Scholarlink

Effective quality control of materials is critical in manufacturing, preventing damaged products that inflate costs and hinder performance. To this end, thermography and deep learning have emerged as powerful tools for defect detection and identification in various material types. Combining these two technologies offers several benefits, including enhanced accuracy, speed, and efficiency in detecting and classifying defects. Therefore, this study provides a short review of the existing deep leaning models used to solve one of the most challenging problems in the manufacturing field, which is defect identification.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Deep Learning-Based Defect Detection and Identification from Thermography Data

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Zoheir Mentouri,
  • Kaddour Gherfi,
  • Abdelmalek Bouguettaya,
  • Rachid Zaghdoudi

摘要

Effective quality control of materials is critical in manufacturing, preventing damaged products that inflate costs and hinder performance. To this end, thermography and deep learning have emerged as powerful tools for defect detection and identification in various material types. Combining these two technologies offers several benefits, including enhanced accuracy, speed, and efficiency in detecting and classifying defects. Therefore, this study provides a short review of the existing deep leaning models used to solve one of the most challenging problems in the manufacturing field, which is defect identification.