Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
June 14, 2026Journal of ImagingOpen Access

Edge-Enhance YOLO for Steel Surface Defect Detection

View Full Paper
Ask AI
Bookmark
Share

Authors

RLRenfei LiMinistry of TransportMLMingxiu LinNortheastern University

Discussion

Loading...

Member takes

Overview

Randomized trial shows improved edge-detection in steel defects, suggesting enhanced manufacturing quality.

Key Points

  • The research aims to improve defect detection in steel manufacturing by enhancing edge sensitivity in YOLO-style detectors.
  • Proposed a YOLO-based framework called EDEN-YOLO with an Edge-Enhance module.
  • Incorporated Local Feature Enhancement and Gated Module to improve edge responses.
  • Evaluated performance on NEU-DET and GC10-DET datasets.
  • EDEN-YOLO achieved 80.5% mAP@0.5 on NEU-DET, improving over YOLOv8 baseline.
  • The model introduced a complexity increase of 0.52M parameters and 1.3 GFLOPs.
  • On GC10-DET, EDEN-YOLO attained 65.2% mAP@0.5, surpassing the 61.0% of YOLOv8.

Cite This Study

Li et al. (2026) studied this question.

synapsesocial.com/papers/6a2e45d5b1cc60ccdea8ac5chttps://doi.org/10.3390/jimaging12060259
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1A light weight multi-scale feature fusion steel surface defect detection model based on YOLOv82024 · 80 citations
  2. 2UEDG:Uncertainty-Edge Dual Guided Camouflage Object Detection2023 · 100 citations
  3. 3You Only Look Once: Unified, Real-Time Object Detection2016 · 51,533 citations
  4. 4MESC-DETR: An Improved RT-DETR Algorithm for Steel Surface Defect Detection2025 · 13 citations
  5. 5LFF-YOLO: A YOLO Algorithm With Lightweight Feature Fusion Network for Multi-Scale Defect Detection2022 · 89 citations