vol. 41, no. 10, 2023, Available from: https://doi.org/10.9734/ajaees/2023/v41i102250
N. Gururaj, V. Vinod, and K. Vijayakumar, “Deep grading of mangoes using Convolutional Neural Network and Computer Vision,” Multimed Tools Appl, vol. 82, no. 25, pp. 39525–39550, Jul. 2022, Available from: https://doi.org/10.1007/S11042-021-11616-2/METRICS
T. Shaik and S. I. Swamykan, “Identification of Diseases Affecting Mango Leaves Using Deep Learning Models,” Communications in Computer and Information Science, vol. 1907 CCIS, pp. 132–144, 2023, Available from: https://doi.org/10.1007/978-3-031-7997-7_10
O. Russakovsky et al., “ImageNet Large Scale Visual Recognition Challenge,” Int J Comput Vis, vol. 115, no. 3, 2015, Available from: https://doi.org/10.1007/s11263-015-0816-y
C. Wang et al., “Application of Convolutional Neural Network-Based Detection Methods in Fresh Fruit Production: A Comprehensive Review,” Front Plant Sci, vol. 13, p. 868745, May 2022, Available from: https://doi.org/ 10.3389/FPLS.2022.868745/BIBTEX
S. P. Mohanty, D. P. Hughes, and M. Salathé, “Using deep learning for image-based plant disease detection,” Front Plant Sci, vol. 7, no. September, p. 215232, Sep. 2016, Available from: https://doi.org/ 10.3389/FPLS.2016.01419/BIBTEX
H. S. Nagamani and H. Sarojadevi, “Tomato Leaf Disease Detection using Deep Learning Techniques,” International Journal of Advanced Computer Science and Applications, vol. 13, no. 1, 2022, Available from: https://doi.org/ 10.14569/IJACSA.2022.0130138
A. Saini, K. Guleria, and S. Sharma, “Tomato Leaf Disease Classification using Convolutional Neural Network Model,” 2023 2nd International Conference on Electrical, Electronics, Information and Communication Technologies, ICEEICT 2023, 2023, Available from: https://doi.org/ 10.1109/ICEEICT56924.2023.10157203
A. Kumar, N. K. Trivedi, and R. G. Tiwari, “Disease Identification in Potato Leaves Using a Multi-Tier Deep Learning Model,” 2023 3rd Asian Conference on Innovation in Technology, ASIANCON 2023, 2023, Available from: https://doi.org/ 10.1109/ASIANCON58793.2023.10270410
N. K. Trivedi, R. G. Tiwari, V. Gautam, and A. K. Balyan, “Intuitive Handcrafted Features and Multi-Layer Visual Feature Fusion for Automated Classification of Groundnut Leaf Diseases,” 2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems, ICETSIS 2024, pp. 974–979, 2024, Available from: https://doi.org/10.1109/ICETSIS61505.2024.10459399
R. G. Tiwari, A. Misra, V. Khullar, A. K. Agarwal, S. Gupta, and A. P. Srivastava, “Identifying Microscopic Augmented Images using Pre-Trained Deep Convolutional Neural Networks,” in Proceedings of International Conference on Technological Advancements and Innovations, ICTAI 2021, 2021. Available from: https://doi.org/ 10.1109/ICTAI53825.2021.9673472
L. Ramos, E. Casas, C. Romero, F. Rivas-Echeverria, and M. E. Morocho-Cayamcela, “A Study of ConvNeXt Architectures for Enhanced Image Captioning,” IEEE Access, vol. 12, 2024, Available from: https://doi.org/ 10.1109/ACCESS.2024.3356551
F. Adnan, M. J. Awan, A. Mahmoud, H. Nobanee, A. Yasin, and A. M. Zain, “EfficientNetB3-Adaptive Augmented Deep Learning (AADL) for Multi-Class Plant Disease Classification,” IEEE Access, vol. 11, pp. 85426–85440, 2023, Available from: https://doi.org/ 10.1109/ACCESS.2023.3303131
B. Koonce, “EfficientNet,” Convolutional Neural Networks with Swift for Tensorflow, pp. 109–123, 2021, Available from: https://doi.org/ 10.1007/978-1-4842-6168-2_10
H. C. Chen et al., “AlexNet Convolutional Neural Network for Disease Detection and Classification of Tomato Leaf,” Electronics 2022, Vol. 11, Page 951, vol. 11, no. 6, p. 951, Mar. 2022, Available from: https://doi.org/ 10.3390/ELECTRONICS11060951
S. Mascarenhas and M. Agarwal, “A comparison between VGG16, VGG19 and ResNet50 architecture frameworks for Image Classification,” Proceedings of IEEE International Conference on Disruptive Technologies for Multi-Disciplinary Research and Applications, CENTCON 2021, pp. 96–99, 2021, Available from: https://doi.org/ 10.1109/CENTCON52345.2021.9687944
