• Home
  • Search
  • A Novel YOLOv10-Based Algorithm for Accurate Steel Surface Defect Detection.
  • Cite Icon40
  • https://doi.org/10.3390/s25030769Copy DOI Icon

A Novel YOLOv10-Based Algorithm for Accurate Steel Surface Defect Detection.

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

To address challenges like manual processes, complicated detection methods, high false alarm rates, and frequent errors in identifying defects on steel surfaces, this research presents an innovative detection system, YOLOv10n-SFDC. The study focuses on the complex dependencies between parameters used for defect detection, particularly the interplay between feature extraction, fusion, and bounding box regression, which often leads to inefficiencies in traditional methods. YOLOv10n-SFDC incorporates advanced elements such as the DualConv module, SlimFusionCSP module, and Shape-IoU loss function, improving feature extraction, fusion, and bounding box regression to enhance accuracy. Testing on the NEU-DET dataset shows that YOLOv10n-SFDC achieves a mean average precision (mAP) of 85.5% at an Intersection over Union (IoU) threshold of 0.5, a 6.3 percentage point improvement over the baseline YOLOv10. The system uses only 2.67 million parameters, demonstrating efficiency. It excels in identifying complex defects like 'rolled in scale' and 'inclusion'. Compared to SSD and Fast R-CNN, YOLOv10n-SFDC outperforms these models in accuracy while maintaining a lightweight architecture. This system excels in automated inspection for industrial environments, offering rapid, precise defect detection. YOLOv10n-SFDC emerges as a reliable solution for the continuous monitoring and quality assurance of steel surfaces, improving the reliability and efficiency of steel manufacturing processes.

Similar Papers
  • Research Article
  • Citations4190

Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression

  • Apr 03, 2020
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Zhaohui Zheng +5
  • Conference Article
  • Citations29

Rethink the IoU-based loss functions for bounding box regression

  • Dec 11, 2020
  • Hongyu Zhai +2
  • Research Article
  • Citations1

Selective feature block and joint IoU loss for object detection

  • Jul 27, 2024
  • Transactions of the Institute of Measurement and Control
  • Junyi Wang +5
  • Conference Article
  • Citations5

A Multi-Scale Defect Detection for Steel Surface Based on Improved Faster R-CNN

  • Nov 17, 2023
  • Mingjie Shen +2
  • Research Article
  • Citations70

Manhattan-distance IOU loss for fast and accurate bounding box regression and object detection

  • May 18, 2022
  • Neurocomputing
  • Yanyun Shen +4
  • Conference Article
  • Citations6

Improved Design Based on IoU Loss Functions for Bounding Box Regression

  • Oct 03, 2022
  • Zhibo Liu +3
  • PDF
  • Research Article
  • Citations50

N-IoU: better IoU-based bounding box regression loss for object detection

  • Nov 28, 2023
  • Neural Computing and Applications
  • Keke Su +5
  • PDF
  • Research Article
  • Citations56

MultiDefectNet: Multi-Class Defect Detection of Building Façade Based on Deep Convolutional Neural Network

  • Nov 23, 2020
  • Sustainability
  • Kisu Lee +4
  • Research Article

Mask-Based IoU for Bounding Box Regression Using Medical Images

  • Dec 31, 2024
  • Turkish Journal of Mathematics and Computer Science
  • Serap Çakar +5
  • Research Article

Real-time and online industrial system for detecting defects of interface surface in automobile brake pipe

  • May 09, 2025
  • Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering
  • Weiwei Gao +5
  • Research Article
  • Citations1

A benchmarking study of instance segmentation methods for photovoltaic cell defect detection using electroluminescence images

  • Jan 01, 2026
  • Solar Energy
  • Ula Hijjawi +3
  • PDF
  • Research Article
  • Citations37

Corner-Point and Foreground-Area IoU Loss: Better Localization of Small Objects in Bounding Box Regression.

  • May 22, 2023
  • Sensors (Basel, Switzerland)
  • Delong Cai +2
  • PDF
  • Research Article
  • Citations125

Object Detection in Remote Sensing Images Based on Improved Bounding Box Regression and Multi-Level Features Fusion

  • Jan 01, 2020
  • Remote Sensing
  • Xiaoliang Qian +5
  • Research Article
  • Citations21

Forest Fire Smoke Recognition Based on Anchor Box Adaptive Generation Method

  • Feb 27, 2021
  • Electronics
  • Enting Zhao +3
  • PDF
  • Research Article
  • Citations209

Comparison of Object Detection and Patch-Based Classification Deep Learning Models on Mid- to Late-Season Weed Detection in UAV Imagery

  • Jul 03, 2020
  • Remote Sensing
  • Arun Narenthiran Veeranampalayam Sivakumar +6
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.