Optimized Dense Dilated Convolutional Attention Vision Transformer (ODCAViT)-Based Multi-Fruit Disease Detection
Received: 24 January 2026 | Revised: 23 March 2026, 4 April 2026, and 10 April 2026 | Accepted: 17 April 2026 | Online: 6 June 2026
Corresponding author: Abbott Po Shun Chen
Abstract
The early detection of fruit diseases plays an important role in modern agriculture, as it helps enhance crop quality and significantly reduces post-harvest losses. This work proposes a unified deep-learning framework for the detection of diseases across different types of fruits such as oranges, mangoes, and pomegranates. Specifically, an Optimized Dense Dilated Convolutional Attention Vision Transformer (ODCAViT) is introduced, which incorporates densely connected dilated convolutional layers into an attention-enhanced Vision Transformer (ViT) architecture. These dense dilated convolutions preserve spatial hierarchies and allow the model to recognize subtle details and scattered disease symptoms in various fruits. In addition, the model captures long-range dependencies and global contextual information, whereas feature responses are refined by focusing on the most discriminative regions using channel attention and Squeeze-and-Excitation (SE) modules. To further improve computational efficiency, the Chaotic Puma Optimization Algorithm (CPOA) is utilized to obtain optimal parameter settings. Experimental results demonstrate that ODCAViT achieves high performance, with 99% accuracy on the pomegranate and mango datasets and 98% accuracy on the orange dataset. Overall, the proposed model demonstrates strong potential for precision agriculture and intelligent fruit disease monitoring.
Keywords:
fruit disease detection, deep learning, dilated convolution, Vision Transformer (ViT)References
A. Tempelaere et al., "An introduction to artificial intelligence in machine vision for postharvest detection of disorders in horticultural products," Postharvest Biology and Technology, vol. 206, Dec. 2023, Art. no. 112576.
P. Sajitha, A. D. Andrushia, N. Anand, and M. Z. Naser, "A review on machine learning and deep learning image-based plant disease classification for industrial farming systems," Journal of Industrial Information Integration, vol. 38, Mar. 2024, Art. no. 100572.
R. Akhter and S. A. Sofi, "Precision agriculture using IoT data analytics and machine learning," Journal of King Saud University - Computer and Information Sciences, vol. 34, no. 8, Part B, pp. 5602–5618, Sept. 2022.
D. B. Ahuja and C. Chattopadhyay, "Pests of Fruit Trees (Citrus, Banana, Mango, Pomegranate and Sapota): E-Pest Surveillance and Pest Management Advisory," ICAR-National Research Centre for Integrated Pest Management, New Delhi and State Department of Horticulture, Commissionerate of Agriculture, Pune, India, 2015.
P. KAUR et al., "DELM: Deep Ensemble Learning Model for Multiclass Classification of Super-Resolution Leaf Disease Images," Turkish Journal of Agriculture and Forestry, vol. 47, no. 5, pp. 727–745, Oct. 2023.
H. M. Zayani et al., "Deep Learning for Tomato Disease Detection with YOLOv8," Engineering, Technology & Applied Science Research, vol. 14, no. 2, pp. 13584–13591, Apr. 2024.
Z. Chen, J. Feng, K. Zhu, Z. Yang, Y. Wang, and M. Ren, "YOLOv8-ACCW: Lightweight Grape Leaf Disease Detection Method Based on Improved YOLOv8," IEEE Access, vol. 12, pp. 123595–123608, 2024.
K. Aghamohammadesmaeilketabforoosh, S. Nikan, G. Antonini, and J. M. Pearce, "Optimizing Strawberry Disease and Quality Detection with Vision Transformers and Attention-Based Convolutional Neural Networks," Foods, vol. 13, no. 12, June 2024, Art. no. 1869.
A. Agarwal, A. Sarkar, and A. K. Dubey, "Computer Vision-Based Fruit Disease Detection and Classification," in Smart Innovations in Communication and Computational Sciences: Proceedings of ICSICCS-2018, Burla, Odisha, India, 2018, pp. 105–115.
Y. Liu, Y. Hu, W. Cai, G. Zhou, J. Zhan, and L. Li, "DCCAM-MRNet: Mixed Residual Connection Network with Dilated Convolution and Coordinate Attention Mechanism for Tomato Disease Identification," Computational Intelligence and Neuroscience, vol. 2022, no. 1, Apr. 2022, Art. no. 4848425.
S. Zhang, S. Zhang, C. Zhang, X. Wang, and Y. Shi, "Cucumber leaf disease identification with global pooling dilated convolutional neural network," Computers and Electronics in Agriculture, vol. 162, pp. 422–430, July 2019.
C. Xu, X. Wang, and S. Zhang, "Dilated convolution capsule network for apple leaf disease identification," Frontiers in Plant Science, vol. 13, Nov. 2022, Art. no. 1002312.
P. Sajitha, A. Diana Andrushia, N. Anand, M. Z. Naser, and E. Lubloy, "A deep learning approach to detect diseases in pomegranate fruits via hybrid optimal attention capsule network," Ecological Informatics, vol. 84, Dec. 2024, Art. no. 102859.
Q. Zeng, L. Niu, S. Wang, and W. Ni, "SEViT: a large-scale and fine-grained plant disease classification model based on transformer and attention convolution," Multimedia Systems, vol. 29, no. 3, pp. 1001–1010, June 2023.
S. Seilov, A. Nurzhaubayev, M. Baideldinov, B. Zhursinbek, M. Ashimgaliyev, and A. Zhumadillayeva, "Hybrid Multi-Scale Neural Network with Attention-Based Fusion for Fruit Crop Disease Identification," Journal of Imaging, vol. 11, no. 12, Dec. 2025, Art. no. 440.