G. Singh, K. Guleria, and S. Sharma, “A Deep Learning-Based Fine-Tuned ResNet50 Model for Multiclass Mango Leaf Disease Classification,” 2nd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2024, pp. 1310–1316, 2024, Available from: https://doi.org/ 10.1109/IDCIOT59759.2024.10467406
S. F. Stefenon, K. C. Yow, A. Nied, and L. H. Meyer, “Classification of distribution power grid structures using inception v3 deep neural network,” Electrical Engineering 2022 104:6, vol. 104, no. 6, pp. 4557–4569, Sep. 2022, Available from: https://doi.org/ 10.1007/S00202-022-01641-1
D. Sinha and M. El-Sharkawy, “Thin MobileNet: An Enhanced MobileNet Architecture,” 2019 IEEE 10th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference, UEMCON 2019, pp. 0280–0285, Oct. 2019, Available from: https://doi.org/ 10.1109/UEMCON47517.2019.8993089
E. M. Martey, H. Lei, X. Li, and O. Appiah, “Effective Image Representation using Double Colour Histogram for Content-Based Image Retrieval,” Informatica (Slovenia), vol. 45, no. 7, 2021, Available from: https://doi.org/ 10.31449/inf.v45i7.3715
S. Gao, “Gray level co-occurrence matrix and extreme learning machine for Alzheimer’s disease diagnosis,” International Journal of Cognitive Computing in Engineering, vol. 2, 2021, Available from: https://doi.org/ 10.1016/j.ijcce.2021.08.002
J. G. A. Barbedo, “An automatic method to detect and measure leaf disease symptoms using digital image processing,” Plant Dis, vol. 98, no. 12, 2014, Available from: https://doi.org/ 10.1094/PDIS-03-14-0290-RE
J. G. Arnal Barbedo, “Plant disease identification from individual lesions and spots using deep learning,” Biosyst Eng, vol. 180, 2019, Available from: https://doi.org/ 10.1016/j.biosystemseng.2019.02.002
S. Ramesh and D. Vydeki, “Application of machine learning in detection of blast disease in south indian rice crops,” Journal of Phytology, vol. 11, 2019, Available from: https://doi.org/ 10.25081/jp.2019.v11.5476
H. Ayaz, E. Rodríguez-Esparza, M. Ahmad, D. Oliva, M. Pérez-Cisneros, and R. Sarkar, “Classification of Apple Disease Based on Non-Linear Deep Features,” Applied Sciences 2021, Vol. 11, Page 6422, vol. 11, no. 14, p. 6422, Jul. 2021, Available from: https://doi.org/ 10.3390/APP11146422
David. P. Hughes and M. Salathe, “An open access repository of images on plant health to enable the development of mobile disease diagnostics,” Nov. 2015, Accessed: May 15, 2025. [Online]. Available from: https://arxiv.org/pdf/1511.08060
M. Brahimi, M. Arsenovic, S. Laraba, S. Sladojevic, K. Boukhalfa, and A. Moussaoui, “Deep Learning for Plant Diseases: Detection and Saliency Map Visualisation,” pp. 93–117, 2018, Available from: https://doi.org/ 10.1007/978-3-319-90403-0_6
A. Ramcharan et al., “A mobile-based deep learning model for cassava disease diagnosis,” Front Plant Sci, vol. 10, 2019, Available from: https://doi.org/ 10.3389/fpls.2019.00272
S. J. Banarase and S. Shirbahadurkar, “Orchard Guard: Deep Learning powered apple leaf disease detection with MobileNetV2 model,” Journal of Integrated Science and Technology, vol. 12, no. 4, 2024, Available from: https://doi.org/ 10.62110/sciencein.jist.2024.v12.799
S. I. Ahmed et al., “MangoLeafBD: A comprehensive image dataset to classify diseased and healthy mango leaves,” Data Brief, vol. 47, p. 108941, Apr. 2023, Available from: https://doi.org/ 10.1016/J.DIB.2023.108941
S. Ali et al., “MangoLeafBD Dataset,” vol. 1, 2022, Available from: https://doi.org/ 10.17632/HXSNVWTY3R.1

Cites this article as

M. Bajpai, Deepshikha, R. G. Tiwari, "Leveraging Convolutional Neural Networks via Transfer Learning for Robust Multi-Class Disease Identification in Mango Leaves", International Journal of Innovative Research in Engineering & Management (IJIREM), Vol-12, Issue-3, Page No-25-31, 2025. Available from: https://doi.org/10.55524/ijirem.2025.12.3.3

Corresponding Author

Manisha Bajpai

M. Tech Scholar, Department of Computer Science and Engineering, Dr. A.P.J. Abdul Kalam Technical University, Lucknow, Uttar Pradesh, India

Download Full Paper

Download PDF

No. of Downloads: 5 | No. of Views: 132

-->

Leveraging Convolutional Neural Networks via Transfer Learning for Robust Multi-Class Disease Identification in Mango Leaves

Citations

Download Full Paper PDF

Total View 132

Total Download 5