EUVIMEDEUVIMED entdecken
Open Access

RulerNet: Learning perspective-invariant ruler representations for robust image scale estimation

Yimu Pan, Manas Mehta, Gwen Sincerbeaux, Jeffery A Goldstein, Alison D Gernand, James Z Wang

Computerized Medical Imaging and Graphics · 2026-08 · 134 · 102805

DOI: 10.1016/j.compmedimag.2026.102805 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computerized Medical Imaging and Graphics, 2026-08. Verfasst von Yimu Pan und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Informatics and Intelligent Systems, College of Information Sciences and Technology, The Pennsylvania State University, University Park…. Hauptthemen laut MEDLINE: Deep Learning, Image Processing, Computer-Assisted. Die Arbeit nennt 80 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIBIB NIH HHS, Burroughs Wellcome Fund, National Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurately converting pixel measurements into absolute real-world dimensions remains a fundamental challenge in computer vision, limiting progress in applications such as biomedicine, forensics, nutritional analysis, and e-commerce. We introduce RulerNet, a deep learning framework that robustly infers scale in the wild by reformulating ruler reading as a unified keypoint detection problem and representing rulers with geometric progression parameters that compactly approximate the non-uniform spacing induced by perspective transformations. Unlike traditional methods that rely on handcrafted thresholds or rigid, ruler-specific pipelines, RulerNet directly localizes centimeter markings using a mark-visibility-based annotation and training strategy that remains valid under mark-preserving transformations, enabling strong generalization across diverse ruler types and imaging conditions while mitigating data scarcity. Additionally, we introduce a scalable synthetic data generation pipeline that combines graphics-based ruler creation with ControlNet-enhanced realism, significantly expanding training diversity and improving model performance. Extensive experiments on both our datasets and public benchmarks demonstrate that RulerNet achieves accurate, consistent, and efficient scale estimation under challenging real-world conditions. Integration into a medical analysis pipeline further demonstrates its practical utility for scale-aware measurement. These results suggest that RulerNet can serve as a generalizable measurement component and be readily integrated with other vision modules, such as segmentation, monocular depth estimation, and diagnostic workflows, for automated analysis in medical and other domains. An online demo is provided. The code and data are publicly released with the paper.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningImage Processing, Computer-AssistedHumansAlgorithms

Stichwörter der Autor:innen

AI-assisted measurementRuler readingScale estimationSynthetic data generation

Autor:innen und Institutionen

  • Department of Informatics and Intelligent Systems, College of Information Sciences and Technology, The Pennsylvania State University, University Park, 16802, PA, USA. Electronic address: ymp5078@psu.edu.
  • Department of Informatics and Intelligent Systems, College of Information Sciences and Technology, The Pennsylvania State University, University Park, 16802, PA, USA.
  • Department of Nutritional Sciences, College of Health and Human Development, The Pennsylvania State University, University Park, 16802, PA, USA.
  • Department of Pathology, Feinberg School of Medicine, Northwestern University, Chicago, 60611, IL, USA.
  • Department of Informatics and Intelligent Systems, College of Information Sciences and Technology, The Pennsylvania State University, University Park, 16802, PA, USA. Electronic address: jwang@ist.psu.edu.

Förderung

  • NIBIB NIH HHS
  • Burroughs Wellcome Fund
  • National Science Foundation
  • National Institute of Biomedical Imaging and Bioengineering

Zitieren

APA

Pan, Y., Mehta, M., Sincerbeaux, G., Goldstein, J. A., Gernand, A. D., & Wang, J. Z. (2026). RulerNet: Learning perspective-invariant ruler representations for robust image scale estimation. Computerized Medical Imaging and Graphics, 134, 102805. https://doi.org/10.1016/j.compmedimag.2026.102805

Vancouver

Pan Y, Mehta M, Sincerbeaux G, Goldstein JA, Gernand AD, Wang JZ. RulerNet: Learning perspective-invariant ruler representations for robust image scale estimation. Computerized Medical Imaging and Graphics. 2026;134:102805. doi:10.1016/j.compmedimag.2026.102805

BibTeX
@article{Pan2026,
  author = {Pan, Yimu and Mehta, Manas and Sincerbeaux, Gwen and Goldstein, Jeffery A and Gernand, Alison D and Wang, James Z},
  title = {RulerNet: Learning perspective-invariant ruler representations for robust image scale estimation},
  journal = {Computerized Medical Imaging and Graphics},
  year = {2026},
  volume = {134},
  pages = {102805},
  doi = {10.1016/j.compmedimag.2026.102805}
}
Kostenlos starten →