PCB Defects Detection

This project focuses on the detection of PCB (Printed Circuit Board) defects using deep learning techniques, specifically utilizing YOLOv8 for object detection. The dataset comprises various types of PCB defects, including missing holes, mouse bites, open circuits, shorts, spurs, and spurious copper, which are crucial for ensuring the quality and functionality of PCBs in electronic manufacturing. The proposed system uses YOLOv8, a state-of-the-art object detection model, to efficiently identify and classify these defects. The back-end of the system is implemented in Python, leveraging Google Colab for computational power, while the front-end is designed with Streamlit to provide a user-friendly interface for visualization and interaction. The system aims to automate the defect detection process, improving the accuracy and speed of quality control in PCB manufacturing. This solution offers significant potential in reducing human error, increasing productivity, and ensuring the reliability of electronic products. Keywords: PCB defect detection, YOLOv8, deep learning, object detection, missing hole, mouse bite, open circuit, short, spur, spurious copper, Streamlit, Python, Google Colab, quality control.