Steel Surface Defect Detection Algorithm Based on Improved YOLOv8 Modeling

Detecting steel defects is a vital process in industrial production, but traditional methods suffer from poor feature extraction and low detection accuracy. To address these issues, this research introduces an improved model, EB-YOLOv8, based on YOLOv8. First, the multi-scale attention mechanism EMA...

Full description

Saved in:
Bibliographic Details
Main Authors: Miao Peng, Sue Bai, Yang Lu
Format: Article
Language:English
Published: MDPI AG 2025-08-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/15/8759
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849407556634542080
author Miao Peng
Sue Bai
Yang Lu
author_facet Miao Peng
Sue Bai
Yang Lu
author_sort Miao Peng
collection DOAJ
description Detecting steel defects is a vital process in industrial production, but traditional methods suffer from poor feature extraction and low detection accuracy. To address these issues, this research introduces an improved model, EB-YOLOv8, based on YOLOv8. First, the multi-scale attention mechanism EMA is integrated into the backbone and neck sections to reduce noise during gradient descent and enhance model stability by encoding global information and weighting model parameters. Second, the weighted fusion splicing module, Concat_BiFPN, is used in the neck network to facilitate multi-scale feature detection and fusion. This improves detection precision. The results show that the EB-YOLOv8 model increases detection accuracy on the NEU-DET dataset by 3.1%, reaching 80.2%, compared to YOLOv8. Additionally, the average precision on the Severstal steel defect dataset improves from 65.4% to 66.1%. Overall, the proposed model demonstrates superior recognition performance.
format Article
id doaj-art-14bb01ed082b4ff8828cd091b7a7b83a
institution Kabale University
issn 2076-3417
language English
publishDate 2025-08-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-14bb01ed082b4ff8828cd091b7a7b83a2025-08-20T03:36:02ZengMDPI AGApplied Sciences2076-34172025-08-011515875910.3390/app15158759Steel Surface Defect Detection Algorithm Based on Improved YOLOv8 ModelingMiao Peng0Sue Bai1Yang Lu2Jilin Provincial Key Laboratory for Numerical Simulation, Jilin Normal University, Siping 136000, ChinaJilin Provincial Key Laboratory for Numerical Simulation, Jilin Normal University, Siping 136000, ChinaJilin Provincial Key Laboratory for Numerical Simulation, Jilin Normal University, Siping 136000, ChinaDetecting steel defects is a vital process in industrial production, but traditional methods suffer from poor feature extraction and low detection accuracy. To address these issues, this research introduces an improved model, EB-YOLOv8, based on YOLOv8. First, the multi-scale attention mechanism EMA is integrated into the backbone and neck sections to reduce noise during gradient descent and enhance model stability by encoding global information and weighting model parameters. Second, the weighted fusion splicing module, Concat_BiFPN, is used in the neck network to facilitate multi-scale feature detection and fusion. This improves detection precision. The results show that the EB-YOLOv8 model increases detection accuracy on the NEU-DET dataset by 3.1%, reaching 80.2%, compared to YOLOv8. Additionally, the average precision on the Severstal steel defect dataset improves from 65.4% to 66.1%. Overall, the proposed model demonstrates superior recognition performance.https://www.mdpi.com/2076-3417/15/15/8759YOLOv8object detectionattention mechanismBiFPNfeature fusion
spellingShingle Miao Peng
Sue Bai
Yang Lu
Steel Surface Defect Detection Algorithm Based on Improved YOLOv8 Modeling
Applied Sciences
YOLOv8
object detection
attention mechanism
BiFPN
feature fusion
title Steel Surface Defect Detection Algorithm Based on Improved YOLOv8 Modeling
title_full Steel Surface Defect Detection Algorithm Based on Improved YOLOv8 Modeling
title_fullStr Steel Surface Defect Detection Algorithm Based on Improved YOLOv8 Modeling
title_full_unstemmed Steel Surface Defect Detection Algorithm Based on Improved YOLOv8 Modeling
title_short Steel Surface Defect Detection Algorithm Based on Improved YOLOv8 Modeling
title_sort steel surface defect detection algorithm based on improved yolov8 modeling
topic YOLOv8
object detection
attention mechanism
BiFPN
feature fusion
url https://www.mdpi.com/2076-3417/15/15/8759
work_keys_str_mv AT miaopeng steelsurfacedefectdetectionalgorithmbasedonimprovedyolov8modeling
AT suebai steelsurfacedefectdetectionalgorithmbasedonimprovedyolov8modeling
AT yanglu steelsurfacedefectdetectionalgorithmbasedonimprovedyolov8modeling