Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 18, 2025Applied SciencesOpen Access

Performance Evaluation and Misclassification Distribution Analysis of Pre-Trained Lightweight CNN Models for Hot-Rolled Steel Strip Surface Defect Classification Under Degraded Imaging Conditions

View Full Paper
Ask AI
Bookmark
Share

Authors

MGMurat Alparslan Güngör

Discussion

Loading...

Member takes

Overview

Analysis reveals MobileNet models improve surface defect classification in hot-rolled steel strips, highlighting misclassification patterns.

Key Points

  • MobileNet-V1 is identified as the most effective lightweight CNN model for classifying surface defects.
  • Evaluation of six state-of-the-art CNN architectures highlights their performance under degraded imaging conditions.
  • A new performance metric allows for assessing misclassification distribution, facilitating model improvement.
  • The study emphasizes that performance on degraded images reduces reliance on image preprocessing techniques.

Cite This Study

Murat Alparslan Güngör (2025) studied this question.

synapsesocial.com/papers/68d463f131b076d99fa6369fhttps://doi.org/10.3390/app151810176
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. 1Performance evaluation of CNN models for steel surface defect detection in lean manufacturing2025 · 3 citations
  2. 2Evaluating the Detection Performance of Different Convolutional Neural Network Models for Steel Surface Defects2025
  3. 3Classification of Surface Defects in Steel Sheets Using Developed NasNet-Mobile CNN and Few Samples2024 · 4 citations
  4. 4MobileSteelNet: A Lightweight Steel Surface Defect Classification Network with Cross-Interactive Efficient Multi-Scale Attention2026
  5. 5A Lightweight Model for Hot-Rolled Steel Strip Surface Defect Recognition2026