Sketch2Sim: an end-to-end modular framework for hand-drawn circuit analysis
Title: Sketch2Sim: an end-to-end modular framework for hand-drawn circuit analysis
标题：Sketch2Sim：一种用于手绘电路分析的端到端模块化框架
Computer Science > Artificial Intelligence arXiv:2610.28836 (cs) [Submitted on 20 Oct 2026] Title:Sketch2Sim: an end-to-end modular framework for hand-drawn circuit analysis Authors:Mohammad Kawsar, Al Amin Islam Ridoy, Md Rakib Hossain, Farzana Akter, AKM Bahalul Haque, Rejwan Bin Sulaiman, Mohammed Amin Almaiah View a PDF of the paper titled Sketch2Sim: an end-to-end modular framework for hand-drawn circuit analysis, by Mohammad Kawsar and 6 other authors View PDF
计算机科学 > 人工智能 arXiv:2610.28836 (cs) [提交于 2026 年 10 月 20 日] 标题：Sketch2Sim：一种用于手绘电路分析的端到端模块化框架 作者：Mohammad Kawsar, Al Amin Islam Ridoy, Md Rakib Hossain, Farzana Akter, AKM Bahalul Haque, Rejwan Bin Sulaiman, Mohammed Amin Almaiah 查看由 Mohammad Kawsar 等 7 位作者撰写的论文《Sketch2Sim：一种用于手绘电路分析的端到端模块化框架》的 PDF 版本。
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.
摘要：本研究提出了一种用于求解手绘电路图的“草图转仿真”系统。该系统将原始图像转换为与集成电路重点仿真程序（SPICE）兼容的网表，并自动计算电路的节点电压和电流。另一个目标是提出一个整体框架，通过改善电路的教学体验并加快工程设计审查，使学生和教育工作者受益。
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.
本文介绍了一种多阶段流水线，它将手绘电路的原始照片转换为可执行的类 SPICE 网表，从而提供了一种解决方案。研究人员整理并标注了一个包含 1,000 个手绘电阻-电感-电容（RLC）电路的数据集，涵盖了组件、文本区域和字符识别。
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.
该系统将电路图分解为三个阶段：（i）基于双“你只看一次”（YOLO）的组件和文本区域检测器；（ii）结合连接时序分类（CTC）的卷积递归神经网络（CRNN）以及基于光学字符识别（OCR）的领域感知符号值提取；（iii）通过阈值处理、骨架化和基于密度的噪声应用空间聚类（DBSCAN）进行图像处理，以自动识别节点并将其与相应组件映射。
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.
该系统生成网表并求解电路。针对模块化阶段的定性和定量消融研究以及端到端测试表明，该系统在各种书写风格、光照条件和此 URL 下均表现出稳健的性能。本研究旨在作为一种交互式学习辅助工具和专业人员的实用工具，提供全面的用户界面（UI），实现电路草图的快速数字化，以用于学习、设计、原型制作或故障排除。