PCB defect detection using deep learning model

This project leverages deep learning techniques for automated defect detection in printed circuit boards (PCBs) using the YOLOv8 object detection model. By training YOLOv8 on a specialized dataset of PCB images annotated with various defect types, the system can accurately identify and localize defects such as missing components, scratches, soldering errors, and other anomalies. The application provides a user-friendly web interface where users can upload PCB images, which are then processed by the trained model to detect and classify defects in real-time. The output includes annotated images highlighting defective regions and defect type predictions, enabling quick quality control and reducing manual inspection efforts in manufacturing. This approach demonstrates the potential of integrating advanced computer vision models into industrial inspection workflows to enhance reliability and efficiency in PCB quality assurance.