ORIGINAL RESEARCH article
Front. Plant Sci.
Sec. Sustainable and Intelligent Phytoprotection
Volume 16 - 2025 | doi: 10.3389/fpls.2025.1641677
This article is part of the Research TopicInnovative Field Diagnostics for Real-Time Plant Pathogen Detection and ManagementView all 9 articles
A Precision Grading Method for Walnut Leaf Brown Spot Dis-ease Integrating Hierarchical Feature Selection and Dynamic Multi-Scale Convolution
Provisionally accepted
- Tarim University, Aral, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Brown spot disease (caused by Ophiognomonia leptostyla) is one of the most destructive fungal diseases in walnut cultivation. Precise grading of plant diseases remains a core technical challenge in the development of smart agriculture. Aiming at the issues of blurred edges and inefficient extraction of complex features in walnut leaf brown spot disease, which hinder accurate grading, this study proposes a disease grading method integrating hierarchical feature selection and adaptive multi-scale dilated convolution fusion. The designed CogFuse-MobileViT model addresses the limitations of the standard MobileViTv3 in capturing blurred edges of tiny lesions through three innovative modules. Specifically, the HFSM module enables hierarchical feature screening; combined with the ECFM module, it enhances the focus on edge features; and the AMSDIDCM module realizes dynamic multi-scale fusion of lesion textures and global structures. Experimental results demonstrate that the model achieves an accuracy of 86.61% on the test set, which is 7.8 percentage points higher than the original model and significantly outperforms mainstream models. This study confirms that the proposed model can effectively achieve accurate grading of walnut leaf brown spot disease.
Keywords: Walnut1, Brown Spot Disease (Ophiognomonia leptostyla)2, Hierarchical FeatureSelection3, Edge Features Perception4, Adaptive Multi-Scale Dilated Convolution5, Disease Grading 6
Received: 05 Jun 2025; Accepted: 09 Sep 2025.
Copyright: © 2025 Wei, Zeng and zheng. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Liangfang zheng, Tarim University, Aral, China
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.