Enhanced Disease Segmentation in Pear Leaves via Edge-Aware Multi-Scale Attention Network
Sensors · 14.08.2025 · 25 (16) · 5058
DOI: 10.3390/s25165058 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 14.08.2025. Verfasst von Xin Shu und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Information and Artificial Intelligence, Anhui Agricultural University, Hefei 230036, China. Hauptthemen laut MEDLINE: Pyrus, Plant Leaves, Plant Diseases, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Anhui Provincial Engineering Laboratory for Beidou Precision Agriculture Information Open Fund Project, Special Fund for Anhui Characteristic Agriculture Industry Technology System, Anhui High School Natural Science Research Project.
Abstract (Originalsprache)
Accurate segmentation of pear leaf diseases is paramount for enhancing diagnostic precision and optimizing agricultural disease management. However, variations in disease color, texture, and morphology, coupled with changes in lighting conditions and gradual disease progression, pose significant challenges. To address these issues, we propose EBMA-Net, an edge-aware multi-scale network. EBMA-Net introduces a Multi-Dimensional Joint Attention Module (MDJA) that leverages atrous convolutions to capture lesion information at different scales, enhancing the model’s receptive field and multi-scale processing capabilities. An Edge Feature Extraction Branch (EFFB) is also designed to extract and integrate edge features, guiding the network’s focus toward edge information and reducing information redundancy. Experiments on a self-constructed pear leaf disease dataset demonstrate that EBMA-Net achieves a Mean Intersection over Union (MIoU) of 86.25%, Mean Pixel Accuracy (MPA) of 91.68%, and Dice coefficient of 92.43%, significantly outperforming comparison models. These results highlight EBMA-Net’s effectiveness in precise pear leaf disease segmentation under complex conditions.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Information and Artificial Intelligence, Anhui Agricultural University, Hefei 230036, China.
- Anhui Beidou Precision Agriculture Information Engineering Research Center, Anhui Agricultural University, Hefei 230036, China.
ORCID-Profile: Yunzhi Wu
Förderung
- Anhui Provincial Engineering Laboratory for Beidou Precision Agriculture Information Open Fund Project
- Special Fund for Anhui Characteristic Agriculture Industry Technology System
- Anhui High School Natural Science Research Project
Zitieren
APA
Shu, X., Ding, J., Wang, W., Jiao, Y., & Wu, Y. (2025). Enhanced Disease Segmentation in Pear Leaves via Edge-Aware Multi-Scale Attention Network. Sensors, 25(16), 5058. https://doi.org/10.3390/s25165058
Vancouver
Shu X, Ding J, Wang W, Jiao Y, Wu Y. Enhanced Disease Segmentation in Pear Leaves via Edge-Aware Multi-Scale Attention Network. Sensors. 2025;25(16):5058. doi:10.3390/s25165058
BibTeX
@article{Shu2025,
author = {Shu, Xin and Ding, Jie and Wang, Wenyu and Jiao, Yuxuan and Wu, Yunzhi},
title = {Enhanced Disease Segmentation in Pear Leaves via Edge-Aware Multi-Scale Attention Network},
journal = {Sensors},
year = {2025},
volume = {25},
number = {16},
pages = {5058},
doi = {10.3390/s25165058}
}
EUVIMED