Metrics
2 File views/ downloads
9 Record Views
Thesis
Optimizing Circuit Board Inspection Through Comparative AI Model Analysis
University of West Florida Libraries
Master of Science (MS), University of West Florida
2026
Abstract
Automated optical inspection of printed circuit boards is a critical component of electronics manufacturing; however, traditional rule-based inspection systems struggle to adapt to variability in solder defects and production conditions. Advances in deep learning–based computer vision provide an opportunity to improve inspection accuracy and robustness through data-driven approaches. This thesis presents a comparative evaluation of modern object detection architectures for PCB solder defect detection.
A unified dataset pipeline was constructed to ensure consistent training and evaluation across all models. Each architecture was trained and evaluated using identical defect classes, dataset splits, and performance metrics. Quantitative evaluation included precision, recall, mAP, and confusion matrix analysis, alongside qualitative assessment of detection behavior.
The results reveal clear trade-offs between detection accuracy, computational efficiency, and deployment suitability. These findings provide practical guidance for selecting vision-based inspection architectures for automated PCB manufacturing systems.
Details
- Title
- Optimizing Circuit Board Inspection Through Comparative AI Model Analysis
- Resource Type
- Thesis
- Contributors
- Tarek Y Elsayed (Committee Chair)Bhuvaneswari Ramachandran (Committee Member)Yazan Alqudah (Committee Member)Jiaming Fu (Committee Member)
- Publisher
- University of West Florida Libraries
- Format
- pdf
- Number of pages
- 107
- Copyright
- Permission granted to the University of West Florida Libraries by the author to digitize and/or display this information for non-profit research and educational purposes. Any reuse of this item in excess of fair use or other copyright exemptions requires the permission of the copyright holder.
- Identifiers
- 99381757109006600
- Academic Unit
- Dr. Muhammad Harunur Rashid Department of Electrical and Computer Engineering; Hal Marcus College of Science and Engineering
- Language
- English
- Awarding Institution
- University of West Florida; Master of Science (MS)
- Theses and Dissertations
- Master of Science (MS), University of West Florida