Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
October 3, 2025Open Access

LabelImg: CNN-Based Surface Defect Detection

View Full Paper
Ask AI
Bookmark
Share

Authors

MIMohsen Asghari IlaniYBYaser Mike Banad

Discussion

Loading...

Member takes

Overview

This deep learning method identifies surface defects in laser powder bed fusion, enhancing production quality.

Key Points

  • The CNN model achieved 99.54% accuracy in detecting various surface defects.
  • Evaluation metrics for true tests show precision of over 96%, with recall and F1 scores exceeding 97%.
  • The deep learning approach requires less processing time than traditional machine learning methods.
  • Using the LabelImg tool, 14,982 labeled images were manually annotated for training and testing the algorithm.

Cite This Study

Ilani et al. (2025) studied this question.

synapsesocial.com/papers/68e02f3cf0e39f13e7fa2562https://doi.org/10.48550/arxiv.2509.05813
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. 1CNN-based Labelled Crack Detection for Image Annotation2024 · 4 citations
  2. 2Advancing Crack Detection Using Deep Learning Solutions for Automated Inspection of Metallic Surfaces2024 · 10 citations
  3. 3Designing an Intelligent Defect Detection Process by Convolutional Neural Networks2026
  4. 4Learning-Based Approach for Automated Surface Inspection with Industrial Tomography Imaging2024 · 7 citations
  5. 5An Integrated AI Automating Inspection Model for Surface Defect Segmentation and Classification in Construction Domain2026