.png){kind=icon}
.png){kind=icon}
Return
RulerNet: Learning perspective-invariant ruler representations for robust image scale estimation
.png){kind=icon}
PRE
AI
Y
M
G
J
A
J
DOI：10.1016/j.compmedimag.2026.102805.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Reformulates ruler reading as centimeter-mark keypoint detection with GP-based perspective-robust scale recovery. • Introduces mark-visibility annotations and training for diverse ruler imagery. • Proposes a fast, feed-forward geometric progression regression model. • Validates scale estimation across diverse rulers and in a medical image pipeline.
Journal
IF:
4.9
Papers:
2.4K
Citations:
5.0K
Organization
Cited Papers