GLNet: global-local feature network for wheat leaf disease image classification
2024
GLNet: A New Model for Classifying Wheat Leaf Diseases
publication
Evidence: high
Author Information
Author(s): Li Shangze, Liu Shen, Ji Mingyu, Cao Yuhao, Yun Bai
Primary Institution: Northeast Forestry University, Harbin, China
Hypothesis
Can a global-local feature network improve the classification of wheat leaf disease images?
Conclusion
The GLNet model significantly enhances the accuracy of classifying wheat leaf disease images by effectively integrating local and global features.
Supporting Evidence
- GLNet achieved an accuracy of 0.9638, outperforming traditional CNNs.
- The model effectively captures both local details and global context in wheat leaf disease images.
- GLNet's architecture allows for better feature understanding and expression.
Takeaway
GLNet is a smart computer program that helps farmers quickly and accurately identify diseases in wheat plants by looking at pictures of the leaves.
Methodology
The study developed a global-local feature network (GLNet) that processes global and local features in parallel and integrates them using a feature fusion block.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website