.png){kind=icon}
.png){kind=icon}
Return
A novel context-adaptive multi-scale defect detection method for object surface defects
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2025.130927.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A new feature pyramid structure called context and texture-extractor module with feature pyramid network (CTM-FPN) has been designed. • A post-processing method called adaptive threshold soft non-maximum suppression (ATS-NMS) is proposed. • A novel context-adaptive multi-scale defect detection (CAMDD) method is proposed. • The CAMDD method proposed in this paper is applied to surface defect detection of tiny transparent lenses. • The experimental results demonstrate that the proposed method effectively detects multi-scale defects.
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W
Organization
No organization information available