An Intelligent Computer Vision and CNN Framework for Automated Plant Disease Detection and Precision Agriculture
Keywords:
Common rust, Computer vision, Convolutional neural network, Deep learning, Grey leaf spot, Image classification, Maize leaf disease, MRW-CNN, Northern leaf blight, Plant disease detection, Precision agriculture, Transfer learningAbstract
Plant diseases represent one of the most critical threats to global agricultural productivity, where maize crops are particularly susceptible to multiple fungal diseases that significantly reduce yield quality and quantity. Traditional disease identification methods depend on manual visual inspection by agricultural experts, which is time-consuming, inconsistent, and impractical for large-scale precision farming applications. Within the paradigm of intelligent agricultural systems, this study proposes an automated deep learning and computer vision framework for maize leaf disease identification and classification. The proposed system introduces a novel Multi-Resolution Weighted CNN (MRW-CNN) architecture that leverages multi-scale feature extraction to achieve superior classification performance across five disease categories, including Common Rust, Grey Leaf Spot, Healthy, Northern Leaf Blight, and Southern Rust. A comprehensive dataset of 2,500 annotated maize leaf images with disease stage annotations (early, advancing, and severe) is utilized for training and evaluation. Comparative analysis of nine fine-tuned CNN architectures demonstrates that MRW-CNN achieves the highest testing accuracy of 97.04% with validation accuracy of 96.56%, outperforming established architectures including Xception (95.80%), MobileNet (94.64%), and Inception V3 (94.48%). The experimental results confirm the effectiveness of the proposed approach in delivering accurate, scalable, and computationally efficient automated disease detection, contributing toward intelligent precision agriculture and early crop disease management systems.
References
S. P. Mohanty, D. P. Hughes, and M. Salathé, “Using deep learning for image-based plant disease detection,” Frontiers in Plant Science, vol. 7, Sep. 2016.
K. P. Ferentinos, “Deep learning models for plant disease detection and diagnosis,” Computers and Electronics in Agriculture, vol. 145, pp. 311–318, Feb. 2018.
E. C. Too, L. Yujian, S. Njuki, and L. Yingchun, “A comparative study of fine-tuning deep learning models for plant disease identification,” Computers and Electronics in Agriculture, vol. 161, pp. 272–279, Jun. 2019.
C. DeChant et al., “Automated identification of northern leaf blight-infected maize plants from field imagery using deep learning,” Phytopathology, vol. 107, no. 11, pp. 1426–1432, Nov. 2017.
A. Ramcharan, K. Baranowski, P. McCloskey, B. Ahmed, J. Legg, and D. P. Hughes, “Deep learning for image-based cassava disease detection,” Frontiers in Plant Science, vol. 8, Oct. 2017.
K. He, X. Zhang, S. Ren and J. Sun, “Deep residual learning for image recognition,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016, pp. 770–778.
C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens and Z. Wojna, “Rethinking the inception architecture for computer vision,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016, pp. 2818–2826.
F. Chollet, “Xception: Deep learning with depthwise separable convolutions,” 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 2017, pp. 1800–1807.
J. G. A. Barbedo, “Factors influencing the use of deep learning for plant disease recognition,” Biosystems Engineering, vol. 172, pp. 84–91, Aug. 2018.
A. Kamilaris and F. X. Prenafeta-Boldú, “Deep learning in agriculture: A survey,” Computers and Electronics in Agriculture, vol. 147, pp. 70–90, Apr. 2018.
P. Jiang, Y. Chen, B. Liu, D. He, and C. Liang, “Real-time detection of apple leaf diseases using deep learning approach based on improved convolutional neural networks,” IEEE Access, vol. 7, pp. 59069–59080, 2019.
A. Singh, B. Ganapathysubramanian, A. K. Singh, and S. Sarkar, “Machine learning for high-throughput stress Phenotyping in plants,” Trends in Plant Science, vol. 21, no. 2, pp. 110–124, Feb. 2016.
K. He, X. Zhang, S. Ren, and J. Sun, “Identity mappings in deep residual networks,” Computer Vision – ECCV 2016, 2016, pp. 630–645.
M. Sandler, A. Howard, M. Zhu, A. Zhmoginov and L. -C. Chen, “MobileNetV2: Inverted residuals and linear bottlenecks,” 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 2018, pp. 4510–4520.
K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv, Apr. 2015.
J. Hu, L. Shen and G. Sun, “Squeeze-and-excitation networks,” 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 2018, pp. 7132–7141.
Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, pp. 436–444, May 2015.
I. Goodfellow, Y. Bengio, and A. Courville, Deep learning. Cambridge, MA, USA: MIT Press, 2016.
O. Russakovsky et al., “ImageNet large scale visual recognition challenge,” International Journal of Computer Vision, vol. 115, pp. 211–252, Apr. 2015.
D. P. Hughes and M. Salathe, “An open access repository of images on plant health to enable the development of mobile disease diagnostics,” arXiv, Apr. 2016.
