Apple leaf disease severity grading based on deep learning and the DRL-Watershed algorithm

Abstract Apple leaf diseases significantly impair the photosynthetic efficiency and growth quality of apple trees, leading to reduced fruit yields. Existing methods for disease detection and severity classification struggle to quickly and accurately segment and quantify diseased areas on leaves, par...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhifang Bi, Fumin Ma, Jiaxiong Guan, Jie Wu, Juxia Li, Fuzhong Li, Yanwen Li, Zhanli Liu
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-15246-8
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849735967838044160
author Zhifang Bi
Fumin Ma
Jiaxiong Guan
Jie Wu
Juxia Li
Fuzhong Li
Yanwen Li
Zhanli Liu
author_facet Zhifang Bi
Fumin Ma
Jiaxiong Guan
Jie Wu
Juxia Li
Fuzhong Li
Yanwen Li
Zhanli Liu
author_sort Zhifang Bi
collection DOAJ
description Abstract Apple leaf diseases significantly impair the photosynthetic efficiency and growth quality of apple trees, leading to reduced fruit yields. Existing methods for disease detection and severity classification struggle to quickly and accurately segment and quantify diseased areas on leaves, particularly in complex backgrounds. To address this issue, we propose a method for assessing the severity of apple leaf diseases based on a combination of improved HRNet and DRL-watershed algorithms. First, we selected HRNet_w32 as the backbone feature extraction network and incorporated a Normalization Attention Mechanism (NAM). Then, we combined the Dice Loss and Focal Loss functions to construct an enhanced HRNet based semantic segmentation model for pixel-level segmentation of both apple leaf and diseased regions. Furthermore, the segmented leaf and disease regions were further optimized using the DRL-watershed algorithm to distinguish overlapping leaf regions. Experimental results demonstrate that the modified HRNet model achieved a mean intersection over union (mIoU) of 88.91% and a mean pixel accuracy (mPA) of 94.13%, representing improvements of 8.77 and 7.25% points, respectively, over the original HRNet. The disease severity assessment accuracy reached 97.65%. This study not only accurately segments apple leaves and diseased areas, but also effectively addresses the impact of complex backgrounds and leaf overlap on disease severity assessment, providing a solid scientific basis for disease management strategies.
format Article
id doaj-art-7260b6be36064dff98592507ba12f749
institution DOAJ
issn 2045-2322
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-7260b6be36064dff98592507ba12f7492025-08-20T03:07:24ZengNature PortfolioScientific Reports2045-23222025-08-0115111910.1038/s41598-025-15246-8Apple leaf disease severity grading based on deep learning and the DRL-Watershed algorithmZhifang Bi0Fumin Ma1Jiaxiong Guan2Jie Wu3Juxia Li4Fuzhong Li5Yanwen Li6Zhanli Liu7Department of Basic Sciences, Shanxi Agricultural UniversityCollege of Energy and Power Engineering, Lanzhou University of TechnologyCollege of Information Science and Engineering, Shanxi Agricultural UniversityCollege of Information Science and Engineering, Shanxi Agricultural UniversityCollege of Information Science and Engineering, Shanxi Agricultural UniversitySchool of Software, Shanxi Agricultural UniversityCollege of Information Science and Engineering, Shanxi Agricultural UniversityTaiyuan Water Resources Management and Protection CenterAbstract Apple leaf diseases significantly impair the photosynthetic efficiency and growth quality of apple trees, leading to reduced fruit yields. Existing methods for disease detection and severity classification struggle to quickly and accurately segment and quantify diseased areas on leaves, particularly in complex backgrounds. To address this issue, we propose a method for assessing the severity of apple leaf diseases based on a combination of improved HRNet and DRL-watershed algorithms. First, we selected HRNet_w32 as the backbone feature extraction network and incorporated a Normalization Attention Mechanism (NAM). Then, we combined the Dice Loss and Focal Loss functions to construct an enhanced HRNet based semantic segmentation model for pixel-level segmentation of both apple leaf and diseased regions. Furthermore, the segmented leaf and disease regions were further optimized using the DRL-watershed algorithm to distinguish overlapping leaf regions. Experimental results demonstrate that the modified HRNet model achieved a mean intersection over union (mIoU) of 88.91% and a mean pixel accuracy (mPA) of 94.13%, representing improvements of 8.77 and 7.25% points, respectively, over the original HRNet. The disease severity assessment accuracy reached 97.65%. This study not only accurately segments apple leaves and diseased areas, but also effectively addresses the impact of complex backgrounds and leaf overlap on disease severity assessment, providing a solid scientific basis for disease management strategies.https://doi.org/10.1038/s41598-025-15246-8Leaf diseaseSemantic segmentationHRNetNAMDRL-watershed algorithmDisease severity grading
spellingShingle Zhifang Bi
Fumin Ma
Jiaxiong Guan
Jie Wu
Juxia Li
Fuzhong Li
Yanwen Li
Zhanli Liu
Apple leaf disease severity grading based on deep learning and the DRL-Watershed algorithm
Scientific Reports
Leaf disease
Semantic segmentation
HRNet
NAM
DRL-watershed algorithm
Disease severity grading
title Apple leaf disease severity grading based on deep learning and the DRL-Watershed algorithm
title_full Apple leaf disease severity grading based on deep learning and the DRL-Watershed algorithm
title_fullStr Apple leaf disease severity grading based on deep learning and the DRL-Watershed algorithm
title_full_unstemmed Apple leaf disease severity grading based on deep learning and the DRL-Watershed algorithm
title_short Apple leaf disease severity grading based on deep learning and the DRL-Watershed algorithm
title_sort apple leaf disease severity grading based on deep learning and the drl watershed algorithm
topic Leaf disease
Semantic segmentation
HRNet
NAM
DRL-watershed algorithm
Disease severity grading
url https://doi.org/10.1038/s41598-025-15246-8
work_keys_str_mv AT zhifangbi appleleafdiseaseseveritygradingbasedondeeplearningandthedrlwatershedalgorithm
AT fuminma appleleafdiseaseseveritygradingbasedondeeplearningandthedrlwatershedalgorithm
AT jiaxiongguan appleleafdiseaseseveritygradingbasedondeeplearningandthedrlwatershedalgorithm
AT jiewu appleleafdiseaseseveritygradingbasedondeeplearningandthedrlwatershedalgorithm
AT juxiali appleleafdiseaseseveritygradingbasedondeeplearningandthedrlwatershedalgorithm
AT fuzhongli appleleafdiseaseseveritygradingbasedondeeplearningandthedrlwatershedalgorithm
AT yanwenli appleleafdiseaseseveritygradingbasedondeeplearningandthedrlwatershedalgorithm
AT zhanliliu appleleafdiseaseseveritygradingbasedondeeplearningandthedrlwatershedalgorithm