GEB-YOLO: Optimized YOLOv7 Model for Surface Defect Detection on Aluminum Profiles

In recent years, achieving high-precision and high-speed target detection of surface defects on aluminum profiles to meet the requirements of industrial applications has been challenging. In this paper, the GEB-YOLO is proposed based on the YOLOv7 algorithm. First, the global attention mechanism (GA...

Full description

Saved in:
Bibliographic Details
Main Authors: Zihao Xu, Jinran Hu, Xingyi Xiao, Yujian Xu
Format: Article
Language:English
Published: MDPI AG 2024-09-01
Series:Engineering Proceedings
Subjects:
Online Access:https://www.mdpi.com/2673-4591/75/1/28
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850090077091266560
author Zihao Xu
Jinran Hu
Xingyi Xiao
Yujian Xu
author_facet Zihao Xu
Jinran Hu
Xingyi Xiao
Yujian Xu
author_sort Zihao Xu
collection DOAJ
description In recent years, achieving high-precision and high-speed target detection of surface defects on aluminum profiles to meet the requirements of industrial applications has been challenging. In this paper, the GEB-YOLO is proposed based on the YOLOv7 algorithm. First, the global attention mechanism (GAM) is introduced, highlighting defect features. Second, the Explicit Visual Center Block (EVCBlock) is integrated into the network for key information extraction. Meanwhile, the BiFPN network structure is adopted to enhance feature fusion. The ablation experiments have demonstrated that the defect detection accuracy of the GEB-YOLO model is improved by 6.3%, and the speed is increased by 15% compared to the YOLOv7 model.
format Article
id doaj-art-e0f89c3e24224296adf752aaf98494bd
institution DOAJ
issn 2673-4591
language English
publishDate 2024-09-01
publisher MDPI AG
record_format Article
series Engineering Proceedings
spelling doaj-art-e0f89c3e24224296adf752aaf98494bd2025-08-20T02:42:38ZengMDPI AGEngineering Proceedings2673-45912024-09-017512810.3390/engproc2024075028GEB-YOLO: Optimized YOLOv7 Model for Surface Defect Detection on Aluminum ProfilesZihao Xu0Jinran Hu1Xingyi Xiao2Yujian Xu3College of Mechanical and Electrical Engineering, Wenzhou University, Wenzhou 325035, ChinaCollege of Mechanical and Electrical Engineering, Wenzhou University, Wenzhou 325035, ChinaCollege of Mechanical and Electrical Engineering, Wenzhou University, Wenzhou 325035, ChinaCollege of Mechanical and Electrical Engineering, Wenzhou University, Wenzhou 325035, ChinaIn recent years, achieving high-precision and high-speed target detection of surface defects on aluminum profiles to meet the requirements of industrial applications has been challenging. In this paper, the GEB-YOLO is proposed based on the YOLOv7 algorithm. First, the global attention mechanism (GAM) is introduced, highlighting defect features. Second, the Explicit Visual Center Block (EVCBlock) is integrated into the network for key information extraction. Meanwhile, the BiFPN network structure is adopted to enhance feature fusion. The ablation experiments have demonstrated that the defect detection accuracy of the GEB-YOLO model is improved by 6.3%, and the speed is increased by 15% compared to the YOLOv7 model.https://www.mdpi.com/2673-4591/75/1/28target detectionsurface defectsGEB-YOLOattention mechanismBiFPN
spellingShingle Zihao Xu
Jinran Hu
Xingyi Xiao
Yujian Xu
GEB-YOLO: Optimized YOLOv7 Model for Surface Defect Detection on Aluminum Profiles
Engineering Proceedings
target detection
surface defects
GEB-YOLO
attention mechanism
BiFPN
title GEB-YOLO: Optimized YOLOv7 Model for Surface Defect Detection on Aluminum Profiles
title_full GEB-YOLO: Optimized YOLOv7 Model for Surface Defect Detection on Aluminum Profiles
title_fullStr GEB-YOLO: Optimized YOLOv7 Model for Surface Defect Detection on Aluminum Profiles
title_full_unstemmed GEB-YOLO: Optimized YOLOv7 Model for Surface Defect Detection on Aluminum Profiles
title_short GEB-YOLO: Optimized YOLOv7 Model for Surface Defect Detection on Aluminum Profiles
title_sort geb yolo optimized yolov7 model for surface defect detection on aluminum profiles
topic target detection
surface defects
GEB-YOLO
attention mechanism
BiFPN
url https://www.mdpi.com/2673-4591/75/1/28
work_keys_str_mv AT zihaoxu gebyolooptimizedyolov7modelforsurfacedefectdetectiononaluminumprofiles
AT jinranhu gebyolooptimizedyolov7modelforsurfacedefectdetectiononaluminumprofiles
AT xingyixiao gebyolooptimizedyolov7modelforsurfacedefectdetectiononaluminumprofiles
AT yujianxu gebyolooptimizedyolov7modelforsurfacedefectdetectiononaluminumprofiles