Fast and Efficient CNN Architectures for Automated ‎Soybean Leaf Disease Classification

  • Authors

    • Kalpesh Patel College of Agriculture, Anand Agricultural University, Vaso, Kheda, Gujarat, India
    • Atul Patel Smt. C M Patel Institute of Computer Applications, Charotar University of Science and Technology, Changa, Anand, Gujarat, India
    https://doi.org/10.14419/myqfsc31

    Received date: September 5, 2025

    Accepted date: November 20, 2025

    Published date: November 29, 2025

  • Deep Learning; Separable CNN; Global Average Pooling; Soybean Leaf Disease; Computational Complexity

  • Abstract

    Soybean leaf diseases significantly affect crop yields in Indian agriculture. Timely detection is crucial for managing these diseases effectively-‎ly. While traditional CNN models deliver high accuracy, they have significant computational demands and slower speeds, limiting real-time ‎use. This study aims to create faster CNN models that effectively identify eight common soybean leaf diseases while being easier to train. ‎The method uses a Separable-CNN with a Global Average Pooling (GAP) layer to reduce parameters and computing needs. The dataset ‎used to train the Fast CNN and Enhanced CNN models included 40,000 images across eight disease categories. These models underwent ‎evaluation using validation and test datasets with varying splits: 70-20-10, 65-25-10, and 60-30-10. The Enhanced CNN achieved 98.14% ‎test accuracy, outperforming models like VGG16, ResNet152V2, and InceptionV3. The Fast CNN achieved 95.70% accuracy with reduced ‎training time, making it suitable for real-time deployment. The confusion matrix showed high accuracy with few errors. The new CNN ‎models accurately identify soybean leaf diseases and work efficiently. These models could help manage diseases quickly and improve AI ‎tools in agriculture‎.

