CircuitNet

Schematic Sketch to Circuit Diagram Using Deep Learning
Interactive Colab Demo »

Project Overview

A deep learning algorithm is proposed to automatically convert schematic sketches into circuit diagrams. The algorithm is promising, achieving a detection accuracy of 90% and a classification accuracy of 96.5%.

Component Segmentation

There are a variety of feature detection algorithms possible, but we opted for traditional image processing techniques due to the inavailability of labeled data.

Classification Architecture

Software Dependancies

This project was built using the following open-source libraries:

• Numpy is an array manipulation library, used for linear algebra, Fourier transform, and random number capabilities.
• CV2 is a library for computer vision tasks.
• Skimage is a library which supports image processing applications on python.
• Matplotlib is a library which generates figures and provides graphical user interface toolkit.
• Tensorflow is an end-to-end open source machine learning platform
• SVG Schematic is a library to build a schematic using Python to instantiate and place the symbols and wires
• Cairo SVG is a library for processing SVG in python