LTVC-Net : Multi-scale dilated and attention-based CNN for mango leaf disease detection
*Mohan Vishal GuptaCorresponding authormohan.computers@tmu.ac.inDepartment of Computer Science & EngineeringCollege of Computing Sciences & Information TechnologyTeerthanker Mahaveer UniversityMoradabad, Uttar Pradesh, 244001, India0000-0002-7315-7207View full profile → , Ranjana Sharmasharmaranjana04@gmail.comDepartment of Computer Science and EngineeringSRM Institute of Science and TechnologyModinagar, Ghaziabad, Uttar Pradesh, 201204, India0000-0002-0088-7153View full profile → , Gesu Thakurdrgesuthakur@gmail.comDepartment of Computer Science & EngineeringCollege of Smart ComputingCOER UniversityRoorkee, Uttrakhand, 247667, India0000-0001-8940-3444View full profile → , Bhupender Singh Rawatrawat.bhupender@gmail.comDepartment of Computer Science & EngineeringCollege of Smart ComputingCOER UniversityRoorkee, Uttrakhand, 247667, India0000-0002-6682-0648View full profile →
* Corresponding author · click or hover a name for details
- Received:
- 01 Dec 2025
- Published Online:
- 31 Jul 2026
- Article type:
- Research Article
- Language:
- EN
- Article no.:
- JIOS-2328
- Pages:
- 2743–2756
Abstract
Mango ranks among the fruits that are of high economic value, and the leaf diseases like anthracnose, powdery mildew, bacterial canker, and sooty mold have great impact on the productivity. Efficient and accurate diagnosis of the disease is very essential for improving the output and sustaining a good agricultural process. Recent advancements in the field of computer vision and deep learning have depicted promising features in plant disease diagnosis. Convolutional neural networks (CNNs) and transfer learning models have shown significant improvement in the process of leaf disease recognition among fruits like mangoes. However, most of the models have depicted generic architecture that could not effectively focus on leaf texture and vein pattern features, which are very essential in disease recognition in complex backgrounds. To overcome the limitations, a new Leaf Texture and Vein pattern-aware Convolutional Neural Networks (LTVC-Net) model specifically targeting the process of mango leaf disease recognition has been proposed in this research. LTVC-Net incorporates dual-scale dilated convolution and channel attention module in its architecture in order to improve multi-scale feature learning while retaining the disease-causing vein and texture features. Experiments on the proposed model have been performed on a publicly available dataset of mango leaf disease that contains multiple disease classes and normal ones. Extensive experiments on the proposed architecture have been performed while comparing the result with five efficient deep learning models that are MobileNetV2, ResNet50, EfficientNetB0, DenseNet121, and InceptionV3 models respectively. Based on the results in terms of ‘accuracy evaluation,’ ‘loss convergence,’ and ‘ROCAUC evaluation,’ the proposed LTVC-Net architecture clearly outperformed all other models in terms of efficiency and minimizes computational cost that could be effectively suitable for real-world applications in agriculture.
Keywords
Subject Classifications
References
[1] U. S. Rao, R. Swathi, V. Sanjana, L. Arpitha, K. Chandrasekhar, and P. K. Naik, “Deep learning precision farming: Grapes and mango leaf disease detection by transfer learning,” Global Transitions Proc., vol. 2, no. 2, pp. 535–544 (2021), doi: 10.1016/j.gltp.2021.08.043.
[2] S. Arivazhagan and S. V. Ligi, “Mango leaf diseases identification using convolutional neural network,” Int. J. Pure Appl. Math., vol. 120, no. 6, pp. 11067–11079 (2018).
[3] N. K. Saini and R. Sharma, “Deep learning approaches for crowd density estimation: A review,” in Proc. 12th Int. Conf. Syst. Modeling Adv. Res. Trends (SMART), pp. 83–88 (2023), doi: 10.1109/SMART59791.2023.10401209.
[4] S. Gulavnai and R. Patil, “Deep learning for image based mango leaf disease detection,” Int. J. Recent Technol. Eng., vol. 8, no. 3S3, pp. 54–56 (2019).
[5] M. R. Mia, S. Roy, S. K. Das, and M. A. Rahman, “Mango leaf disease recognition using neural network and support vector machine,” Iran J. Comput. Sci., vol. 3, no. 3, pp. 185–193 (2020), doi: 10.1007/s42044-020-00059-9.
[6] A. Sharma, R. K. Bijral, J. Manhas, and V. Sharma, “Mango leaf diseases detection using deep learning,” Int. J. Knowl. Based Comput. Syst., vol. 10, no. 1, pp. 40–44 (2022).
