Skip to content

Hazrat-Ali9/Deep-Learning-AOI-for-PCBs-Real-Time-YOLO-Detection-of-Missing-Holes-Mouse-Bites-Shorts-and-Spurs

Folders and files

NameName
Last commit message
Last commit date

Latest commit

ย 

History

1 Commit
ย 
ย 

Repository files navigation

โœจ Key Features

๐Ÿ”Ž Real-Time YOLO Detection โ€“ Detects PCB defects instantly during inspection

๐Ÿ•ณ๏ธ Defect Categories โ€“ Identifies missing holes, mouse bites, shorts, and spurs

๐Ÿ–ผ๏ธ Image Preprocessing โ€“ Data augmentation, resizing, normalization for better accuracy

๐Ÿค– Transfer Learning โ€“ Fine-tuned YOLO models for PCB-specific datasets

๐Ÿ“Š Model Evaluation โ€“ Precision, Recall, mAP, confusion matrix for defect classification

โšก High-Speed Inference โ€“ Optimized for real-time industrial AOI workflows

๐Ÿ› ๏ธ Scalable Integration โ€“ Can be embedded into PCB assembly lines with cameras

๐Ÿ“ˆ Visualization Tools โ€“ Bounding boxes, defect heatmaps, and confidence scores

๐Ÿงฐ Tech Stack

Programming: Python ๐Ÿ

Deep Learning Frameworks: YOLOv5 / YOLOv7 / YOLOv8, PyTorch, TensorFlow

Computer Vision: OpenCV, Albumentations

Data Science Tools: NumPy, Pandas, Matplotlib, Seaborn

Deployment: ONNX Runtime, TensorRT, Flask/FastAPI for API integration

๐Ÿ“ Project Structure ๐Ÿ“ dataset/ # PCB defect dataset (train/val/test) ๐Ÿ“ notebooks/ # Jupyter notebooks for model training & evaluation ๐Ÿ“ models/ # Trained YOLO models & weights ๐Ÿ“ src/ # Scripts for preprocessing, training, detection ๐Ÿ“ results/ # Detection outputs, metrics, graphs ๐Ÿ“ deployment/ # Code for real-time inference & API integration

๐Ÿš€ Getting Started git clone https://github.com/yourusername/Deep-Learning-AOI-for-PCBs-Real-Time-YOLO-Detection-of-Missing-Holes-Mouse-Bites-Shorts-and-Spurs.git cd Deep-Learning-AOI-for-PCBs... pip install -r requirements.txt python detect.py --source test_images/

๐Ÿ“Œ Use Cases

๐Ÿญ Electronics Manufacturing โ€“ Automated PCB inspection on production lines

๐Ÿ”ง Quality Control โ€“ Reduce human errors in PCB defect identification

๐Ÿ“Š Research & Development โ€“ Benchmarking PCB inspection using deep learning

๐ŸŽ“ Educational Projects โ€“ Learning deep learning applications in industrial AI

๐Ÿค Contributing

Contributions are welcome! Add datasets, improve detection accuracy, or optimize deployment and submit a PR.

๐Ÿ“œ License

MIT License โ€“ Open-source for industrial AI innovation and research.

โญ Support

If this project helps you, please star โญ the repo and share it with the AI + Electronics community.

About

โšฝ Deep โšพ Learning ๐ŸฅŽ AOI PCBs is ๐Ÿ€ an Automated ๐Ÿˆ Optical ๐ŸŽณ Inspection โ›ธ system Printed ๐ŸŽฎ Circuit Boards โœˆ using Deep ๐Ÿš€ Learning ๐Ÿš YOLO It enables ๐Ÿšข real time ๐Ÿ›ธ defect detection ๐Ÿ›ฅ of critical PCB ๐Ÿšˆ issues like ๐Ÿš’ missing holes ๐Ÿšž mouse bites ๐Ÿฆ shorts and ๐Ÿงฑ spurs improving ๐Ÿซ‘ manufacturing ๐Ÿ… accuracy reducing ๐Ÿ human inspection errors

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors