Chip-Schematic-Converter

Designing integrated circuits is traditionally a complex and error-prone process, requiring expert knowledge and specialized software. Hand-drawn schematics, commonly used in early-stage design and education, are difficult to directly convert into digital formats suitable for simulation or fabrication. This project presents a machine-learning–based system that interprets handwritten circuit schematics and generates corresponding digital netlists. Using computer vision techniques, the system detects and classifies components and their interconnections, mapping them onto an X-Y plane to produce accurate, fabrication-ready outputs. Preliminary results demonstrate successful recognition of common electronic components and wire paths, significantly reducing manual transcription effort. This approach has the potential to accelerate chip prototyping, make hardware design more accessible to students and hobbyists, and serve as a foundation for further automation in electronic design workflows. Future work will focus on expanding component recognition and improving error correction capabilities.