SINA: A Circuit Schematic Image-to-Netlist Generator Using Artificial Intelligence

2026-01-29

AI Summary

This work proposes an end-to-end automated system to address the challenges of inaccurate component recognition and connectivity inference in the conversion of circuit schematic images into machine-readable netlists. The approach synergistically integrates deep learning, connected-component labeling (CCL), optical character recognition (OCR), and a vision-language model (VLM). Notably, it pioneers the use of VLM for component label assignment, enabling more reliable semantic understanding of schematic elements. Through the coordinated application of these complementary techniques, the system achieves high-fidelity netlist generation. Experimental results demonstrate an overall accuracy of 96.47%, representing a 2.72-fold improvement over the current state-of-the-art method.

Technology Category

• Computer Vision: Language and Vision
• Machine Learning: Probabilistic Circuits and Graphical Models
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Current methods for converting circuit schematic images into machine-readable netlists struggle with component recognition and connectivity inference. In this paper, we present SINA, an open-source, fully automated circuit schematic image-to-netlist generator. SINA integrates deep learning for accurate component detection, Connected-Component Labeling (CCL) for precise connectivity extraction, and Optical Character Recognition (OCR) for component reference designator retrieval, while employing a Vision-Language Model (VLM) for reliable reference designator assignments. In our experiments, SINA achieves 96.47% overall netlist-generation accuracy, which is 2.72x higher than state-of-the-art approaches.

Problem

• circuit schematic
• netlist generation
• component recognition
• connectivity inference
• image-to-netlist

Innovation

• deep learning
• Connected-Component Labeling
• Optical Character Recognition
• Vision-Language Model
• netlist generation