Contact Me

AI Mentorship Project

CircuitSeer

Project Details
BG

  • Kushagra Bharti

  • Nishant Bhagat

  • Sahishnu Sagiraju

  • Ethan Ung

  • Sreevasan Sivasubramanian

  • Yuvraj Kashyap

Acknowledgments

I would like to acknowledge my mentees for their invaluable contributions to this project: Kushagra Bharti, Nishant Bhagat, Sahishnu Sagiraju, Ethan Ung, Sreevasan Sivasubramanian, and Yuvraj Kashyap. Your dedication and hard work have been instrumental in our success.

I would also like to extend my gratitude to the AI Mentorship Program at the University of Texas at Dallas for providing the guidance and resources necessary to make this project possible.

 

Feel free to check out my github for more info on our code.

BG

What does it do?

Welcome to CircuitSeer — the innovative outcome of a dedicated student project under the AI Mentorship Program at the University of Texas at Dallas. CircuitSeer is your go-to AI-powered tool for analyzing and solving electronic circuits with precision and ease. Developed by a team of ambitious students, this tool utilizes advanced object detection technology to identify circuit components, trace wiring, and generate schematic analyses.

Designed with both educational and practical applications in mind, CircuitSeer is perfect for students who are learning the ropes of electronic circuit design or for those who need a reliable assistant in checking their homework and preparing for exams. Just upload your circuit diagram and let CircuitSeer dissect the layout, identify all components, and explain step-by-step solutions for configurations, enhancing both your understanding and efficiency.

Dive into the world of AI-driven electronic design with CircuitSeer. Explore the tool today to enhance your learning experience and embrace the cutting-edge of circuit analysis technology!

Technologies Used

YOLOv5

  • Description: YOLOv5 (You Only Look Once, version 5) is a state-of-the-art object detection system that excels in speed and accuracy for real-time applications.
  • Application: Adapted to detect and classify densely packed electronic components, such as resistors and capacitors, in CircuitSeer.
  • Benefits: Offers fast detection speeds and high accuracy, essential for the real-time analysis of circuit diagrams.

Python

  • Description: A versatile programming language widely used for its simplicity and powerful libraries.
  • Application: Powers the backend processes in CircuitSeer, handling data manipulation, model interaction, and server responses.

Flask

  • Description: A lightweight WSGI web application framework designed for easy start-up and scalability to complex applications.
  • Application: Manages web server requests in CircuitSeer, linking the client-side application with backend processing.
  • Benefits: Enables quick setup of web servers, with a high degree of customization available through various extensions.

Canny Edge Detection & Hough Transform

  • Description: Classical computer vision algorithms for detecting edges and lines.
  • Application: Used to delineate wiring and structural elements in circuit diagrams, aiding in the mapping of connections.
  • Benefits: Crucial for recognizing geometric structures in images, ensuring accurate layout identification in electronic circuits.

Project Overview

CircuitSeer is an AI-powered tool developed by a team of students under the AI Mentorship Program at the University of Texas at Dallas. The project harnesses cutting-edge technologies like YOLOv5 for object detection, and classical algorithms such as Canny Edge Detection and Hough Transform for circuit analysis. CircuitSeer’s core functionality revolves around the automated identification, classification, and analysis of electronic components in circuit diagrams. It offers a unique solution that simplifies the complexities of electronic design, particularly for educational purposes. The tool is designed to assist students and professionals alike in visualizing and solving electronic circuits efficiently, providing real-time feedback and detailed schematic insights.

Mentorship Experience

Mentoring a group of six ambitious students on the CircuitSeer project was an extraordinary journey. Each team member brought their unique skills and perspectives to the table, enriching the development process. Guiding such a diverse and large group towards a common goal was not only a challenge but also a profoundly rewarding experience. It was inspiring to see how each mentee engaged with the project, contributing to different facets from object detection to interface design, all while navigating the complexities of AI technology.

This experience was particularly enlightening as it underscored the importance of collaboration, perseverance, and innovation in achieving project objectives. The role of a mentor in such settings extends beyond technical guidance; it involves fostering a collaborative spirit, encouraging creative problem-solving, and supporting the professional growth of the mentees. The success of CircuitSeer is a testament to the collective effort and dedication of the team, and the project has been a significant step in their educational and professional development.

Witnessing the mentees apply their learning in real-time, overcome obstacles, and eventually deliver a functional and impactful tool was immensely satisfying. It affirmed the value of mentorship in academic and project-based settings, where practical application and hands-on experience are crucial. The CircuitSeer project not only delivered a valuable tool for electronic circuit analysis but also cultivated a learning environment that promoted growth, teamwork, and innovation.

Go Back To Projects