Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM68865
Volume:
10 |
11 |
Nov 2026
Pages:
1-6
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Information Science and Engineering
JNN College of Engineering, Shivamogga
Information Science and Engineering
JNN College of Engineering, Shivamogga
Information Science and Engineering
JNN College of Engineering, Shivamogga
Information Science and Engineering
JNN College of Engineering, Shivamogga
Information Science and Engineering
JNN College of Engineering, Shivamogga
Information Science and Engineering
JNN College of Engineering, Shivamogga
Printed circuit boards (PCBs) are essential components of electronic devices, and their quality directly affects the reliability and performance of electronic systems. Conventional PCB inspection methods often rely on manual examination, which can be time-consuming and inconsistent when identifying small defects or missing components. This paper presents an artificial intelligence-based PCB inspection system using the YOLOv8 object detection framework. The system consists of two independent detection branches. The bare-PCB branch identifies six defect categories: missing hole, mouse bite, open circuit, short, spur, and spurious copper, using a publicly available PCB defect dataset. The assembled-PCB branch detects missing resistors and missing capacitors using a manually collected dataset. Both models are integrated into a web-based inspection application developed using Flask. The application supports image upload and camera-based image capture and displays detection results through bounding boxes, class labels, and confidence scores. The bare-PCB model achieved a reported mean Average Precision of 94.7% at an Intersection over Union threshold of 0.5 and 51.0% across thresholds from 0.5 to 0.95. The assembled-PCB model is evaluated independently to assess its ability to identify missing components. The integrated system provides a practical framework for assisting PCB quality inspection through automated visual detection.
KEYWORDS
This paper presents a YOLOv8-based approach for detecting six bare-PCB defect classes: missing hole, mouse bite, open circuit, short, spur, and spurious copper. The selected YOLOv8s model achieves a reported mAP@50 of 94.7% and mAP@50–95 of 51.0%. Integration with a Flask-based web application enables visualization of defect labels, bounding boxes, and confidence scores.The system architecture also supports assembled-PCB inspection for missing capacitors and resistors using a separate model.
[1] X. Chen, Y. Wu, X. He, and W. Ming, “A Comprehensive Review of Deep Learning-Based PCB Defect Detection,” *IEEE Access*, vol. 11, 2023. [2] Q. Ling and N. A. Mat Isa, “Printed Circuit Board Defect Detection Methods Based on Image Processing, Machine Learning and Deep Learning: A Survey,” *IEEE Access*, 2023. [3] Q. Ge, R. Wu, Y. Wu, and H. Liu, “A Class-Incremental Learning Method for PCB Defect Detection,” *IEEE Transactions on Instrumentation and Measurement*, vol. 74, 2025. [4] Z. Yan, R. Hao, B. Huang, L. Zhu, and H. Pan, “A Domain Incremental Learning Framework for PCB Continuous Defect Detection,” *IEEE Transactions on Instrumentation and Measurement*, vol. 74, 2025. [5] W. Wu and colleagues, “A High-Performance and Enhanced Generalization Small Target Defect Detection Method for PCB Boards Based on YOLO-EMAC,” *IEEE Transactions on Instrumentation and Measurement*, 2025. [6] X. He and M. Xie, “ABF-YOLO: A Fine-Grained PCB Defect Detection Framework Integrating Axial Attention and Bidirectional Feature Fusion,” *IEEE Transactions on Consumer Electronics*, vol. 71, no. 3, 2025. [7] X. Liu, “An Adaptive Defect-Aware Attention Network for Accurate PCB-Defect Detection,” *IEEE Transactions on Instrumentation and Measurement*, vol. 73, 2024. [8] L. Luo and colleagues, “CIFPNet: Contextual Information Aggregation and Foreground Prototype Guidance Network for Few-Shot PCB Defect Detection,” *IEEE Transactions on Instrumentation and Measurement*, 2025. [9] “Few-Shot PCB Surface Defect Detection Based on Feature Enhancement and Multi-Scale Fusion,” *IEEE Access*, 2022. [10] “PCB Defect Detection Method Based on Transformer-YOLO,” *IEEE Access*, 2022.
Publication Date
11/11/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
2
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...