arXiv cs.AI· Mohammad Kawsar, Al Amin Islam Ridoy, Md Rakib Hossain, Farzana Akter, AKM Bahalul Haque, Rejwan Bin Sulaiman, Mohammed Amin Almaiah·· 13 小时前AI 评分31
Sketch2Sim：手绘电路图端到端模块化分析框架
Sketch2Sim: an end-to-end modular framework for hand-drawn circuit analysis
AI 导读
Sketch2Sim 将手绘电路照片转换为可执行的 SPICE 兼容网表，并自动计算节点电压与电流。系统采用双 YOLO 检测器识别元件与文本区域，结合 CRNN+CTC 与 OCR 提取符号数值，再用阈值化、骨架化和 DBSCAN 自动识别节点并映射元件。研究构建了 1,000 个手绘 RLC 电路数据集，消融与端到端测试显示其在多种书写风格和光照条件下表现稳健。
正文 · 原文
Abstract:This study proposes a sketch-to-simulation system to solve handwritten circuit diagrams. The system converts raw images into a Simulation Program with Integrated Circuit Emphasis (SPICE)-compatible netlist and automatically calculates the circuit's nodal voltages and currents. Another objective is to propose a holistic framework that benefits students and educators by enhancing the teaching and learning experience of electric circuits and expediting engineering design reviews. This article presents a multistage pipeline that converts raw photographs of handwritten electric circuits into executable SPICE-like netlists, providing a solution. A dataset of 1,000 hand-drawn Resistor-Inductor-Capacitor (RLC) circuits was curated and annotated for components, text regions, and character recognition. The proposed system decomposes a circuit diagram into three stages: (i) dual You Only Look Once (YOLO)-based detectors for components and text regions, (ii) a Convolutional Recurrent Neural Network (CRNN) with Connectionist Temporal Classification (CTC) and Optical Character Recognition (OCR)-based domain-aware symbol value extraction, and (iii) image processing with thresholding, skeletonization, and Density-Based Spatial Clustering of Applications with Noise (DBSCAN) to automatically identify nodes and map them with corresponding components. The proposed system produces the netlist and solves the circuit. The qualitative and quantitative ablation studies on modular stages, as well as end-to-end tests, demonstrate robust performance across various handwriting styles, lighting conditions, and this http URL study serves as an interactive learning aid and practical tool for professionals, providing a comprehensive user interface (UI), enabling rapid digitization of circuit sketches for study, design, prototyping, or troubleshooting.
| Subjects: | Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.28836 [cs.AI] |
| (or arXiv:2610.28836v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.28836 arXiv-issued DOI via DataCite (pending registration) |
|
| Related DOI: | https://doi.org/10.7717/peerj-cs.4103
DOI(s) linking to related resources |
Submission history
From: AKM Bahalul Haque [view email]
[v1]
Tue, 20 Oct 2026 19:04:12 UTC (20,479 KB)
来源：arXiv cs.AI · arxiv.org