J. Hu, L. Shen, and G. Sun, "Squeeze-and-Excitation Networks," in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 2018, pp. 7132–7141.
G. Lin, Q. Wu, L. Qiu, and X. Huang, "Image super-resolution using a dilated convolutional neural network," Neurocomputing, vol. 275, pp. 1219–1230, Jan. 2018.
S. Senthil Pandi, A. Senthilselvi, J. Gitanjali, K. ArivuSelvan, J. Gopal, and J. Vellingiri, "Rice plant disease classification using dilated convolutional neural network with global average pooling," Ecological Modelling, vol. 474, Dec. 2022, Art. no. 110166.
S. Verma, A. Chug, R. P. Singh, A. P. Singh, and D. Singh, "SE-CapsNet: Automated evaluation of plant disease severity based on feature extraction through Squeeze and Excitation (SE) networks and Capsule networks," Kuwait Journal of Science, vol. 49, no. 1, pp. 1–31, 2022.
A. Y. Ashurov et al., "Enhancing plant disease detection through deep learning: a Depthwise CNN with squeeze and excitation integration and residual skip connections," Frontiers in Plant Science, vol. 15, Jan. 2025, Art. no. 1505857.
B. N. Naik, R. Malmathanraj, and P. Palanisamy, "Detection and classification of chilli leaf disease using a squeeze-and-excitation-based CNN model," Ecological Informatics, vol. 69, July 2022, Art. no. 101663.
L. R. Ali, S. A. Jebur, M. M. Jahefer, A. K. Nawar, and Z. S. Mahdi, "Integrating Squeeze-and-Excitation Network with Pretrained CNN Models for Accurate Plant Disease Detection," International Journal of Electrical and Computer Engineering Systems, vol. 16, no. 8, pp. 621–632, Sept. 2025.
Y. Pratama, E. Rasywir, and A. Siswanto, "Optimized Non-Overlapping Multi-Object Segmentation for Palm Oil Images Using FCN with Squeeze-and-Excitation and Attention Mechanisms," Scientific Journal of Informatics, vol. 12, no. 1, pp. 87–98, May 2025.
X. Wang, T. Kong, C. Shen, Y. Jiang, and L. Li, "SOLO: Segmenting Objects by Locations," in Computer Vision – ECCV 2020: 16th European Conference, Glasgow, UK, 2020, pp. 649–665.
T.-Y. Hsiao, Y.-C. Chang, H.-H. Chou, and C.-T. Chiu, "Filter-based deep-compression with global average pooling for convolutional networks," Journal of Systems Architecture, vol. 95, pp. 9–18, May 2019.
Y. Wang, G. Wang, C. Chen, and Z. Pan, "Multi-scale dilated convolution of convolutional neural network for image denoising," Multimedia Tools and Applications, vol. 78, no. 14, pp. 19945–19960, July 2019.
C. Xu, C. Yu, S. Zhang, and X. Wang, "Multi-Scale Convolution-Capsule Network for Crop Insect Pest Recognition," Electronics, vol. 11, no. 10, May 2022, Art. no. 1630.
K. Han et al., "A Survey on Vision Transformer," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 1, pp. 87–110, Jan. 2023.
B. Abdollahzadeh et al., "Puma optimizer (PO): a novel metaheuristic optimization algorithm and its application in machine learning," Cluster Computing, vol. 27, no. 4, pp. 5235–5283, July 2024.
G. Kaur and S. Arora, "Chaotic whale optimization algorithm," Journal of Computational Design and Engineering, vol. 5, no. 3, pp. 275–284, July 2018.
G. I. Sayed, A. Darwish, and A. E. Hassanien, "A New Chaotic Whale Optimization Algorithm for Features Selection," Journal of Classification, vol. 35, no. 2, pp. 300–344, July 2018.
M. Kmich et al., "Chaotic Puma Optimizer Algorithm for controlling wheeled mobile robots," Engineering Science and Technology, an International Journal, vol. 63, Mar. 2025, Art. no. 101982.
"Orange Quality Analysis Dataset." Kaggle. [Online]. Available: https://www.kaggle.com/datasets/shruthiiiee/orange-quality.
P. B and D. H. R, "Pomegranate Fruit Diseases Dataset for Deep Learning Models." Mendeley Data, Nov. 15, 2023.
P. B․ and H. R․, "A comprehensive standardized dataset of numerous pomegranate fruit diseases for deep learning," Data in Brief, vol. 54, June 2024, Art. no. 110284.
"MangoFruitDDS." Kaggle. [Online]. Available: https://www.kaggle.com/datasets/warcoder/mangofruitdds.
D. Faye, I. Diop, N. Mbaye, D. Dione, and M. M. Diedhiou, "MangoFruitDDS: A Standard Mango Fruit Diseases Dataset Made in Africa," in Advanced Research in Technologies, Information, Innovation and Sustainability: Third International Conference, Madrid, Spain, 2023, pp. 237–250.
G. T. Yehulu et al., "Mango fruit disease detection and classification using MobileNetV3_large model," Scientific African, vol. 30, Dec. 2025, Art. no. e03061.
Q. Wang, B. Wu, P. Zhu, P. Li, W. Zuo, and Q. Hu, "ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks," in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, 2020, pp. 11531–11539.
H. Wang, S. Qiu, H. Ye, and X. Liao, "A Plant Disease Classification Algorithm Based on Attention MobileNet V2," Algorithms, vol. 16, no. 9, Sept. 2023, Art. no. 442.
Downloads
How to Cite
License
Copyright (c) 2026 P. Sajitha, Diana A. Andrushia, N. Anand, S. S. Suni, Christine Dewi, Abbott Po Shun Chen
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
