BoardVision: Real-Time Motherboard Defect Detection using YOLOv7 and Faster R-CNN

Files

MotherboardDefectDetection3444.pdf (1.8 MB)

Links to Files

Permanent Link

http://hdl.handle.net/11603/38812

Collections

UMBC Student Collection
UMBC Computer Science and Electrical Engineering Department
UMBC Faculty Collection

Author/Creator

Author/Creator ORCID

Date

2025-04-29

Type of Work

posters
Text

Department

Program

Citation of Original Publication

Brandon Hill and Solaiman KMA, “BoardVision: Real-Time Motherboard Defect Detection Using YOLOv7 and Faster R-CNN,” April 29, 2025.

Rights

This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.

Subjects

System Architecture
YOLOv7
Defect Detection
BoardVision
Faster R-CNN

Abstract

This poster introduces BoardVision, a real-time system for detecting motherboard defects using YOLOv7 and Faster R-CNN. Designed for reproducibility and educational use, the tool includes a GUI and supports video, image, and live webcam input. Evaluations show promising accuracy across defect classes with interactive performance.