Scholarlink

<p>Micro defects, such as casting pores in industrial products, have been detected by human visual inspection using X-ray CT images and image processing tools. Although recent deep model-based methods achieve high anomaly detection performances, the detection of micro defects is challenging because metrics for anomaly detection are dominated by low-frequency information. To overcome the problem, we propose introducing frequency-dependent losses to capture reconstruction errors appearing around micro defects and frequency-dependent data augmentation to improve the sensitivity against the errors. We demonstrate the effectiveness of the proposed method through experiments with MVTec AD dataset especially on the detection of micro defects.</p>

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

FIRE-AD: frequency-dependent image reconstruction error for micro defect detection

  • 期刊论文

  • 发表日期：

    2025年6月13日

查看全文
  • Yuhei Nomura,
  • Hirotaka Hachiya

摘要

Micro defects, such as casting pores in industrial products, have been detected by human visual inspection using X-ray CT images and image processing tools. Although recent deep model-based methods achieve high anomaly detection performances, the detection of micro defects is challenging because metrics for anomaly detection are dominated by low-frequency information. To overcome the problem, we propose introducing frequency-dependent losses to capture reconstruction errors appearing around micro defects and frequency-dependent data augmentation to improve the sensitivity against the errors. We demonstrate the effectiveness of the proposed method through experiments with MVTec AD dataset especially on the detection of micro defects.