MSPB-YOLO: High-Precision Detection Algorithm of Multi-Site Pepper Blight Disease Based on Improved YOLOv8

In response to the challenges of low accuracy in traditional pepper blight identification under natural complex conditions, particularly in detecting subtle infections on early-stage leaves, stems, and fruits. This study proposes a multi-site pepper blight disease image recognition algorithm based o...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaodong Zheng, Zichun Shao, Yile Chen, Hui Zeng, Junming Chen
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Agronomy
Subjects:
Online Access:https://www.mdpi.com/2073-4395/15/4/839
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850183838516379648
author Xiaodong Zheng
Zichun Shao
Yile Chen
Hui Zeng
Junming Chen
author_facet Xiaodong Zheng
Zichun Shao
Yile Chen
Hui Zeng
Junming Chen
author_sort Xiaodong Zheng
collection DOAJ
description In response to the challenges of low accuracy in traditional pepper blight identification under natural complex conditions, particularly in detecting subtle infections on early-stage leaves, stems, and fruits. This study proposes a multi-site pepper blight disease image recognition algorithm based on YOLOv8, named MSPB-YOLO. This algorithm effectively locates different infection sites on peppers. By incorporating the RVB-EMA module into the model, we can significantly reduce interference from shallow noise in high-resolution depth layers. Additionally, the introduction of the RepGFPN network structure enhances the model’s capability for multi-scale feature fusion, resulting in a marked improvement in multi-target detection accuracy. Furthermore, we optimized CIOU to DIOU by integrating the center distance of bounding boxes into the loss function; as a result, the model achieved an impressive mAP@0.5 score of 96.4%. This represents an enhancement of 2.2% over the original algorithm’s mAP@0.5. Overall, this model provides effective technical support for promoting intelligent management and disease prevention strategies for peppers.
format Article
id doaj-art-41bb57b31cd649938ceb2d6562f74688
institution OA Journals
issn 2073-4395
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Agronomy
spelling doaj-art-41bb57b31cd649938ceb2d6562f746882025-08-20T02:17:13ZengMDPI AGAgronomy2073-43952025-03-0115483910.3390/agronomy15040839MSPB-YOLO: High-Precision Detection Algorithm of Multi-Site Pepper Blight Disease Based on Improved YOLOv8Xiaodong Zheng0Zichun Shao1Yile Chen2Hui Zeng3Junming Chen4Faculty of Humanities and Arts, Macau University of Science and Technology, Macao 999078, ChinaFaculty of Humanities and Arts, Macau University of Science and Technology, Macao 999078, ChinaFaculty of Humanities and Arts, Macau University of Science and Technology, Macao 999078, ChinaSchool of Design, Jiangnan University, Wuxi 214122, ChinaFaculty of Humanities and Arts, Macau University of Science and Technology, Macao 999078, ChinaIn response to the challenges of low accuracy in traditional pepper blight identification under natural complex conditions, particularly in detecting subtle infections on early-stage leaves, stems, and fruits. This study proposes a multi-site pepper blight disease image recognition algorithm based on YOLOv8, named MSPB-YOLO. This algorithm effectively locates different infection sites on peppers. By incorporating the RVB-EMA module into the model, we can significantly reduce interference from shallow noise in high-resolution depth layers. Additionally, the introduction of the RepGFPN network structure enhances the model’s capability for multi-scale feature fusion, resulting in a marked improvement in multi-target detection accuracy. Furthermore, we optimized CIOU to DIOU by integrating the center distance of bounding boxes into the loss function; as a result, the model achieved an impressive mAP@0.5 score of 96.4%. This represents an enhancement of 2.2% over the original algorithm’s mAP@0.5. Overall, this model provides effective technical support for promoting intelligent management and disease prevention strategies for peppers.https://www.mdpi.com/2073-4395/15/4/839pepper blightYOLOmulti-site detectionRepGFPNdisease prevention strategies
spellingShingle Xiaodong Zheng
Zichun Shao
Yile Chen
Hui Zeng
Junming Chen
MSPB-YOLO: High-Precision Detection Algorithm of Multi-Site Pepper Blight Disease Based on Improved YOLOv8
Agronomy
pepper blight
YOLO
multi-site detection
RepGFPN
disease prevention strategies
title MSPB-YOLO: High-Precision Detection Algorithm of Multi-Site Pepper Blight Disease Based on Improved YOLOv8
title_full MSPB-YOLO: High-Precision Detection Algorithm of Multi-Site Pepper Blight Disease Based on Improved YOLOv8
title_fullStr MSPB-YOLO: High-Precision Detection Algorithm of Multi-Site Pepper Blight Disease Based on Improved YOLOv8
title_full_unstemmed MSPB-YOLO: High-Precision Detection Algorithm of Multi-Site Pepper Blight Disease Based on Improved YOLOv8
title_short MSPB-YOLO: High-Precision Detection Algorithm of Multi-Site Pepper Blight Disease Based on Improved YOLOv8
title_sort mspb yolo high precision detection algorithm of multi site pepper blight disease based on improved yolov8
topic pepper blight
YOLO
multi-site detection
RepGFPN
disease prevention strategies
url https://www.mdpi.com/2073-4395/15/4/839
work_keys_str_mv AT xiaodongzheng mspbyolohighprecisiondetectionalgorithmofmultisitepepperblightdiseasebasedonimprovedyolov8
AT zichunshao mspbyolohighprecisiondetectionalgorithmofmultisitepepperblightdiseasebasedonimprovedyolov8
AT yilechen mspbyolohighprecisiondetectionalgorithmofmultisitepepperblightdiseasebasedonimprovedyolov8
AT huizeng mspbyolohighprecisiondetectionalgorithmofmultisitepepperblightdiseasebasedonimprovedyolov8
AT junmingchen mspbyolohighprecisiondetectionalgorithmofmultisitepepperblightdiseasebasedonimprovedyolov8