  • References

    1. E. D. K. Ruby, S. Gopalakrishnan, T. Chitra, A. Choubey, G. Amirthayogam, and G. Sasi, “Advanced Image Processing Techniques for Automat-ed Detection of Healthy and Infected Leaves in Agricultural Systems,” Mesopotamian Journal of Computer Science, vol. 2024, pp. 62–70, Jun. 2024, https://doi.org/10.58496/MJCSC/2024/006.
    2. A. Haridasan, J. Thomas, and E. D. Raj, “Deep learning system for paddy plant disease detection and classification.” Environ Monit Assess, vol. 195, no. 1, Nov. 2022, https://doi.org/10.1007/s10661-022-10656-x.
    3. A. B. Duque, D. Macêdo, C. Zanchettin, and L. L. J. Santos, “Squeezed Very Deep Convolutional Neural Networks for Text Classification,” Springer, 2019, pp. 193–207. https://doi.org/10.1007/978-3-030-30487-4_16.
    4. B. Liu, J. Li, D. Zou, L. Feng, P. Fu, and S. Feng, “An FPGA-Based CNN Accelerator Integrating Depthwise Separable Convolution,” Electronics (Basel), vol. 8, no. 3, p. 281, Mar. 2019, https://doi.org/10.3390/electronics8030281.
    5. Q. Zhu, X. Jiang, and R. Ye, “Sentiment Analysis of Review Text Based on BiGRU-Attention and Hybrid CNN,” IEEE Access, vol. 9, pp. 149077–149088, Jan. 2021, https://doi.org/10.1109/ACCESS.2021.3118537.
    6. H. Sinha, V. Awasthi, and P. K. Ajmera, “Audio classification using braided convolutional neural networks,” IET Signal Processing, vol. 14, no. 7, pp. 448–454, Sep. 2020, https://doi.org/10.1049/iet-spr.2019.0381.
    7. V. Christlein, M. Seuret, A. Nicolaou, L. Spranger, A. Maier, and P. Kral, “Deep Generalized Max Pooling,” Institute of Electrical Electronics En-gineers, Sep. 2019, pp. 1090–1096. https://doi.org/10.1109/ICDAR.2019.00177.
    8. T. Liu et al., “Spatial Channel Attention for Deep Convolutional Neural Networks,” Mathematics, vol. 10, no. 10, p. 1750, May 2022, https://doi.org/10.3390/math10101750.
    9. P. Vasavi, A. Punitha, and T. V. Narayana Rao, “Crop leaf disease detection and classification using machine learning and deep learning algorithms by visual symptoms: a review,” International Journal of Electrical and Computer Engineering (IJECE), vol. 12, no. 2, p. 2079, Apr. 2022, https://doi.org/10.11591/ijece.v12i2.pp2079-2086.
    10. L. W. Kuswidiyanto, X. Han, and H.-H. Noh, “Plant Disease Diagnosis Using Deep Learning Based on Aerial Hyperspectral Images: A Review,” Remote Sens (Basel), vol. 14, no. 23, p. 6031, Nov. 2022, https://doi.org/10.3390/rs14236031.
    11. H. Paul, H. Udayangani, K. Umesha, N. Lankasena, C. Liyanage, and K. Thambugala, “Maize leaf disease detection using a convolutional neural network: a mobile application based on pre-trained VGG16 architecture,” N Z J Crop Hortic Sci, vol. 53, no. 2, pp. 367–383, Aug. 2024, https://doi.org/10.1080/01140671.2024.2385813.
    12. C. P. Vijay and K. Pushpalatha, “DV-PSO-Net: A novel deep mutual learning model with Heuristic search using Particle Swarm optimization for Mango leaf disease detection,” Journal of Integrated Science and Technology, May 2024, https://doi.org/10.62110/sciencein.jist.2024.v12.804.
    13. H. Hairani and T. Widiyaningtyas, “Augmented Rice Plant Disease Detection with Convolutional Neural Networks,” INTENSIF: Jurnal Ilmiah Penelitian dan Penerapan Teknologi Sistem Informasi, vol. 8, no. 1, pp. 27–39, Feb. 2024, https://doi.org/10.29407/intensif.v8i1.21168.
    14. S. B. Jadhav, V. R. Udupi, and S. B. Patil, “Identification of plant diseases using convolutional neural networks,” International Journal of Infor-mation Technology, vol. 13, no. 6, pp. 2461–2470, Feb. 2020, https://doi.org/10.1007/s41870-020-00437-5.
    15. L. M. Abouelmagd, M. Y. Shams, H. S. Marie, and A. E. Hassanien, “An optimized capsule neural network for tomato leaf disease classification,” EURASIP J Image Video Process, vol. 2024, no. 1, Jan. 2024, https://doi.org/10.1186/s13640-023-00618-9.
    16. E. Hirani, V. Magotra, P. Bide, and J. Jain, “Plant Disease Detection Using Deep Learning,” institute of electrical electronics engineers, Apr. 2021, pp. 1–4. https://doi.org/10.1109/I2CT51068.2021.9417910.
    17. A. Tuncer, “Cost-optimized hybrid convolutional neural networks for detection of plant leaf diseases,” J Ambient Intell Humaniz Comput, vol. 12, no. 8, pp. 8625–8636, May 2021, https://doi.org/10.1007/s12652-021-03289-4.
    18. M. S. Islam et al., “Multimodal Hybrid Deep Learning Approach to Detect Tomato Leaf Disease Using Attention Based Dilated Convolution Fea-ture Extractor with Logistic Regression Classification.,” Sensors, vol. 22, no. 16, p. 6079, Aug. 2022, https://doi.org/10.3390/s22166079.
    19. V. K. Vishnoi, B. Kumar, K. Kumar, A. A. Khan, and S. Mohan, “Detection of Apple Plant Diseases Using Leaf Images Through Convolutional Neural Network,” IEEE Access, vol. 11, pp. 6594–6609, Jan. 2023, https://doi.org/10.1109/ACCESS.2022.3232917.
    20. M. Z. Hasan, K. M. Z. Hasan, M. S. Ahamed, and A. Rakshit, “Recognition of Jute Diseases by Leaf Image Classification using Convolutional Neural Network,” institute of electrical electronics engineers, Jul. 2019, pp. 1–5. https://doi.org/10.1109/ICCCNT45670.2019.8944907.
    21. A. Khan, A. Sohail, A. S. Qureshi, and U. Zahoora, “A survey of the recent architectures of deep convolutional neural networks,” Artif Intell Rev, vol. 53, no. 8, pp. 5455–5516, Apr. 2020, https://doi.org/10.1007/s10462-020-09825-6.
    22. E. Suryawati, R. Sustika, R. S. Yuwana, H. F. Pardede, and A. Subekti, “Deep Structured Convolutional Neural Network for Tomato Diseases De-tection,” institute of electrical electronics engineers, Oct. 2018, pp. 385–390. https://doi.org/10.1109/ICACSIS.2018.8618169.
