EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Vision-Based Topology-Consistent Structural Parsing of Hand-Drawn Circuit Diagrams

Haoyu Wang iD, Yuhan Wu, Xiaoming Liu iD, Wen Li

Sensors · 29.05.2026 · 26 (11) · 3440

DOI: 10.3390/s26113440 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 29.05.2026. Verfasst von Haoyu Wang und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic Engineering, Nanjing Forestry University, No. 159 Longpan Road, Nanjing 210037, China. Die Arbeit nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Hand-drawn circuit diagrams remain common in education, maintenance, and early-stage design and are often photographed for storage, sharing, and reuse. Recovering electrically meaningful structure from such camera-acquired images is difficult because irregular strokes, wire discontinuities, crossings, symbol–text interference, and imaging artifacts can disrupt valid circuit topology. We therefore formulate the task as topology recovery with semantic completion rather than symbol recognition alone. To solve it, we propose a topology-consistent structural parsing framework that integrates multi-source visual perception, wire connected-component-guided connectivity reasoning, and explicit endpoint semantic recovery for direction-sensitive and multi-terminal components. On an independent benchmark of 1317 hand-drawn circuit diagrams, the proposed method achieves a 95.14% strict image-level end-to-end success rate. The recovered structures are further exported as Simulation Program with Integrated Circuit Emphasis (SPICE)-compatible netlists for downstream simulation and verification. These results support a practical vision-based image acquisition and processing workflow for converting camera-acquired hand-drawn circuit images into machine-readable and simulation-ready circuit representations.

Schlagwörter

Stichwörter der Autor:innen

SPICE netlist generationcamera-acquired imagescircuit digitizationhand-drawn circuit diagramsimage acquisition and processingsensing and imagingstructural parsingtopology recoveryvision-based sensing

Autor:innen und Institutionen

  • School of Electronic Engineering, Nanjing Forestry University, No. 159 Longpan Road, Nanjing 210037, China.
  • Postdoctoral Scientific Research Workstation, Nantong Youxing Wiring Harness Co., Ltd., Nantong 226000, China.
  • School of Computer Science, Nanjing Audit University, No. 86 Yushan West Road, Nanjing 211815, China.

ORCID-Profile: Haoyu Wang, Xiaoming Liu

Zitieren

APA

Wang, H., Wu, Y., Liu, X., & Li, W. (2026). Vision-Based Topology-Consistent Structural Parsing of Hand-Drawn Circuit Diagrams. Sensors, 26(11), 3440. https://doi.org/10.3390/s26113440

Vancouver

Wang H, Wu Y, Liu X, Li W. Vision-Based Topology-Consistent Structural Parsing of Hand-Drawn Circuit Diagrams. Sensors. 2026;26(11):3440. doi:10.3390/s26113440

BibTeX
@article{Wang2026,
  author = {Wang, Haoyu and Wu, Yuhan and Liu, Xiaoming and Li, Wen},
  title = {Vision-Based Topology-Consistent Structural Parsing of Hand-Drawn Circuit Diagrams},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {11},
  pages = {3440},
  doi = {10.3390/s26113440}
}
Kostenlos starten →