.png){kind=icon}
.png){kind=icon}
Return
Novel attention-based phase-feature correlation fusion network for three-dimensional super-resolution thermographic visualization of delamination defects in carbon fiber composite laminates
.png){kind=icon}
PRE
AI
D
Y
J
J
E
K
H
Z
DOI：10.1016/j.optlaseng.2026.109844.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Novel attention-based phase-feature correlation fusion network is proposed. • Multi-scale feature extractor module and group feature interaction mechanism are designed. • Lightweight feature transformation and residual connection and three-level cascading architecture are designed. • A quantitative comparative analysis of the SSIM, PSNR, and DR, is also conducted. • The proposed method can achieve 3D super-resolution visualization of small-size delamination defects.
Keywords:
attention-based network
phase-feature correlation
super-resolution
delamination defects
carbon fiber composites
Journal
IF:
3.7
Papers:
7.1K
Citations:
1.7W
Organization
Cited Papers