pcb-defect-detection-using-yolov8x

PCB- Defect Detection using YOLOv8x a Research Project

https://github.com/gokulprasanth-m/pcb-defect-detection-using-yolov8x

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
    Found CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (5.1%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

PCB- Defect Detection using YOLOv8x a Research Project

Basic Info
  • Host: GitHub
  • Owner: GOKULPRASANTH-M
  • Default Branch: main
  • Size: 543 KB
Statistics
  • Stars: 0
  • Watchers: 0
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created 9 months ago · Last pushed 9 months ago
Metadata Files
Readme Citation

README.md

PCB-Defect-Detection-using-YOLOv8x

PCB- Defect Detection using YOLOv8x a Research Project In this project, we designed and implemented YOLOv8x-HICAUps, a cutting-edge deep learning model aimed at automating the detection of surface defects in Printed Circuit Boards (PCBs) with high precision and efficiency. The model introduces several key innovations:

HorNet Backbone: Enhances feature extraction from high-density PCB layouts by capturing intricate textures and micro-patterns.

CBAM Attention Module: Improves focus on defect-relevant regions by combining spatial and channel attention, leading to more accurate detection of subtle anomalies like mouse bites, spurs, and pinholes.

Attention-Based Upsampling: Retains fine-grained details during the decoding phase to avoid blurring of small defects and ensures better boundary preservation.

Lightweight Detection Head: Tailored for real-time inference on embedded hardware and edge devices, balancing speed and accuracy.

The model was extensively evaluated on standard PCB defect datasets and achieved a detection accuracy of 98.3%, outperforming state-of-the-art approaches. Designed with deployment in mind, YOLOv8x-HICAUps bridges the gap between academic research and practical manufacturing applications, offering a scalable, low-complexity, and high-performance solution for smart electronics inspection.

Owner

  • Login: GOKULPRASANTH-M
  • Kind: user

Citation (CITATION.cff)

cff-version: 1.2.0
message: "If you use this work, please cite it as below:"
authors:
  - family-names: Mounika
    given-names: M
  - family-names: Gokulprasanth
    given-names: M
  - family-names: Vadivu
    given-names: G
title: "YOLOV8X-HICAUPS: An Attention Based Approach for Accurate PCB Defect Detection"
version: "1.0"
doi: 10.33564/ijeast.2025.v09i11.013
date-released: 2025-06-15
type: article
journal: "International Journal of Engineering Applied Sciences and Technology"

GitHub Events

Total
  • Push event: 13
Last Year
  • Push event: 13