A Convolutional Neural Networks Approach to Detecting Foliar Diseases in Zea Mays

The presence of diseases in Zea Mays (Maize) pose a big threat to food security. This could cause big losses in output to farmers, hence subjecting them to economic burdens. Traditional methods for identifying maize diseases depend on skilled visual identification and expertise, which are not very effective and can lead to wrong diagnosis. This study hereby proposes an effective deep learning approach for the automated identification of foliar diseases in maize plants. The study specifically utilized Convolutional Neural Networks (CNN), incorporating two pre-trained models: EfficientNet and VGG16. Varied dataset comprising images of maize leaves afflicted with several foliar diseases were ensembled to train and test the CNN models. EfficientNet and VGG16 were pretrained models that were fine-tuned to work better for the specific goal of finding the diseases in maize. The experimental findings showed that both VGG16 and EfficientNet demonstrated promising performance, while VGG16 remains a robust baseline with 91% accuracy, the structural efficiency of EfficientNet (96% accuracy) provides a more viable solution for deployment in mobile devices for real-time agricultural diagnosis. The higher accuracy of EfficientNet suggests its suitability for this specific agricultural application and indicates the effectiveness of CNN models in accurately identifying foliar diseases in maize.

Maize, EfficientNet, VGG16, Disease

1. Askale, G. T., Yibel, A. B., Taye, B. M., & Wubneh, G. D. (2025). Mobile based deep CNN model for maize leaf disease detection and classification. Plant Methods, 21(1), 72. [Google Scholar] [Crossref]

2. Atila, Ü., Polat, H., & Özkan, M. (2020) "EfficientNet-based deep learning architecture for plant disease detection." Computers and Electronics in Agriculture, 178, 105739. doi:10.1016/j.compag.2020.105739. [Google Scholar] [Crossref]

3. Bedi, P., & Gole, A. (2020) "Hybrid model based on Convolutional Auto Encoder and Convolutional Neural Network for automatic plant disease detection." In 2020 International Conference on Smart Electronics and Communication (ICOSEC) (pp. 1-5). IEEE. doi:10.1109/ICOSEC49019.2020.9266972. [Google Scholar] [Crossref]

4. Chibesa, M., et al. (2021) "Machine Learning Techniques for Crop Disease Detection and Classification: A Review." Computers and Electronics in Agriculture, 191, 106264. [Google Scholar] [Crossref]

5. Guo, Y., Zhang, Y., Zhang, C., & Jiang, Y. (2020) "A deep learning-based mathematical model for plant disease detection and recognition." International Journal of Advanced Technology and Engineering Exploration, 7(1), 1-6. doi:10.19101/ijatee.2022.10100136. [Google Scholar] [Crossref]

6. Hassan, M., Elhoseny, M., Hassanien, A. E., & Muhammad, K. (2021) "Deep learning-based plant disease detection using convolutional neural networks." Computers, Materials & Continua, 7(2), 2017-2032. doi:10.32604/cmc.2021.014764. [Google Scholar] [Crossref]

7. Jana, S., Begum, A. R., Selvaganesan, S. (2020) "Design and Analysis of Pepper Leaf Disease Detection Using Deep Belief Network." European Journal of Molecular & Clinical Medicine, Volume 7, pp. 1724-1731. [Google Scholar] [Crossref]

8. Liu J, He C, Jiang Y, Wang M, Ye Z, & He M. (2024) A high-precision identification method for maize leaf diseases and pests based on LFMNet under complex backgrounds. Plants. 2024. https://doi.org/10.3390/plants13131827. [Google Scholar] [Crossref]

9. Liu, J. and Wang, X. (2021) "Plant diseases and pests detection based on Deep Learning: a review," Plant Methods, pp.17, 22. [Google Scholar] [Crossref]

10. Wang, N., Sundin, G. W., Fuente, L. D. L., Cubero, J., Tatineni, S., Brewer, M. T., ... & Munkvold, G. (2024). Key challenges in plant pathology in the next decade. Phytopathology®, 114(5), 837-842. [Google Scholar] [Crossref]

11. Yuan, Y., Chen, L., Wu, H., & Li, L. (2022). Advanced agricultural disease image recognition technologies: A review. Information Processing in Agriculture, 9(1), 48-59. [Google Scholar] [Crossref]

• What the Desert Fathers Teach Data Scientists: Ancient Ascetic Principles for Ethical Machine-Learning Practice
• Comparative Analysis of Some Machine Learning Algorithms for the Classification of Ransomware
• Comparative Performance Analysis of Some Priority Queue Variants in Dijkstra’s Algorithm
• Transfer Learning in Detecting E-Assessment Malpractice from a Proctored Video Recordings.
• Dual-Modal Detection of Parkinson’s Disease: A Clinical Framework and Deep Learning Approach Using NeuroParkNet