[7] M. Mohapatra, A. K. Parida, P. K. Mallick, and N. Padhy, “Mango leaf disease detection based on deep learning approach,” in Proc. Int. Conf. Advancements Smart Secure Intell. Comput. (ASSIC), pp. 1–7 (2022), doi: 10.1109/ASSIC55218.2022.10088364.
[8] K. P. Asha Rani and S. Gowrishankar, “ConvNeXt-based mango leaf disease detection: Differentiating pathogens and pests for improved accuracy,” Int. J. Adv. Comput. Sci. Appl., vol. 14, no. 6, pp. 73–82 (2023), doi: 10.14569/IJACSA.2023.0140608.
[9] R. Saleem, J. H. Shah, M. Sharif, and G. J. Ansari, “Mango leaf disease identification using fully resolution convolutional network,” Comput. Mater. Contin., vol. 69, no. 3, pp. 3591–3609 (2021), doi: 10.32604/cmc.2021.018665.
[10] V. Gautam, R. K. Ranjan, P. Dahiya, and A. Kumar, “ESDNN: A novel ensembled stack deep neural network for mango leaf disease classification and detection,” Multimed. Tools Appl., vol. 83, no. 4, pp. 10989–11015 (2024), doi: 10.1007/s11042-023-16264-z.
[11] R. Saleem, J. H. Shah, M. Sharif, M. Yasmin, H. S. Yong, and J. Cha, “Mango leaf disease recognition and classification using novel segmentation and vein pattern technique,” Appl. Sci., vol. 11, no. 24, Art. no. 11901 (2021), doi: 10.3390/app112411901.
[12] T. Varma, P. Mate, N. A. Azeem, S. Sharma, and B. Singh, “Automatic mango leaf disease detection using different transfer learning models,” Multimed. Tools Appl., vol. 84, no. 11, pp. 9185–9218 (2025), doi: 10.1007/s11042-024-20161-4.
[13] S. Zaman, A. H. Nur, R. B. Sulaiman, M. Aljaidi, M. N. Uddin, W. Hadi, and A. Alsarhan, “Transforming mango cultivation: A deep learning approach for leaf disease detection,” in Proc. 1st Int. Conf. Comput. Intell. Approaches Appl. (ICCIAA), pp. 1–7 (2025).
[14] B. Zhang, Z. Wang, C. Ye, H. Zhang, K. Lou, and W. Fu, “Classification of infection grade for anthracnose in mango leaves under complex background based on CBAM-DBIRNet,” Expert Syst. Appl., vol. 260, Art. no. 125343 (2025), doi: 10.1016/j.eswa.2024.125343.
[15] M. E. Rayed, J. R. Jim, M. J. Islam, M. F. Mridha, M. M. Kabir, and M. J. Hossen, “MangoLeafXNet: An explainable deep learning model for accurate mango leaf disease classification,” IEEE Access, early access (2025), doi: 10.1109/ACCESS.2025.3564928.
[16] F. S. Alamri, T. Sadad, A. S. Almasoud, R. A. Aurangzeb, and A. Khan, “Mango disease detection using fused vision transformer with ConvNeXt architecture,” Comput. Mater. Contin., vol. 83, no. 1, pp. 1069–1088 (2025), doi: 10.32604/cmc.2025.061197.
[17] W. T. Sung, I. G. T. Isa, and S. J. Hsiao, “Improved mango disease detection model for energy-efficient edge computing device,” Sens. Mater., vol. 37, no. 2, pp. 697–715 (2025), doi: 10.18494/SAM5308.
[18] B. Farhana, N. A. Muhammad, A. Muhammad, and T. Muhammad, “Ensembled AttenNet: A novel deep learning approach for mango leaf disease detection,” Phys. Educ. Health Soc. Sci., vol. 2, no. 1, pp. 1–15 (2025).
[19] M. V. Gupta, R. K. Dwivedi, and A. Kumar, “Enhancing remote sensing satellite image classification through parameter optimization in hybrid CNN-LSTM model,” J. Discrete Math. Sci. Cryptogr., vol. 26, no. 7, pp. 2061–2079 (2023), doi: 10.47974/JDMSC-1855.
[20] M. V. Gupta, R. K. Dwivedi, and A. Kumar, “Impact analysis of convolutional neural network in classification of satellite imagery,” J. Inf. Optim. Sci., vol. 44, no. 6, pp. 1151–1166 (2023), doi: 10.47974/JIOS-1453.
