Home

Awesome

<div align="center"> <a href="https://github.com/aaanthonyyy"> <img src="CircuitNet-Logo-01.svg" alt="Logo" width="200" height="200"> </a> <h3 align="center">CircuitNet</h3> <p align="center"> Schematic Sketch to Circuit Diagram Using Deep Learning <br/> <a href="https://colab.research.google.com/drive/1ox4m12Oa3GjwP47UdRArwCaUXbgUSLBf?authuser=2"><strong>Interactive Colab Demo »</strong></a> </p> </div>

Project Overview

<div align="center"> <img src="https://user-images.githubusercontent.com/43044255/170146864-9e7f77e7-fd16-4c4e-9d26-26639a7e9c37.png" alt="Logo" width="600"/> </div>

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%.

<br/> <br/>

Component Segmentation

<div align="center"> <img src="https://user-images.githubusercontent.com/43044255/170148823-b921898d-1d6a-457b-8dfa-ffa2ad8d0ea7.png" alt="Logo" width="600"/> <br/> <br/> </div> There are a variety of feature detection algorithms possible, but we opted for traditional image processing techniques due to the inavailability of labeled data. <br/> <br/>

Classification Architecture

<div align="center"> <img src="https://user-images.githubusercontent.com/43044255/170149446-d57c13f0-3ab0-4542-86c9-8a7093d11627.png" alt="Logo" width="600"/> <br/> <br/> </div>

Software Dependancies

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