    23. R. Tabares-Soto et al., “Strategy to improve the accuracy of convolutional neural network architectures applied to digital image steganalysis in the spatial domain.,” PeerJ Comput Sci, vol. 7, no. 5, p. e451, Apr. 2021, https://doi.org/10.7717/peerj-cs.451.
    24. M. Dai et al., “Pepper leaf disease recognition based on enhanced lightweight convolutional neural networks.,” Front Plant Sci, vol. 14, Aug. 2023, https://doi.org/10.3389/fpls.2023.1230886.
    25. A. Y. Ashurov et al., “Enhancing plant disease detection through deep learning: a Depthwise CNN with squeeze and excitation integration and re-sidual skip connections.,” Front Plant Sci, vol. 15, Jan. 2025, https://doi.org/10.3389/fpls.2024.1505857.
    26. T. S. Alam, C. B. Jowthi, and A. Pathak, “Comparing pre-trained models for efficient leaf disease detection: a study on custom CNN,” Journal of Electrical Systems and Information Technology, vol. 11, no. 1, Feb. 2024, https://doi.org/10.1186/s43067-024-00137-1.
    27. A. Zisserman and K. Simonyan, “Very Deep Convolutional Networks for Large-Scale Image Recognition,” Sep. 2014.
    28. K. He, S. Ren, X. Zhang, and J. Sun, “Identity Mappings in Deep Residual Networks,” Mar. 2016, cornell university. https://doi.org/10.1007/978-3-319-46493-0_38.
    29. Y. Liu, S. Xu, D. Cheng, J. Han, and D. Zhang, “Capsule Networks with Residual Pose Routing.,” IEEE Trans Neural Netw Learn Syst, vol. 36, no. 2, pp. 2648–2661, Feb. 2025, https://doi.org/10.1109/TNNLS.2023.3347722.
    30. F. Chollet, “Xception: Deep Learning with Depthwise Separable Convolutions,” Oct. 2016, cornell university. https://doi.org/10.1109/CVPR.2017.195.
    31. R. Zhao, W. Luk, and X. Niu, “Automatic Optimising CNN with Depthwise Separable Convolution on FPGA,” association for computing machin-ery, Feb. 2018, p. 285. https://doi.org/10.1145/3174243.3174959.
    32. E. Rahimian, S. F. Atashzar, S. Zabihi, A. Asif, and A. Mohammadi, “XceptionTime: Independent Time-Window Xceptiontime Architecture for Hand Gesture Classification,” institute of electrical electronics engineers, May 2020, pp. 1304–1308. https://doi.org/10.1109/ICASSP40776.2020.9054586.
    33. C. Szegedy, Z. Wojna, J. Shlens, S. Ioffe, and V. Vanhoucke, “Rethinking the Inception Architecture for Computer Vision,” institute of electrical electronics engineers, Jun. 2016, pp. 2818–2826. https://doi.org/10.1109/CVPR.2016.308.
    34. M. Z. Alom, C. Yakopcic, V. K. Asari, M. Hasan, and T. M. Taha, “Inception recurrent convolutional neural network for object recognition,” Mach Vis Appl, vol. 32, no. 1, Jan. 2021, https://doi.org/10.1007/s00138-020-01157-3.
    35. C. Szegedy, S. Ioffe, V. Vanhoucke, and A. Alemi, “Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning,” Pro-ceedings of the AAAI Conference on Artificial Intelligence, vol. 31, no. 1, Feb. 2017, https://doi.org/10.1609/aaai.v31i1.11231.
    36. M. G. Ragab, S. J. Abdulkadir, and N. Aziz, “Random Search One Dimensional CNN for Human Activity Recognition,” institute of electrical elec-tronics engineers, Oct. 2020, pp. 86–91. https://doi.org/10.1109/ICCI51257.2020.9247810.
    37. G. Lu, Z. Wang, and W. Zhang, “Optimizing Depthwise Separable Convolution Operations on GPUs,” IEEE Transactions on Parallel and Distrib-uted Systems, vol. 33, no. 1, pp. 70–87, Jan. 2022, https://doi.org/10.1109/TPDS.2021.3084813.
    38. R. Zhao, W. Luk, and X. Niu, “Automatic Optimising CNN with Depthwise Separable Convolution on FPGA,” association for computing machin-ery, Feb. 2018, p. 285. https://doi.org/10.1145/3174243.3174959.
    39. F. Chollet, “Xception: Deep Learning with Depthwise Separable Convolutions,” Oct. 2016, cornell university. https://doi.org/10.1109/CVPR.2017.195.
    40. R. Ye, L. Zhang, and F. Liu, “3D Depthwise Convolution: Reducing Model Parameters in 3D Vision Tasks,” springer, 2019, pp. 186–199. https://doi.org/10.1007/978-3-030-18305-9_15.
    41. M. Z. Asghar et al., “Facial Mask Detection Using Depthwise Separable Convolutional Neural Network Model During COVID-19 Pandemic.,” Front Public Health, vol. 10, Mar. 2022, https://doi.org/10.3389/fpubh.2022.855254.
    42. A. Bhujel, N.-E. Kim, E. Arulmozhi, J. K. Basak, and H.-T. Kim, “A Lightweight Attention-Based Convolutional Neural Networks for Tomato Leaf Disease Classification,” Agriculture, vol. 12, no. 2, p. 228, Feb. 2022, https://doi.org/10.3390/agriculture12020228.
    43. Y. Gulzar, “Enhancing soybean classification with modified inception model: A transfer learning approach,” Emir J Food Agric, vol. 36, pp. 1–9, Apr. 2024, https://doi.org/10.3897/ejfa.2024.122928.
    44. L. Meng, “The Convolutional Neural Network Text Classification Algorithm in the Information Management of Smart Tourism Based on Internet of Things,” IEEE Access, vol. 12, pp. 3570–3580, Jan. 2024, https://doi.org/10.1109/ACCESS.2024.3349386.
    45. E. Westphal and H. Seitz, “A machine learning method for defect detection and visualization in selective laser sintering based on convolutional neural networks,” Addit Manuf, vol. 41, p. 101965, Mar. 2021, https://doi.org/10.1016/j.addma.2021.101965.

  • Downloads

  • How to Cite

    Patel, K. ., & Patel, A. . (2025). Fast and Efficient CNN Architectures for Automated ‎Soybean Leaf Disease Classification. International Journal of Basic and Applied Sciences, 14(7), 595-605. https://doi.org/10.14419/myqfsc31